ArticlePDF AvailableLiterature Review

Predictive Maintenance for Pump Systems and Thermal Power Plants: State-of-the-Art Review, Trends and Challenges


Abstract and Figures

Thermal power plants are an important asset in the current energy infrastructure, delivering ancillary services, power, and heat to their respective consumers. Faults on critical components, such as large pumping systems, can lead to material damage and opportunity losses. Pumps plays an essential role in various industries and as such clever maintenance can ensure cost reductions and high availability. Prognostics and Health Management, PHM, is the study utilizing data to estimate the current and future conditions of a system. Within the field of PHM, Predictive Maintenance, PdM, has been gaining increased attention. Data-driven models can be built to estimate the remaining-useful-lifetime of complex systems that would be difficult to identify by man. With the increased attention that the Predictive Maintenance field is receiving, review papers become increasingly important to understand what research has been conducted and what challenges need to be addressed. This paper does so by initially conceptualising the PdM field. A structured overview of literature in regard to application within PdM is presented, before delving into the domain of thermal power plants and pump systems. Finally, related challenges and trends will be outlined. This paper finds that a large number of experimental data-driven models have been successfully deployed, but the PdM field would benefit from more industrial case studies. Furthermore, investigations into the scale-ability of models would benefit industries that are looking into large-scale implementations. Here, examining a method for automatic maintenance of the developed model will be of interest. This paper can be used to understand the PdM field as a broad concept but does also provide a niche understanding of the domain in focus.
Content may be subject to copyright.
Predictive Maintenance for Pump Systems and
Thermal Power Plants: State-of-the-Art Review,
Trends and Challenges
Jonas Fausing Olesen 1,2 and Hamid Reza Shaker 1,*
1Center for Energy Informatics, University of Southern Denmark, 5230 Odense, Denmark;
2Ørsted, Markets & Bioenergy, Asset Risk Management, Kraftværksvej 53, 7000 Fredericia, Denmark
Received: 8 April 2020; Accepted: 21 April 2020; Published: 24 April 2020
Thermal power plants are an important asset in the current energy infrastructure,
delivering ancillary services, power, and heat to their respective consumers. Faults on critical
components, such as large pumping systems, can lead to material damage and opportunity losses.
Pumps plays an essential role in various industries and as such clever maintenance can ensure
cost reductions and high availability. Prognostics and Health Management, PHM, is the study
utilizing data to estimate the current and future conditions of a system. Within the field of PHM,
Predictive Maintenance, PdM, has been gaining increased attention. Data-driven models can
be built to estimate the remaining-useful-lifetime of complex systems that would be difficult to
identify by man. With the increased attention that the Predictive Maintenance field is receiving,
review papers become increasingly important to understand what research has been conducted and
what challenges need to be addressed. This paper does so by initially conceptualising the PdM field.
A structured overview of literature in regard to application within PdM is presented, before delving
into the domain of thermal power plants and pump systems. Finally, related challenges and trends
will be outlined. This paper finds that a large number of experimental data-driven models have
been successfully deployed, but the PdM field would benefit from more industrial case studies.
Furthermore, investigations into the scale-ability of models would benefit industries that are looking
into large-scale implementations. Here, examining a method for automatic maintenance of the
developed model will be of interest. This paper can be used to understand the PdM field as a broad
concept but does also provide a niche understanding of the domain in focus.
machine learning; predictive maintenance; remaining useful lifetime; state of the
art review
1. Introduction
Production facilities are built with increasing complexity to satisfy the increase in demand for
quality products and availability. To deliver on this, manufacturers need to understand the current state
of their assets to avoid unnecessary downtime [
]. The maintenance procedure can be compared to the
health care procedures conducted on man. If conducted efficiently, the system will be operating under
fewer restrictions and prove to have higher performance. This means cost reductions, resource-saving,
increased life expectancy, and reduced downtime. On the other hand, poor maintenance management
can result in a reduction in safety, reputation, and quality of product delivered [
]. Hence, the question
becomes when maintenance should be deployed. Traditionally maintenance had been done either
reactive or preventive [
]. The reactive maintenance approach allows components and machinery to
run till failure. The consequence is long downtime and thus a market opportunity loss. The preventive
maintenance approach deploys maintenance based on a time or cycle metric. This is seen in cars
Sensors 2020,20, 2425; doi:10.3390/s20082425
Sensors 2020,20, 2425 2 of 25
going x kilometers before going for service or jet engines doing x cycles. This significantly reduces
downtime, as the metric is decided based on expert knowledge. The downside is that asset operators
do not know whether the maintenance is deployed efficiently [
]. If the engine could go longer
without maintenance a result would be poor resource management. To answer the when, a just-in-time
maintenance approach would be optimal [5].
1.1. The Role of Power Plants and the Need for Pumps
Combined heat and power plants, CHP, are an important asset in current energy infrastructures,
as they can provide power, grid stability, and heating simultaneously. With increasing amounts of
intermittent renewable capacity being installed both power grids and CHP operators are pressured.
Power grids face larger instability, while CHP operators are pressured by low electricity prices due to
cheap renewable energy [
]. Hence, power grid operators depend on the availability and quality of
the product provided by the CHPs, while CHP units strive to stay competitive. Though depending on
the energy market framework, the CHPs tend to be competing with each other and thus the plant with
higher efficiency or flexibility tend to be activated. This means that asset managers at all time need to
know, which plants require maintenance to reduce downtime at high electricity price hours. If a critical
component fails at a bad time, it can cause severe damage and represent a significant loss. Hence,
knowing when to conduct maintenance to reduce downtime is of great importance. CHPs larger
than 300 MW can have more than 100 pumps installed, varying in size and type, which speaks to the
complexity of the system [
]. A feedwater pump failing results in a large capacity reduction or full
shut-down depending on the system setup, which in turn presents an opportunity loss and safety
issue for asset operators. Avoiding this is desirable. Pumps are utilised in various fields and comes
in various forms, but tend to be critical components for operation. Examples are seen in seawage
industries and aviation [9,10].
1.2. The Field of Prognostics and Health Management
Continuous improvements in information and communication technology, ICT, have increased
data accessibility and in turn created a basis for Industry 4.0. This allows for increased automation
and data exchange, through increased deployment of Internet-of-Things, IoT, sensors [
]. The field
dealing with these complex systems and benefits from the development in technology is the study of
Prognostics and Health Management, PHM. PHM present tools to understand complex systems,
develop health indicators, and predict future complications. PHM has allowed for conducting
Condition-based Maintenance and Predictive Maintenance, PdM [1,2].
The prognostics within maintenance have been studied to a great degree within literature and
has been found to be gaining interest, as new papers are being released at a rapid pace. Figure 1
depicts the trend on three recognised databases considering PdM. This emphasizes the importance
of literature reviews. The focal point of literature reviews is to recap what has been investigated,
while also determining what challenges and unmet needs require examination.
Prior art conducting reviews within the field of PHM can be found in Table 1. It was found that
literature reviews covered a great area of interests, such as algorithms, applications, decision-making,
implementation, etc. The thing they have in common is that they are scoped broadly to cover various
industries and fields. Thus, the purpose and novelty of this paper is the focus it provides on specific
topic. Carvalho et al. [
] presents a structured review of new literature presented in the years after
2014 and does so in a general manner, so the reader can get a general understanding of what moves
within the field. Merkt et al. [
] studies various maintenance approaches and the different applications
that PdM might have. This is done by studying the full cycle of developing a successful model. Lee
et al. [
] outlines a framework for considering to what extent a company will be gaining value from
various PdM approaches. It more specifically dives into rotary components and their common failure
types, before presenting a set of case studies. This paper will provide an understanding of newly
published art within the PdM field and then delve into PdM within pumping systems and CHPs. This
Sensors 2020,20, 2425 3 of 25
allows for a niche understanding of the differences between the general trends and the specific studied
field. This approach can be applied to other fields or industries to evaluate gaps.
Figure 1.
The published papers on predictive maintenance from 2000 to 2020 on MDPI, ScienceDirect
and IEEE.
Table 1. An overview of a set of review papers in relation to the field of PHM.
Reference Year Focus
[13] 2019 Structured PdM literature review of 30 papers and their algorithms.
Applications for RF, ANN, SVM, k-means are presented.
[14] 2019 A review of decision making algorithms and their applications.
[15] 2019 Review and proposition of efficient step-wise method for
companies to deploy models on historical data and digital twins.
[4] 2019 Review of various maintenance strategies, their application
and use-cases with focus on the full cycle of creating PdM models.
[16] 2018 An introduction to CDM with a strong overview over what
possibilities it provides.
[2] 2014
A holistic overview of PHM. Present tools for companies
to consider to evaluate what degree of maintenance they need.
An overview of common fault types on rotary
equipment and a list of algorithms with their use-case.
This paper investigates the literature within the field of PdM, creating a structured overview
of current applications. A deep dive into applications found on pumping systems will be provided,
before elaborating on how this is or could be applied to a CHP setting. The findings on pumping
systems can be extended to other fields. The paper will among other outline the current trends and
challenges. One of the focus points will be the scale-ability of the models as systems tend to rely on
more than one pumping system. The paper is structured as follows; Section 2introduces the concept
of PdM and puts it into context for the reader. Furthermore, shortly introduce how models can be
developed and what is required of the model owner. Following this, state-of-the-art applications will
Sensors 2020,20, 2425 4 of 25
be presented alongside the advantages and limitations of the algorithms considered. Section 3will
then delve into the applications found within pumping systems and CHPs, this is done by presenting
an initial overview of common faults within pumps. Section 4will be presenting the challenges that
PdM currently faces. Section 5will present the future trends found for PdM and what unmet needs
that require investigation. Section 6finalises the paper with a conclusion on the review.
2. Predictive Maintenance
2.1. Defining Predictive Maintenance
To better grasp PdM, the authors have decided to initially define the concept. According to Oxford
Learner’s Dictionaries the adjective predictive is formally defined as: “Connected with the ability to
show what will happen in the future” and maintenance is defined as: “The act of keeping something
in good condition by checking or repairing it regularly” [
]. Hence, combining the two will allow
for the following definition of PdM; “the act and ability to keep something in a good condition by
understanding what happens in the future”.
The following definition of PdM is provided by Mobley [
]; “Predictive Maintenance is a
philosophy or attitude that, simply stated, uses the actual operating condition of plant equipment and
systems to optimize total plant operation. A comprehensive predictive maintenance management
program uses the most cost-effective tools (e.g., vibration monitoring, thermography, tribology) to
obtain the actual operating condition of critical plant systems and based on this actual data schedules
all maintenance activities on an as-needed basis.” Therefore, PdM strives to identify trends, anomalies,
degradation at an early stage, so that sufficient counter measurements can be deployed. The term
PdM and CDM has found different use in various papers. Some define it to differ, while others use it
interchangeably. This paper will be using the later, as the field of CDM has somewhat developed into a
PDM-CDM field. The PDM-CDM considers a broader area of both fault detection, diagnostic, and
2.2. Methods of the Predictive Maintenance Field
Several methods of doing PdM exists, where each approach has a set of pros and cons. It is
commonplace to establish system models as they automate the prognostics and can continuously
monitor complex system effectively, furthermore, provide indicators of potential risks. Figure 2
presents an overview of common model types utilised. The physical model approach has in current
literature been referred to as a digital twin [
]. The physical laws and formulas governing the
system is utilised to establish a model that represents the machinery with great detail. The benefit
of such models are the accuracy and knowledge of the system that it provides. White-box models
allow for the identification of faults, as the full system is described. This type of modelling have
been found to have high accuracy. The weakness of digital twins is the time they consume before
being established [
]. Knowledge-based models enable the use of domain expert knowledge and
deploy it in models, this can be beneficial as it can assist the prediction process [
]. Data-driven
models mainly apply machine learning, soft computing, and statistical theory to establish a model that
takes in historical operational or condition data. Though, in many cases not as accurate as physical
models, data-driven models can achieve high accuracy. Relative to the amount of time it takes to
establish a digital twin, a data-driven model can be developed fast. The weakness of data-driven
models is their need for a large amount of high-quality data [
]. If the data is faulty, it will be reflected
in the model and the accuracy will deteriorate. Pre-processing methods exist to prepare data and
up the quality. Physical and knowledge-based models are as an initial stance not considered to be
within the scope of the paper, but is still included to the extent that some papers propose a hybrid
approach. Hybrid models combine two approaches and hence utilises the strength of each method
to overcome the weaknesses of the other [
]. The focal point of this paper is within data-driven
models, but the authors saw the need to mention other applicable approaches and recommends the
Sensors 2020,20, 2425 5 of 25
interested reader to consider the following book by Lughofer and Sayed-Mouchaweh [
]. Lughofer
and Sayed-Mouchaweh [
] presents the concepts and applications of the various PdM approaches
and introduces a set of case studies.
Figure 2. A representation of model types that can be developed and utilised within the PdM field.
2.3. Framework for Developing a Machine Learning Model
This section will give an overview of how literature tend to approach creating a data-driven model.
First, understanding what type of data you have at your disposition will allow for narrowing down
what type of model will be suitable and what information you can achieve. Figure 3gives an overview
of what type of approaches exists. Initially identify whether the data is labelled. If labelled, a broad set
of options are available within the realm of supervised methods. If unlabelled, the typical problem
type will be that of unsupervised, which allows for clustering. If a different type of information is
desired, then manual labelling is possible or it would require a change to the current management of
data, by creating a metric that identifies conditional data of the monitored system.
Figure 3.
An overview of various methods that can be chosen depending on what information is
desired and to what extent data is available.
It seems that a consensus on how a model should be build have somewhat been reached within
literature. Though, the order of the steps might be defined or prioritised differently, the same
steps tend to be included. Figure 4depicts an overview of the common steps taken to develop
Sensors 2020,20, 2425 6 of 25
a machine learning model. Data Acquisition refers to the gathering of data. With the deployment
of communication technology, sensors have been a key source of data, sending and storing data
in databases. Data Preprocessing is the steps taken to prepare the data. A taxonomy, suggested by
Cernuda [
], prepares six steps to consider and is displayed in Figure 5. The exact order depends on
the data being worked on. Choosing Model & Training considers the amount of available models and
the task of training it. In some literature, these are split into two steps, which the authors also consider
a possibility. The amount of models available has rapidly increased and gaining an overview can be a
challenge, thus finding an appropriate model requires testing. In the paper by
Lee et al. [2]
, a table over
a set of models and tools have been proposed alongside their corresponding strengths and weaknesses.
A paper by Fernandez-Delgado et al. [
] present an extensive study on various machine learning
techniques. Training can often be used as a basis for choosing a model, due to the training commonly
giving an indication of the model performance. Methods commonly deployed in literature to evaluate
training performance is the k-fold method and hold-out method. The k-fold method splits the data
such that a k
of the data is used to predict upon and the rest for training, this being iterated k times.
The hold-out method is often recommended for larger data sets. This method takes out a percentage
of the data to be predicted upon, where the rest is used for training. Model Evaluation considers the
performance of the model on an unseen test data set. This allows the developer to determine how
the model potentially will perform prior to being deployed. Analysing whether the model accuracy
found in training aligns with testing. Parameter Tuning allows for optimising the accuracy of a model.
Machine learning models operate with different parameters to allow for flexibility and to increase
or reduce bias. The last two steps consider deploying and maintaining the model. Deploying the
system can relate to installation or integration of software, while it can also refer to soft values, such as
Change Management for the customer to adopt the new tool and use it for decision-making. Model
maintenance considers that systems often are dynamic, where a common assumption on a model is
that the system is static [27].
Figure 4.
An overview of the process for developing a successful machine learning model, be it in a
PdM setting or another.
Sensors 2020,20, 2425 7 of 25
Figure 5.
A suggested Taxonomy for Data Preprocessing. The exact order does not necessarily matter
and each step should be considered whether necessary for the application at hand.
Another common acknowledgment is that the individual case study requires a different approach.
Despite this, efforts have been invested in developing a structured approach to create and streamline
model construction. The authors recommend the interested reader to consider Lee et al. [
] for an
overview of what considerations should be done before determining whether predictive maintenance
is something that should be deployed, furthermore on how to approach it effectively. The above
discussed problem was popularised as the No Free Lunch Theorem by Wolpert and Macready [
] for
optimisation. This refers to that no single algorithm is superior to the other, as they each serve a
purpose and is case dependent.
2.4. Overview of Methods
This section will be introducing relevant literature on successful applications of predictive
maintenance. The concept of each highlighted ML method will be introduced shortly before relevant
literature will be presented. Machine learning methods tend to be grouped by their “way of
functioning”, e.g., tree-based models, such as decision trees, or neural networks with their various
architectures. The authors have tried to take this grouping-by-similarity approach, but the authors are
aware that some might fall into two categories or not fall into any category. An overview of relevant
literature categorised can be seen in Table 2. The reader should be aware that papers can have applied
several types of methods for either testing or comparison, this allows for the paper to be mentioned
several times within the list. Listing the papers show a fair distribution of papers across all categories,
but a preference towards research within ANN & DL can be seen as it has been increasing in popularity.
Furthermore, it is found that a significant amount of papers are presented in a experimental setting and
that approximately 30% of the studied literature utilised vibration data to determine the health status
of a system. Though, the majority of prior art is presented in a experimental setting, the applications
does span over a large area, which shows the flexibility of the PdM field.
2.4.1. Stochastic Algorithms
Stochastic data-driven models within prognostics are often considered within the Bayesian
category. Rather than giving a single estimated output on the current system health, it gives a
probability distribution of possible likely options [
]. In this way, the Bayesian method can present
the current state of the system, but can also evaluate future trends before a given threshold. Stochastic
algorithms are mainly used within degradation models and the most common Bayesian network
algorithms are Particle Filters, Kalman Filters, and hidden Markov models [29,30].
Sensors 2020,20, 2425 8 of 25
Table 2.
A list of studied papers categorised by the characteristics of the algorithm applied. The list is an effort on displaying what is moving within the field, but does
not reflect all available algorithms.
Category Algorithm Area of Application Type of Machinery Data Reference
ANN & DL MLP Experimental Motor Vibration [31]
Aeropropulsion system & truck engine Nasa & Scania Trucks [32]
Battery Capacity [33]
Transportation Rail Oil-level, voltage, pressure, temperature [34]
ELM Wind Turbines Gear Vibration [35]
KELM Power Production Hydropower generator Vibration [36]
SW-ELM Experimental - PHM Challenge 2008 [37]
CNN Experimental Aeropropulsion system & truck engine Nasa & Scania trucks [32]
Buildings Fans Electrical, mechanical, temporal values [38]
Milling Cutting machinery Force, feed rate, speed [39]
(LSTM)-RNN Experimental Aeropropulsion system & truck engine Nasa & Scania trucks [32]
Turbofan engine Nasa [40,41]
Motor bearings Vibration [42]
Battery Capacity [43]
TDNN Experimental PEMFC Voltage [44]
SFAM-ANN Rotational mechanical assets Bearings Vibration [45]
Stochastic DLM w. BN Transportation Aircraft aircondition Airplane Condition Monitoring System (temperature) [46]
Markov Experimental - - [47]
Transportation Rail - [29]
KF Experimental Battery - [48]
Voltage, current, capacity [30]
SUKF Experimental Bearings Vibration [49]
EKF Experimental Battery - [50]
PF Experimental Battery - [50]
Voltage, current, capacity [30]
DBF Stainless steel industry Hot rolling process (drums) Density, temperature, pressure, power, force [51]
Sensors 2020,20, 2425 9 of 25
Table 2. Cont.
Category Algorithm Area of Application Type of Machinery Data Reference
Statistical LR Experimental Industrial radial fans Vibration, rotational speed, temperature, pressure [52]
Milling Cutting machinery Vibration [53]
RFR Experimental Industrial radial fans Vibration, rotational speed, temperature, pressure [52]
Milling Cutting machinery Vibration [53]
SR Experimental Industrial radial fans Vibration, rotational speed, temperature, pressure [52]
ARMA Experimental PEMFC Voltage [44]
ARIMA Experimental Battery - [50]
RVM Experimental Battery - [50]
SVR Experimental Battery Capacity [54]
SVM Experimental Bearings Vibration [55]
LS-SVM Refinery Destillation process - [56]
LS-SVM NAR Food industry Vertical form fill and seal machine Vibration, thermal imaging [57]
Fault Detection & SVM Agro-industry Harvester Vibration [58]
Fault Classification DT Transport Rail ERP system data, conditional data [59]
RF Transport Rail ERP system data, conditional data [59]
Milling Cutting machinery Speed, feed rate, depth [60]
RBF-SVM ion-Implanter tool Filament Current [61]
Sensors 2020,20, 2425 10 of 25
Degradation can be difficult to determine, especially, when the progress status is hidden.
This means that a degradation can to some extent seem linear, but in reality contain non-linear
elements. Furthermore, data can be noisy to the extent that it greatly influences the predicted RUL and
hence reduces accuracy. Son et al. [
] delves into this issue. A method is proposed to utilise condition
monitored data to predict the RUL with an acceptable error. The RUL is estimated by deploying a
model based on a constrained KF model. To do so, a set of inequality restraints are set up to achieve
the desired accuracy. To verify the method, it is tested on a case study of an automotive lead-acid
battery. Qiu et al. [
] also studies a battery, but looks at both state of charge, state of health, and RUL.
To improve the accuracy of the prediction, BS-SRCKF is deployed for the state of charge, which in turn
is combined with MHKF and an EKF to do a joint estimate of the state of charge and state of health.
The state of health values are then utilised in a particle filter that relies on an improved cuckoo search
to determine the RUL.
In an alternative approach, Xue et al. [
] deploys an AUKF alongside genetic algorithm that
optimises the parameters for a SVR model. The AUKF serves the purposes of calculating the process
noise covariance and observation noise covariance, this is done continuously over the time series. The
method is verified on a battery data set provided by NASA.
In the study proposed by Ruiz-Sarmiento et al. [
], machinery degradation in the hot rolling
process is studied. This is done by applying a Bayesian Filter. This utilises expert knowledge along
side historical data to increase the accuracy of the predictions. The filter deployed is called a Discrete
Bayes Filter. The findings of the paper result that this hybrid model relying on expert knowledge and
machine learning theory increases the overall accuracy than they could individually.
2.4.2. Statistical Algorithms
Statistical data-driven models within prognostics are relatively simple trend extrapolation.
They rely on condition monitoring data to create a trend curve from a single dimension time series that
then reflects the degradation of health for the asset. Where stochastic algorithms give a probability
distribution as an output, the statistical algorithms give a single specified output. A common algorithm
is ARIMA, but it is also possible to apply regression techniques [22].
SVM sees its use in both classification and regression problems. In the paper by
Yan et al. [55]
, the
RUL of bearings is estimated based on a classification. This is done by splitting the degradation into 5
categories. The method requires a dimensionless input. This is achieved by calculating the RMS for the
vibration data. To evaluate the model, data from a public data set is utilised. The data set considered
are from IMS and PRONOSTIA. The model performs equally to better than other models proposed to
estimate RUL.
In a paper by Susto et al. [
], SVM is utilised to classify whether the machinery is in need of
maintenance. The machinery in consideration is that of an ion-implanter tool. The base case is the
current PvM scheme. The study finds that the PdM approach can perform equally to better than
the presented PvM scheme. In an approach to detect faults early, LS-SVM Regression is applied to
a Vertical Form Fill and Seal. The paper by Langone et al. [
] initially applies an unsupervised
clustering algorithm, KSC, to initially identify anomalies within the data set, before applying the
LS-SVM regression for prognostics. The model successfully detects when the dirt is building up within
the machinery.
In the study by Li et al. [
], LS-SVM is applied in an alternative manner to a distillation process.
The data set is based on a moving-window and hence applies just-in-time maintenance. Here the work
focuses on creating an online soft sensor tool that allows for monitoring the distillation process. A
comparison between applying LS-SVM as a static and dynamic version is done for presenting the
results. The static LS-SVM arrives at a
of 0.995 with a RSME 1.7991, where the dynamic version,
with the largest moving window, presents a R2of 0.999 and a RMSE of 0.062.
An alternative approach proposed by Zhou et al. [
], considers algorithms across the categories
of statistical and ANN. The RUL prediction is conducted on a PEM fuel cell. The prediction is divided
Sensors 2020,20, 2425 11 of 25
into three phases. The first phase deals with non-stationary trends by deploying PAM. The second
phase, the order of an ARMA model is estimated and deployed to filter the linear degradation elements
in the data. The final phase utilised the leftover non-linear elements to train a TDNN. The paper finds
the model to predict RUL with high confidence.
2.4.3. Artificial Neural Network and Deep Neural Network
The idea of ANN stems from the functionality of the human brain. The nervous system is the
driver behind everything that a human does and the nervous system consists of neurons. An ANN
replicates this by having a set of layers, where each layer consists of neurons. Each layer is connected
and can receive and transmit signals, corresponding to the synapse within the nervous system.
Each connector has a weight, the neurons have an activation function and a threshold value. These are
the parameters considered within ANN. As technology has developed and ANN has taken on
increasingly complex tasks, a new term has been given to more complex ANN, which is called
Deep Neural Network. The most distinct difference between the two terms is the complexity, referring
to the architecture of the networks and the number of layers that it may contain [22,63,64].
In a paper presented by Silva and Capretz [
], two fans are studied by applying CNN. CNN is
typically known for being applied to image recognition, but is in an alternative approach applied to
fault detection and predictive maintenance. The features used are divided into electrical, mechanical,
and temporal. Initially, features are one-dimensional, hence a data transformation is required. The
paper is inspired by Wang and Oates [
] and Chen et al. [
] to try GAF and Moving Average Mapping,
respectively, and converts the data into two-dimensions. The intent is to allow for better knowledge on
the relationship between features. CNN is applied and finds an accuracy of 95% and 98% for the two
fans. The proposed method reports that it outperforms traditional methods such as RF, SVM, and MLP.
In a study proposed by Markiewicz [
], predictive maintenance of induction motors is considered.
The paper touches upon the issues of data gathering and storage, as it is an energy intensive process.
Hence, Markiewicz [
] presents a solution where predictive maintenance is done locally on a set of
ultra-low power wireless sensors. This is possible with a reduced computational complexity from
applying a compressed RNN. For their cell, LSTM is applied as they argue that it does not suffer from
a vanishing or exploding gradient problem [
]. By applying a compressed RNN algorithm they found
an accuracy of approximately 92% and that this was comparable or at a better performance than other
algorithms e.g., KNN. This approach moreover benefited from the lowered energy consumption.
Zhang et al. [
] investigates a degradation model on bearing performance by applying LSTM
RNN. The model builds on vibration data, but also introduces an alternative indicator, namely
“waveform entropy”. Entropy can be for a discrete instance of random vector X be defined as follows:
p(xi)·ln(p(xi)) (1)
where the
is the entropy,
is the number of elements in X,
is a single element of X, and
the probability mass function. The paper sets out to develop a dimensionless indicator. This is due to
e.g., load and speed not only resembling the health of a system, but also reflects the current operating
condition. Inspired by Ali et al. [45], a waveform entropy can be calculated:
Here WFE is the waveform entropy,
is the waveform factor at time instance
, and
is the
length of the sliding window. This method benefit from not requiring signal decomposition, such as
other time-frequent domain features. WFE is a local mean of logarithmic vibration energy. Hence,
a strong representation of the state of the vibration levels. The paper presents three steps for predictive
Sensors 2020,20, 2425 12 of 25
maintenance. Fault detection, fault classification, and a degradation model. The WFE supports this
and gives great results.
2.4.4. Clustering
Clustering represents a category of unsupervised algorithms, which objective is to find clusters
within a data set. Algorithms typically rely on a centroid or hierarchical approach to determine the
clustering of data that reflects the shortest distance internally and the largest distance between clusters.
Examples of algorithms are k-means, Expectation Maximisation, Hierarchical Clustering.
As clustering is unsupervised, the main purpose of clustering algorithms is to find golden nuggets
within the data. In a PdM setting, the main goal of clustering becomes to detect failure and anomalies
within data. In a paper by Uhlmann et al. [
], k-means is deployed in a supervised setting to see the
performance of detecting faults on a Selective Laser Melting machine tool.
Another approach is using clustering alongside other algorithms. This is done in the work by Cao
et al. [
]. Here fuzzy clustering is deployed to determine the severity of a failure, before deploying
semantic technologies to investigate the time of the failure. Similarly,
Daher et al. [70]
, applies fuzzy
C-means alongside ANFIS to detect the RUL of a distillation column.
2.5. Advantages and Limitations
In this section, some of the strengths and weaknesses of the investigated algorithms will be
elaborated upon. Considering that the various types differ greatly, each has its purpose and application.
Table 3lists some general advantages and limitations of the three categories. This is not a complete
list, as the individual architecture within ANN & DL and algorithm within regression present a set of
strengths and weaknesses. This is considered out of scope for this paper. For a look into benchmarking
of ML, the reader is recommended to visit Olson et al. [
]. Furthermore,
Fernandez-Delgado et al. [26]
present a comparison of 179 machine learning algorithms on various data sets. Where Ahmed et
al. [
] looks at an empirical comparison of time series forecasting within the machine learning domain.
This paper will proceed to discuss some of the specific advantages and limitations found within the
literature of the various case studies.
Table 3.
An overview of some of the general advantages and limitations of the algorithms within the
given categories [
]. As individual algorithms present their own set of strengths and weaknesses
the reader is recommended to study the individual algorithm as well.
Category Advantage Limitation
ANN Great w. large dataset Black box model
Handles noisy data Requires a large dataset
Limited/no need for pre-processing Computational expensive
Adaptive nature
Deals w. nonlinear & complex tasks
Various architectures
Stochastic Can deal w. smaller datasets Require quality pre-processing
Result w. probability distribution Require accurate degradation modelling
Can operate alongside statistical approach Can struggle w. multidimensional data
Prior knowledge can be incrementally introduced
w. new data to achieve better performance
Can deal w. nonlinear tasks
Statistical Single precise RUL estimate Early prediction tend to be inaccurate
Various types of regression models Utilise a single dimension for prognostic
ANN solutions have been gaining speed as new architectures have been discovered [
ANN have enabled machine learning to complete more complex tasks that were not previously
possible or were difficult by nature. The downside is that it is a black box, meaning low interpretability.
Sensors 2020,20, 2425 13 of 25
Sampaio et al. [
] found that the MLP architecture worked effectively on non-linear and complex
systems, furthermore it had great generalisation. On the downside, the convergence was found to
be somewhat slow and that the model had a tendency to overfit. Finally, when the proposed model
projected a RUL value near the end of the lifetime, it would slowly move further away.
Zhou et al. [
] claimed that the use of ANN provided great calculation speed. More specifically,
the KELM algorithm performed better than other algorithms in generalisation, due to it being able to
find a least-square optimal solution. Another advantage being that it can achieve multiple outputs.
Though one weakness being that it is heavily dependent on the initial parameters, so if estimated
poorly it will be reflected in the model. Similarly, Javed et al. [
] finds that ELM has a fast iterative
tuning process for deciding on hidden layer parameters. This is due to the algorithm doing it in a
single-step and does not need human intervention. The downside is the random parameters could be
initiated poorly.
Markiewicz et al. [
] finds LSTM-RNN to benefit from being relative stable, notably because it
does not suffer from the vanishing or exploding gradient problem [
Zhang et al. [33]
states that
LSTM-RNN has good performance on sequential data due to the recurrent feedback. Finally, as argued
by Nguyen and Medjaher [
], LSTM-RNN benefits from having a long-term memory meaning it can
keep important information for later application. This can be especially beneficial for degradation
prognostics. Ruiz-Sarmiento et al. [
] decided on utilising a Bayesian approach by applying DAE, this
was due to the algorithm being robust against noisy and fluctuating data. They further stated that the
reason for not utilising a KF was due to the linearity assumption within the underlying system of KF.
Several papers applied either SVM or SVR algorithms. Here, Li et al. [
] stated that LS-SVM had
a good performance on non-linear regression, especially in generalisation. Ruiz-Gonzalez [
] chose
a SVM classifier due to the strong generalisation, furthermore, with a small data set the chances of
overfitting with SVM were relatively low, as well as having a good computation time. Langone et
al. [
] found that LS-SVM benefitted from being able to achieve a global optimum due to least-square
presenting itself as convex. Zhou et al. [
] on the other hand states that SVR has a long computational
with larger data sets and constrained optimisation issues.
3. Applications
The paper has till now studied various state-of-the-art ML approaches on doing PdM and applying
algorithms. This general overview is needed when further delving into a specific topic to identify
challenges and unmet needs. The focus of this paper lies within pumping systems and with the
understanding of the current usage of predictive maintenance, the paper will move further towards
what has been accomplished within the field of predictive maintenance on pumps. According to United
States International Trade Commission in 2005 [
], 80% of the pumps produced in the world are
centrifugal pumps and Karassik and McGuire [76] states that 90% of the pumps used in the chemical
industry are centrifugal pumps. Hence, this paper will primarily focus on applications on centrifugal
pumps. To finalise this section, understanding what has been conducted on PdM within a power plant
setting will also be elaborated upon. As power plants heavily rely on their pumps functioning. Notice
that power plants can potentially be using both centrifugal pumps and positive displacement pumps.
An article released by Collins and Davis on PowerEngineering [
], gives a great overview of things
to consider before investing in one type of pump and states that a power plant of 300 MW will on
average have approximately 100 pumps installed.
Sensors 2020,20, 2425 14 of 25
3.1. Common Faults in Pumping Systems
A centrifugal pump consists of several rotating and static components that has the task of
displacing liquids. Due to the interaction of moving parts and liquids interacting with a solid and static
surface, several errors can surface. A thorough investigation by Forbes [
] resulted in a conclusion
of dividing the main issues of a centrifugal pump into 13 types of faults. Each of the 13 types of
faults could then further be divided into more specific reasons for the fault happening. Table 4
presents an overview of detectable errors with their corresponding data tags that might be of interest.
To get a more detailed description of specific issues, the reader is recommended to visit Forbes [
The main components of a simple centrifugal pump will consist of an impeller, a suction nozzle, a
discharge nozzle, a shaft, a mechanical seal, and several bearings. A more detailed overview can
be seen in Figure 6. Due to the nature of the pump, the pump faults can be categorised into three
categories. Hydraulic, mechanical, and other failures. The hydraulic failures are caused by the liquid
flowing within the piping. The state of the liquid can influence the performance of the pump, but also
damage parts of the pump. Mechanical failures refer to the interaction of moving and static parts, this
commonly causes wear or other types of fatigue. Finally, other type failures are a category for failures
that do not directly fall into the two other groups. The power consumption of a pump can often be an
indicator of whether the pump is performing desirably.
Table 4. Failure types by category for a centrifugal pump.
Name of Fault Category Relevant Data Tag Description
Cavitation Hydraulic Failures Vibration, pump efficiency,
noise, pressure, flow rate
Formation of vapour bubbles that collapses and damages
the piping system. Can result in fatigue or erosion.
Pressure Pulsation Hydraulic Failures Vibration, pressure Can come from running frequencies of the pump,
be ressonance of the system, acoustic behaviour, etc.
Radial Thrust Hydraulic Failures Temperature Thrust directed towards the center of the
pump rotor. Typically occurs at low flow rates.
Axial Thrust Hydraulic Failures Temperature Thrust imposed on the shaft in either an inboard or
outboard direction. Common consequence is fatigue failure.
Suction and Discharge
Recirculation Hydraulic Failures Pressure, noise
An unavoidable fault is the recirculation of some
water within the impeller, either in suction
or discharge of the impeller. Can often be determined by
observing pressure pulsations at inlet and outlet.
Bearing Failure Mechanical Failure Vibration, temperature,
(stress waves/shock pulses)
Can be due to various reasons, such as
contamination of bearing oil by water, other liquid,
high heat, introduction of solid particles.
Seal Failure Mechanical Failure Temperature
Opening of the lapped faces results in solids
entering, or solids sticks to the surface and
introduces severe wear on the hard face.
Lubrication Failure Mechanical Failure Temperature Excessive heat reduces the lubricating
ability and lifetime of the oil.
Excessive Vibrations Mechanical Failure Vibration
Stems from unbalanced moving parts, particles of
the liquid interacts with the pumping system. A large
source of errors should be evaluated to do identification.
Excessive Power
Consumption Other Failure Voltage, current,
impeller speed
A typical indication of the pumping system
having a failure somewhere in the system and
can have different sources for the error.
Blockage Other Failure Flow rate Clogging of piping system or the impeller
can result in the pump stopping to function.
Sensors 2020,20, 2425 15 of 25
Figure 6.
A simple figure of a centrifugal pump. From left to right; water enters the impeller through
the suction nozzle, where kinetic energy will be applied to the liquid through turning of the shaft.
The chasing keeps the water within the system, while the mechanical seals make sure there is no
leakage. The bearing reduces the friction between the moving and stationary parts and is found in
several places within a pumping system. The water exits at the discharge nozzle.
3.2. Pumps and Thermal Power Plants
Pumps have been around for a long time and seen their application within various industries.
Displacing liquid has always been a need for humans to easily transport e.g., water and it is a key
part of the modern infrastructure. An example of a common pumping system is seen in CHPs.
District heating allows for increased efficiency of power plants by utilising excess heat and deliver
heat to costumers. When a critical pump breaks down, it influences the performance of the CHP and
hence maintenance becomes of importance to minimise failure and capacity reduction. Table 5lists
algorithms applied to pumps and CHPs found in the literature. It furthermore presents the objective
of applying the algorithm and what data was used. Literature on pumps are more commonplace
as they serve a general purpose, but it is in most literature limited to fault detection and diagnostic.
The literature presented on pumps is not limited to centrifugal pumps as they play a significant role
in various systems. Utilising prior art will assist other industries relying on pumps to have an easier
time adopt similar systems. The literature found within the CHP domain was very limited, as most
of the power plant related material was referring to nuclear power plants, NPP [
]. The authors
recognise that the list is not complete and that the list would benefit from a more exhaustive search,
but it is representative of current applications.
Sensors 2020,20, 2425 16 of 25
Table 5.
An overview of relevant literature for the domain of PdM within all types of pumps and CHP
units. It is not an exhaustive list, but it can give insight into where more efforts should be focused.
Application Algorithm Objective Data Type Reference
Pump GNB, SVM, RF, MLP, KNN Detect cavitation Vibration [81]
SVM Detect cavitation & blockage Vibration [82]
GMM Clustering Detect operation modes Vibration [83]
SOM NN Fault detection Vibration [84]
Polynomial Regression Fault detection & diagnostic Temperature, Pressure,
Mass Flow, Current [85]
PF Estimate RUL Vibration [83]
AO-PF Estimate RUL oil flow [10]
LR, AHSM Estimate RUL Flow, vibration [86]
KF Estimate RUL Vibration [87]
LN, MLP, DAE Estimate RUL Flow, pressure, stress [88]
CHP LR, MLP, SVR, RF Performance estimation
Temperature, Humidity,
Exhaust Vacuum, Full
Load Power
EE, Autoencoders, IF Anomaly detection
Temperature, Humidity,
Exhaust Vacuum, Full
Load Power
FL, LR RUL estimate of turbine - [90]
The difficulty of creating models on pumps and CHPs stems from their flexible nature. NPPs
will primarily be operating at high to full capacity at all times. If a NPP is not doing so, it becomes a
bad business case for the asset owner. The value of a CHP is, on the other hand, the flexibility that it
offers. This is the same for pumps. Depending on the pump it can either freely regulate up and down,
or it can have set modes to operate in. Wang et al. [
] presents a model, which initially clusters the
operation modes of a centrifugal pump by applying GMM Clustering before estimating a RUL with a
PF. Such methods allow for easier fault detection and also eases the process of creating a RUL.
As CHPs are composed of various components, it becomes tricky to create just a single model for
the full CHP, but requires a model on component level. Hundi and Shahsavari [
] challenges this, by
creating a model which estimates the performance depending on various conditional and time-series
data, by applying various regression methods. This later allows for anomaly detection, by presenting a
separate model.
The benefit of CHPs being build of various components is that literature from other areas might
be applicable. e.g., bearings are commonplace within rotary machinery and state-of-the-art algorithms
have been applied to this area [
]. Another method of overcoming data reflecting a flexible
operation is presented by Moleda et al. [
]. Moleda et al. [
] investigates a feedwater pump on a
CHP in Poland. An approach utilising a bag of regression models is suggested. This is done by creating
a regression model for each data tag and then calculate the RMSE between the estimated value of the
model and the actual value. Though it does not give a RUL estimate, this method allows for detecting
drift, anomaly, and outliers.
A trend found within the data sets utilised is that many rely on vibration
measurements [8184,86,87]
Vibrations are common within pumps, but also generally applied. This is due to vibrations giving a good
indication of the current state of health for the given system. Furthermore, given a little pre-processing
the degradation curve becomes fairly detectable. In a paper by Tse et al. [
], a slurry pump is studied.
Multiple vibration sensor data is extracted and fusioned. Following this a KF is applied to determine the
degradation. The proposed method is not reliant on run-to-failure data and can predict the RUL even
with one channel failing to provide data.
Sensors 2020,20, 2425 17 of 25
4. Challenges for Predictive Maintenance Applications
A set of challenges were identified, during the literature review. This section will outline some
general challenges that PdM faces currently and then some domain-specific challenges concerning
pumps and CHP units.
In Tabel 2a set of application areas was defined. A large proportion was identified as being
experimental [
]. Meaning that a component was investigated in an experimental
setting and hence not necessarily attached to a manufacturer or plant. This shows that even though
PdM has come a long way, there still exists a gap between experiments and industrial applications.
The field of PdM would benefit from applying algorithms to historic data from industrial processes [
This is reasoned that experimental data sets tend to be more fine-tuned, whereas industrial historic
data tend to be noisy and have a larger amount of missing data. A sensor might not have been installed
for the desired data tag. As seen in Section 3.2, most pump models were developed on vibration data.
If vibration data is not available other methods have to be deployed. Furthermore, a component can
have multiple sensors as a source for a model, which requires the developer to align and pre-process
data [
]. Furthermore, industrial data sets, typically, do not have a labelling metric, hence it
requires the developer to dive into expert knowledge or company ERP systems to identify faulty data,
which in turn can introduce bias. Here, some models present themselves more lucrative, as they do
not require a large amount of pre-processing or small amounts of domain knowledge.
Data-driven models tend to make certain assumptions on the system that it reflects. One common
assumption is that it is static and does not develop over time [
]. This will in many cases be
proven to be wrong with many systems being dynamic. Especially within the field of PdM, as a
component is replaced with another, it will require a certain maintenance for each model developed.
Several strategies exist to develop models, but currently most of the models are developed offline,
before implementation and does not consider maintenance. Here, some methods have been deployed
to look at a certain frame or period, e.g., the last year, thus a continuously moving frame. With the
deployment of more IoT equipment, new options open up. Some studies within the field of automatic
maintenance and continuous improvement have been completed [93].
Another challenge lies in the task of determining an accurate RUL. Depending on the data
available different models and methods exist to tackle the problem [
]. In many cases, there is not
necessarily run-to-failure data available, but rather a degradation path or rather depend on expert
knowledge. The issue then becomes to estimate the RUL from the available data. Some components
can have a steady linear degradation at the start of their lifetime, but then suddenly start dropping by
the end of it. This is common within e.g., batteries [
]. Hence, an issue of determining a hidden
state process.
In regards to the pump and CHP domain, a challenge was identified concerning the operation.
Most experimental data can be measured at a fixed operation, but as CHPs and pumps have
variable operation [
], errors may be hidden within the mass of data. Here techniques need to
be extended to handle such issues. Another problem is the scale-ability and streamlining of models.
As industrial process might have several similar or identical components, it is important to investigate
the scale-ability of developed models for them to be used for plug-and-play. This should ease the
implementation of PdM into the industrial sector. This is challenged by the No free lunch theorem, as a
component at one plant might differ slightly from another and then, in turn, prove that another model
might be more suitable.
5. Future Trends
Following Figure 1, the trend within the field of PdM seems obvious. An increasing interest
for research seems to take place. This follows the increase in deployment of ICT enabling data and
knowledge sharing. Some companies are already dealing with prior mentioned challenges, such as
streamlining and scale-ability of algorithms. e.g., Oracle presents the MSET2 tool that can be deployed
for process monitoring [
]. Another company stated that its monitoring tool could significantly reduce
Sensors 2020,20, 2425 18 of 25
maintenance costs [
]. These services will be increasingly common. As tools for easily development
and implementation become more common, industrial applications will follow naturally, as it becomes
commonplace to utilise the state of the art of PdM to stay competitive.
Another trend that Industry 4.0 brings, is the possibility for automatic maintenance of models [
Models will be self-sustainable even with new components being installed, though it will be presenting
new issues to deal with as well. Following Moore’s Law, a doubling in computational power can be
expected to happen every second year [
]. This will continuously increase the possibilities to solve
increasingly complex tasks and open up for various new architectures and algorithms from the ML
This paper did not extend to physical and knowledge-based models, only to the point that it
was introduced through hybrid models. Though, it seems that increasing amounts of literature is
considering combining either data-driven models with physical or knowledge-based models, as this
can improve accuracy and trust in the developed model [
]. This can be reasoned that
data-driven to a certain degree lack interpretability, where e.g., knowledge-based models would allow
for domain experts to influence the model [
]. This might be ideal for the industry moving forward,
as it would present them with a larger toolkit to operate within.
6. Conclusions
This paper presented a literature review on current state-of-the-art applications within the field of
predictive maintenance. The paper initially presented a thorough introduction to what PdM offers and
gave a framework on how to prepare and develop PdM models. Here literature was recommended for
further reading to deepen the understanding of how model construction could be done. Then literature
with applications in various areas were introduced, this allowed for the identification of advantages
and limitations of certain algorithms. It further allowed for identifying certain trends within the
predictive maintenance field. This was compared to the specific domain of pumps and combined heat
and power plants. Here certain gaps were identified, as limited material could be identified within the
combined heat and power area. A set of challenges for predictive maintenance were then presented
before outlining future trends.
For future work, the authors recommend that a more exhaustive literature review is conducted as
there are increasing amounts of literature being published at a rapid pace. General trends could be
identified from the studied literature, but the paper would benefit from verification of the exhaustive
search. This is especially related to domain-specific areas, as general literature does not seem to be
lacking. Furthermore, the literature review should be extended to include literature of other types of
models, such as physical and knowledge-based models.
Author Contributions:
Conceptualization, J.F.O. and H.R.S.; methodology, J.F.O.; Formal analysis, J.F.O.;
investigation, J.F.O.; data curation, J.F.O.; writing—original draft preparation, J.F.O.; writing, J.F.O.; review
and editing, H.R.S.; visualization, J.F.O.; supervision, H.R.S.; All authors have read and agreed to the published
version of the manuscript.
This paper was written in connection with a project on Predictive Maintenance within
thermal power plants. The authors would like to express their gratitude to Ørsted for the collaboration.
Conflicts of Interest: The authors declare no conflict of interest.
The following abbreviations are used in this manuscript:
ML Machine Learning
RUL Remaining Useful lifetime
ICT Information and Communication Technology
PHM Prognostic and Health Management
Sensors 2020,20, 2425 19 of 25
PdM Predictive Maintenance
PvM Preventive Maintenance
CDM Condition-based Maintenance
CHP Combined heat and power plant
NPP Nuclear Power Plant
ANN Artificial Neural Network
DL Deep Learning
MLP Multilayer Perceptron
ELM Extreme Learning Machine
KELM Kernel Extreme Learning Machine
SW-ELM Summation Wavelet Extreme Learning Machine
CNN Convolutional Neural Network
LSTM-RNN Long-Short Term Memory Recurrent Neural Network
TDNN Time Delay Neural Network
SFAM Simplified Fuzzy Adaptive Resonance Theory Map (Neural Network)
DLM Dynamic Linear Model
BN Bayesian Network
KF Kalman Filter
SUKF Switching Unscented Kalman Filter
EKF Extended Kalman Filter
PF Particle Filter
DBF Discrete Bayes Filter
LR Linear Regression
RFR Random Forest Regression
SR Symbolic Regression
ARMA Autoregressive Moving Average
ARIMA Autoregressive Integrated Moving Average
RVM Relevance Vector Machine
SVR Support-vector Regression
SVM Support-vector Machine
LS-SVM Least-squares Support-vector Machine
LS-SVM NAR Least-squares Support-vector Machine Nonlinear Autoregressive
DT Decision Tree
RF Random Forest
RBF-SVM Radial Basis Support-vector Machine
BS-SRCKF Backward Smoothing Square Root Cubature Kalman Filter
MHKF Multiscale Hybrid Kalman Filter
AUKF Adaptive Unscented Kalman Filter
RMS Root Mean Square
KSC Kernel Spectral Clustering
RSME Root Mean Square Error
R2Coefficient of Determination
PEMFC Proton-Exchange Membrane Fuel Cell
GAF Grammian Angular Field
KNN k-Nearest Neighbour
ANFIS Adaptive Neuro-Fuzzy Inference System
GNB Gaussian Naive Bayes
GMM Clustering Gaussian Mixture Model
SOM NN Self Organizing Map Neural Network
Sensors 2020,20, 2425 20 of 25
AO-PF Adaptive-Order Particle Filter
AHSMM Adaptive Hidden Semi-Markov Model
LN Ladder Network
DAE Denoising Autoencoder
EE Elliptic Envelope
IF Isolation Forest
FL Fuzzy-Logic
ERP System Enterprise Resource Planning System
MSET2 Multivariate State Estimation Technique
Uckun, S.; Goebel, K.; Lucas, P.J. Standardizing research methods for prognostics. In Proceedings of the
2008 International Conference on Prognostics and Health Management, Denver, CO, USA, 6–9 October 2008;
pp. 1–10. doi:10.1109/PHM.2008.4711437.
Lee, J.; Wu, F.; Zhao, W.; Ghaffari, M.; Liao, L.; Siegel, D. Prognostics and health management design for
rotary machinery systems—Reviews, methodology and applications. Mech. Syst. Signal Process.
42, 314–334. doi:10.1016/j.ymssp.2013.06.004.
Mobley, R.K. Role of Maintenance Organization. In An Introduction to Predictive Maintenance; Elsevier:
Amsterdam, The Netherlands, 2002; pp. 43–59. doi:10.1016/b978-075067531-4/50003-8.
Merkt, O. On the Use of Predictive Models for Improving the Quality of Industrial Maintenance: An
Analytical Literature Review of Maintenance Strategies. In Proceedings of the 2019 Federated Conference on
Computer Science and Information Systems (FedCSIS), Leipzig, Germany, 1–4 September 2019; pp. 693–704.
Phogat, S.; Gupta, A.K. Expected maintenance waste reduction benefits after implementation of Just
in Time (JIT) philosophy in maintenance (a statistical analysis). J. Qual. Maint. Eng.
,25, 25–40.
Lund, R.; Mathiesen, B.V. Large combined heat and power plants in sustainable energy systems. Appl. Energy
2015,142, 389–395. doi:10.1016/j.apenergy.2015.01.013.
Wang, J.; You, S.; Zong, Y.; Træholt, C.; Zhou, Y.; Mu, S. Optimal dispatch of combined heat and power plant
in integrated energy system: A state of the art review and case study of Copenhagen. Energy Procedia 2019,
158, 2794–2799. doi:10.1016/j.egypro.2019.02.040.
Collins, D.; Davis, J. Things Power Plant Engineers Need to Know About Pumps. Available online: to-know-about-
pumps/#gref (accessed on 23 April 2020).
Forbes, G. A review of major centrifugal pump failure modes with application to the water supply and
sewerage industries. In ICOMS Asset Management Conference Proceedings; Asset Management Council:
Oakleigh, Australia, 2011.
Li, T.; Wang, S.; Shi, J.; Ma, Z. An adaptive-order particle filter for remaining useful life prediction of aviation
piston pumps. Chin. J. Aeronaut. 2018,31, 941–948. doi:10.1016/j.cja.2017.09.002.
Isaksson, A.J.; Harjunkoski, I.; Sand, G. The impact of digitalization on the future of control and operations.
Comput. Chem. Eng. 2018,114, 122–129. doi:10.1016/j.compchemeng.2017.10.037.
Permin, E.; Lindner, F.; Kostyszyn, K.; Grunert, D.; Lossie, K.; Schmitt, R.; Plutz, M. Smart Devices in
Production System Maintenance. In Predictive Maintenance in Dynamic Systems: Advanced Methods, Decision
Support Tools and Real-World Applications; Lughofer, E., Sayed-Mouchaweh, M., Eds.; Springer International
Publishing: Cham, Switzerland, 2019; pp. 25–51. doi:10.1007/978-3-030-05645-2_2.
Carvalho, T.P.; Soares, F.A.; Vita, R.; da P. Francisco, R.; Basto, J.P.; Alcalá, S.G.S. A systematic literature
review of machine learning methods applied to predictive maintenance. Comput. Ind. Eng.
,137, 106024.
Bousdekis, A.; Lepenioti, K.; Apostolou, D.; Mentzas, G. Decision Making in Predictive Maintenance:
Literature Review and Research Agenda for Industry 4.0. IFAC-PapersOnLine
,52, 607–612.
Sensors 2020,20, 2425 21 of 25
Werner, A.; Zimmermann, N.; Lentes, J. Approach for a Holistic Predictive Maintenance Strategy by
Incorporating a Digital Twin. Procedia Manuf. 2019,39, 1743–1751. doi:10.1016/j.promfg.2020.01.265.
Sakib, N.; Wuest, T. Challenges and Opportunities of Condition-based Predictive Maintenance: A Review.
Procedia CIRP 2018,78, 267–272. doi:10.1016/j.procir.2018.08.318.
Oxford Learner’s Dictionaries. Oxford Advanced Learner’s Dictionary. 2019.
Available online:
(accessed on 23
April 2020).
Mobley, R.K. Impact of Maintenance. In An Introduction to Predictive Maintenance; Elsevier: Amsterdam, The
Netherlands, 2002; pp. 1–22. doi:10.1016/b978-075067531-4/50001-4.
Armendia, M.; Alzaga, A.; Peysson, F.; Euhus, D. Twin-Control Approach. In Twin-Control: A Digital Twin
Approach to Improve Machine Tools Lifecycle; Armendia, M., Ghassempouri, M., Ozturk, E., Peysson, F., Eds.;
Springer International Publishing: Cham, Switzerland, 2019; pp. 23–38. doi:10.1007/978-3-030-02203-7_2.
Schluse, M.; Priggemeyer, M.; Atorf, L.; Rossmann, J. Experimentable Digital Twins—Streamlining
Simulation-Based Systems Engineering for Industry 4.0. IEEE Trans. Ind. Inform.
,14, 1722–1731.
Tinga, T.; Loendersloot, R. Physical Model-Based Prognostics and Health Monitoring to Enable Predictive
Maintenance. In Predictive Maintenance in Dynamic Systems: Advanced Methods, Decision Support Tools and
Real-World Applications; Lughofer, E., Sayed-Mouchaweh, M., Eds.; Springer International Publishing: Cham,
Switzerland, 2019; pp. 313–353. doi:10.1007/978-3-030-05645-2_11.
Bektas, O.; Marshall, J.; Jones, J.A. Comparison of Computational Prognostic Methods for Complex
Systems Under Dynamic Regimes: A Review of Perspectives. Arch. Comput. Methods Eng.
Liao, L.; Köttig, F. A hybrid framework combining data-driven and model-based methods for system
remaining useful life prediction. Appl. Soft Comput. 2016,44, 191–199. doi:10.1016/j.asoc.2016.03.013.
Lughofer, E.; Sayed-Mouchaweh, M. (Eds.) Predictive Maintenance in Dynamic Systems; Springer International
Publishing: Cham, Switzerland, 2019. doi:10.1007/978-3-030-05645-2.
Cernuda, C. On the Relevance of Preprocessing in Predictive Maintenance for Dynamic Systems. In Predictive
Maintenance in Dynamic Systems: Advanced Methods, Decision Support Tools and Real-World Applications;
Lughofer, E., Sayed-Mouchaweh, M., Eds.; Springer International Publishing: Cham, Switzerland, 2019; pp.
53–93. doi:10.1007/978-3-030-05645-2_3.
Fernandez-Delgado, M.; Cernadas, E.; Barro, S.; Amorim, D. Do we Need Hundreds of Classifiers to Solve
Real World Classification Problems? J. Mach. Learn. Res. 2014,15, 3133–3181.
Mathew, J.; Luo, M.; Pang, C.K. Regression kernel for prognostics with support vector machines.
In Proceedings of the 2017 22nd IEEE International Conference on Emerging Technologies and Factory
Automation (ETFA), Limassol, Cyprus, 12–15 September 2017; pp. 1–5. doi:10.1109/ETFA.2017.8247740.
Wolpert, D.H.; Macready, W.G. No free lunch theorems for optimization. IEEE Trans. Evol. Comput.
1, 67–82. doi:10.1109/4235.585893.
Gerum, P.C.L.; Altay, A.; Baykal-Gürsoy, M. Data-driven predictive maintenance scheduling policies for
railways. Transp. Res. Part Emerg. Technol. 2019,107, 137–154. doi:10.1016/j.trc.2019.07.020.
Qiu, X.; Wu, W.; Wang, S. Remaining useful life prediction of lithium-ion battery based on improved cuckoo
search particle filter and a novel state of charge estimation method. J. Power Sources
,450, 227700.
Sampaio, G.S.; de Aguiar Vallim Filho, A.R.; da Silva, L.S.; da Silva, L.A. Prediction of Motor Failure Time
Using An Artificial Neural Network. Sensors 2019,19, 4342. doi:10.3390/s19194342.
Rengasamy, D.; Jafari, M.; Rothwell, B.; Chen, X.; Figueredo, G.P. Deep Learning with Dynamically
Weighted Loss Function for Sensor-Based Prognostics and Health Management. Sensors
,20, 723.
Zhang, S.; Zhai, B.; Guo, X.; Wang, K.; Peng, N.; Zhang, X. Synchronous estimation of state of health
and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural
networks. J. Energy Storage 2019,26, 100951. doi:10.1016/j.est.2019.100951.
Sensors 2020,20, 2425 22 of 25
En, T.Y.; Ki, M.S.; Hui, N.T.; Jie, T.J.; Bin Mohamed Vusoff, M.A. Predictive Maintenance of a Train
System Using a Multilayer Perceptron Artificial Neural Network. In Proceedings of the 2018 International
Conference on Intelligent Rail Transportation (ICIRT), Singapore, 12–14 December 2018; pp. 1–5.
Pan, Y.; Hong, R.; Chen, J.; Singh, J.; Jia, X. Performance degradation assessment of a wind
turbine gearbox based on multi-sensor data fusion. Mech. Mach. Theory
,137, 509–526.
Zhou, K.B.; Zhang, J.Y.; Shan, Y.; Ge, M.F.; Ge, Z.Y.; Cao, G.N. A Hybrid Multi-Objective Optimization Model
for Vibration Tendency Prediction of Hydropower Generators. Sensors
,19, 2055. doi:10.3390/s19092055.
Javed, K.; Gouriveau, R.; Zerhouni, N. A New Multivariate Approach for Prognostics Based on
Extreme Learning Machine and Fuzzy Clustering. IEEE Trans. Cybern.
,45, 2626–2639.
Silva, W.; Capretz, M. Assets Predictive Maintenance Using Convolutional Neural Networks. In Proceedings
of the 2019 20th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence,
Networking and Parallel/Distributed Computing (SNPD), Toyama, Japan, 8–11 July 2019; pp. 59–66.
Gouarir, A.; Martínez-Arellano, G.; Terrazas, G.; Benardos, P.; Ratchev, S. In-process Tool Wear Prediction
System Based on Machine Learning Techniques and Force Analysis. Procedia CIRP
,77, 501–504.
Nguyen, K.T.; Medjaher, K. A new dynamic predictive maintenance framework using deep learning for
failure prognostics. Reliab. Eng. Syst. Saf. 2019,188, 251–262. doi:10.1016/j.ress.2019.03.018.
Deng, Y.; Bucchianico, A.D.; Pechenizkiy, M. Controlling the accuracy and uncertainty trade-off in RUL
prediction with a surrogate Wiener propagation model. Reliab. Eng. Syst. Saf.
,196, 106727.
Markiewicz, M.; Wielgosz, M.; Boche´nski, M.; Tabaczy ´nski, W.; Konieczny, T.; Kowalczyk, L. Predictive
Maintenance of Induction Motors Using Ultra-Low Power Wireless Sensors and Compressed Recurrent
Neural Networks. IEEE Access 2019,7, 178891–178902. doi:10.1109/ACCESS.2019.2953019.
Yu, Y.; Hu, C.; Si, X.; Zheng, J.; Zhang, J. Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle
labeled dataset. Neurocomputing 2020. doi:10.1016/j.neucom.2020.03.041.
Zhou, D.; Al-Durra, A.; Zhang, K.; Ravey, A.; Gao, F. Online remaining useful lifetime prediction of proton
exchange membrane fuel cells using a novel robust methodology. J. Power Sources
,399, 314–328.
Ali, J.B.; Chebel-Morello, B.; Saidi, L.; Malinowski, S.; Fnaiech, F. Accurate bearing remaining useful life
prediction based on Weibull distribution and artificial neural network. Mech. Syst. Signal Process.
56–57, 150–172. doi:10.1016/j.ymssp.2014.10.014.
Sun, J.; Wang, F.; Ning, S. Aircraft air conditioning system health state estimation and prediction for
predictive maintenance. Chin. J. Aeronaut. 2019. doi:10.1016/j.cja.2019.03.039.
Curcurù, G.; Galante, G.; Lombardo, A. A predictive maintenance policy with imperfect monitoring. Reliab.
Eng. Syst. Saf. 2010,95, 989–997. doi:10.1016/j.ress.2010.04.010.
Son, J.; Zhou, S.; Sankavaram, C.; Du, X.; Zhang, Y. Remaining useful life prediction based on noisy
condition monitoring signals using constrained Kalman filter. Reliab. Eng. Syst. Saf.
,152, 38–50.
Cui, L.; Wang, X.; Xu, Y.; Jiang, H.; Zhou, J. A novel Switching Unscented Kalman Filter
method for remaining useful life prediction of rolling bearing. Measurement
,135, 678–684.
Saha, B.; Goebel, K.; Christophersen, J. Comparison of prognostic algorithms for estimating remaining useful
life of batteries. Trans. Inst. Meas. Control 2009,31. doi:10.1177/0142331208092030.
Ruiz-Sarmiento, J.R.; Monroy, J.; Moreno, F.A.; Galindo, C.; Bonelo, J.M.; Gonzalez-Jimenez, J. A predictive
model for the maintenance of industrial machinery in the context of industry 4.0. Eng. Appl. Artif. Intell.
2020,87, 103289. doi:10.1016/j.engappai.2019.103289.
Zenisek, J.; Holzinger, F.; Affenzeller, M. Machine learning based concept drift detection for predictive
maintenance. Comput. Ind. Eng. 2019,137, 106031. doi:10.1016/j.cie.2019.106031.
Sensors 2020,20, 2425 23 of 25
Traini, E.; Bruno, G.; D’Antonio, G.; Lombardi, F. Machine Learning Framework for Predictive Maintenance
in Milling. IFAC-PapersOnLine 2019,52, 177–182. doi:10.1016/j.ifacol.2019.11.172.
Du, J.; Zhang, W.; Zhang, C.; Zhou, X. Battery remaining useful life prediction under coupling stress based
on support vector regression. Energy Procedia 2018,152, 538–543. doi:10.1016/j.egypro.2018.09.207.
Yan, M.; Wang, X.; Wang, B.; Chang, M.; Muhammad, I. Bearing remaining useful life prediction
using support vector machine and hybrid degradation tracking model. ISA Trans.
,98, 471–482.
Li, Q.; Xing, L.; Liu, W.; Ba, W. Adaptive Soft Sensor Based on a Moving Window Just-in-time Learning
LS-SVM for Distillation Processes. IFAC-PapersOnLine 2015,48, 51–56. doi:10.1016/j.ifacol.2015.12.099.
Langone, R.; Alzate, C.; Ketelaere, B.D.; Vlasselaer, J.; Meert, W.; Suykens, J.A. LS-SVM based spectral
clustering and regression for predicting maintenance of industrial machines. Eng. Appl. Artif. Intell.
37, 268–278. doi:10.1016/j.engappai.2014.09.008.
Ruiz-Gonzalez, R.; Gomez-Gil, J.; Gomez-Gil, F.; Martínez-Martínez, V. An SVM-Based Classifier for
Estimating the State of Various Rotating Components in Agro-Industrial Machinery with a Vibration Signal
Acquired from a Single Point on the Machine Chassis. Sensors
,14, 20713–20735. doi:10.3390/s141120713.
Bukhsh, Z.A.; Saeed, A.; Stipanovic, I.; Doree, A.G. Predictive maintenance using tree-based classification
techniques: A case of railway switches. Transp. Res. Part Emerg. Technol.
,101, 35–54.
Ravikumar, S.; Ramachandran, K. Tool Wear Monitoring of Multipoint Cutting Tool using Sound
Signal Features Signals with Machine Learning Techniques. Mater. Today Proc.
,5, 25720–25729.
Susto, G.A.; Schirru, A.; Pampuri, S.; Pagano, D.; McLoone, S.; Beghi, A. A predictive maintenance system for
integral type faults based on support vector machines: An application to ion implantation. In Proceedings
of the 2013 IEEE International Conference on Automation Science and Engineering (CASE), Madison, WI,
USA, 17–21 August 2013; pp. 195–200. doi:10.1109/CoASE.2013.6653952.
Xue, Z.; Zhang, Y.; Cheng, C.; Ma, G. Remaining useful life prediction of lithium-ion batteries with adaptive
unscented kalman filter and optimized support vector regression. Neurocomputing
,376, 95–102.
63. Graves, A. Neural Networks; Springer; Berlin, Germany, 2012.
Bishop, C. Neural Networks For Pattern Recognition; Oxford University Press: Oxford, UK, 2005; Volume 227.
Wang, Z.; Oates, T. Imaging Time-Series to Improve Classification and Imputation. arXiv
Chen, J.; Chen, W.; Huang, C.; Huang, S.; Chen, A. Financial Time-Series Data Analysis Using
Deep Convolutional Neural Networks. In Proceedings of the 2016 7th International Conference
on Cloud Computing and Big Data (CCBD), Macau, China, 16–18 November 2016; pp. 87–92.
Zhang, B.; Zhang, S.; Li, W. Bearing performance degradation assessment using long short-term memory
recurrent network. Comput. Ind. 2019,106, 14–29. doi:10.1016/j.compind.2018.12.016.
Uhlmann, E.; Pontes, R.P.; Geisert, C.; Hohwieler, E. Cluster identification of sensor data for
predictive maintenance in a Selective Laser Melting machine tool. Procedia Manuf.
,24, 60–65.
Cao, Q.; Samet, A.; Zanni-Merk, C.; de Bertrand de Beuvron, F.; Reich, C. An Ontology-based Approach for
Failure Classification in Predictive Maintenance Using Fuzzy C-means and SWRL Rules. Procedia Comput.
Sci. 2019,159, 630–639. doi:10.1016/j.procs.2019.09.218.
Daher, A.; Hoblos, G.; Khalil, M.; Chetouani, Y. New prognosis approach for preventive and predictive
maintenance—Application to a distillation column. Chem. Eng. Res. Des.
,153, 162–174.
Olson, R.; La Cava, W.; Orzechowski, P.; Urbanowicz, R.; Moore, J. PMLB: A Large Benchmark Suite for
Machine Learning Evaluation and Comparison. BioData Min. 2017,10. doi:10.1186/s13040-017-0154-4.
Ahmed, N.; Atiya, A.; Gayar, N.; El-Shishiny, H. An Empirical Comparison of Machine Learning Models for
Time Series Forecasting. Econom. Rev. 2010,29, 594–621. doi:10.1080/07474938.2010.481556.
Sensors 2020,20, 2425 24 of 25
Wang, X.; Qin, Y.; Wang, Y.; Xiang, S.; Chen, H. ReLTanh: An activation function with vanishing gradient
resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis. Neurocomputing
2019,363, 88–98. doi:10.1016/j.neucom.2019.07.017.
Krishnan, R.; Jagannathan, S.; Samaranayake, V. Direct Error Driven Learning for Deep Neural Networks
with Applications to Bigdata. Procedia Comput. Sci. 2018,144, 89–95. doi:10.1016/j.procs.2018.10.508.
Webster, J.A.; McNay, D.A.; Lundy, D.; De Sapio, V.; De Sapio, V.; Fan, Q.; Fravel, D.; Houck, G.; Lenchitz, H.;
Mapes, C.; et al. Foundry Products: Competitive Conditions in the U.S. Market; United States International Trade
Commission: Washington, DC, USA, 2005.
Karassik, I.J.; McGuire, T. Centrifugal Pumps; Springer: New York, NY, USA, 1997.
Kim, G.; Kim, H.; Zio, E.; Heo, G. Application of particle filtering for prognostics with measurement
uncertainty in nuclear power plants. Nucl. Eng. Technol. 2018,50, 1314–1323. doi:10.1016/
Gohel, H.A.; Upadhyay, H.; Lagos, L.; Cooper, K.; Sanzetenea, A. Predictive Maintenance Architecture
Development for Nuclear Infrastructure using Machine Learning. Nucl. Eng. Technol.
Zhao, Y.; Tong, J.; Zhang, L.; Wu, G. Diagnosis of operational failures and on-demand failures in nuclear
power plants: An approach based on dynamic Bayesian networks. Ann. Nucl. Energy
,138, 107181.
Nguyen, H.P.; Liu, J.; Zio, E. A long-term prediction approach based on long short-term memory
neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and
applied to time-series data of NPP steam generators. Appl. Soft Comput.
,89, 106116.
Hu, Q.; Ohata, E.F.; Silva, F.H.; Ramalho, G.L.; Han, T.; Filho, P.P.R. A new online approach for
classification of pumps vibration patterns based on intelligent IoT system. Measurement
,151, 107138.
Panda, A.K.; Rapur, J.S.; Tiwari, R. Prediction of flow blockages and impending cavitation in centrifugal
pumps using Support Vector Machine (SVM) algorithms based on vibration measurements. Measurement
2018,130, 44–56. doi:10.1016/j.measurement.2018.07.092.
Wang, J.; Zhang, L.; Zheng, Y.; Wang, K. Adaptive prognosis of centrifugal pump under variable operating
conditions. Mech. Syst. Signal Process. 2019,131, 576–591. doi:10.1016/j.ymssp.2019.06.008.
Tao, X.; Wang, Z.; Ma, J.; Fan, H. Study on fault detection using wavelet packet and SOM neural network. In
Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing),
Beijing, China, 23–25 May 2012; pp. 1–5. doi:10.1109/PHM.2012.6228817.
Moleda, M.; Momot, A.; Mrozek, D. Predictive Maintenance of Boiler Feed Water Pumps Using SCADA
Data. Sensors 2020,20, 571. doi:10.3390/s20020571.
Liu, Q.; Dong, M.; Lv, W.; Geng, X.; Li, Y. A novel method using adaptive hidden semi-Markov model
for multi-sensor monitoring equipment health prognosis. Mech. Syst. Signal Process.
,64–65, 217–232.
Tse, Y.L.; Cholette, M.E.; Tse, P.W. A multi-sensor approach to remaining useful life estimation for a slurry
pump. Measurement 2019,139, 140–151. doi:10.1016/j.measurement.2019.02.079.
He, R.; Dai, Y.; Lu, J.; Mou, C. Developing ladder network for intelligent evaluation system: Case of
remaining useful life prediction for centrifugal pumps. Reliab. Eng. Syst. Saf.
,180, 385–393.
Hundi, P.; Shahsavari, R. Comparative studies among machine learning models for performance
estimation and health monitoring of thermal power plants. Appl. Energy
,265, 114775.
Alamaniotis, M.; Grelle, A.; Tsoukalas, L.H. Regression to fuzziness method for estimation of
remaining useful life in power plant components. Mech. Syst. Signal Process.
,48, 188–198.
Dong, S.; Luo, T. Bearing degradation process prediction based on the PCA and optimized LS-SVM model.
Measurement 2013,46, 3143–3152. doi:10.1016/j.measurement.2013.06.038.
Sensors 2020,20, 2425 25 of 25
Koutroulis, G.; Thalmann, S. Challenges from Data-Driven Predictive Maintenance in Brownfield Industrial
Settings. In Business Information Systems Workshops; Abramowicz, W., Paschke, A., Eds.; Springer International
Publishing: Cham, Switzerland, 2019; pp. 461–467.
Wotawa, F. Reasoning from First Principles for Self-adaptive and Autonomous Systems. In Predictive
Maintenance in Dynamic Systems: Advanced Methods, Decision Support Tools and Real-World Applications;
Lughofer, E., Sayed-Mouchaweh, M., Eds.; Springer International Publishing: Cham, Switzerland, 2019; pp.
427–460. doi:10.1007/978-3-030-05645-2_15.
Gross, K.C.; Li, D. Machine Learning Innovation for High Accuracy Remaining Useful Life (RUL) Estimation
for Critical Assets in IoT Infrastructures. In Proceedings of the International Conference Internet Computing
and Internet of Things, Las Vegas, NV, USA, 30 July–2 August 2018; pp. 101–107.
Predictive maintenance tool monitors pump and motor with wireless access and protective alerts.
World Pumps 2019,2019, 11. doi:10.1016/s0262-1762(18)30411-5.
Kuniavsky, M. Introduction The middle of Moore’s law. In Smart Things: Ubiquitous Computing User Experience
Design; Elsevier: Amsterdam, The Netherlands, 2010; pp. 3–11. doi:10.1016/b978-0-12-374899-7.00001-1.
2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (
... Only a few papers focus on the energy generation field, but even those are specific to particular sources of energy. For example, Fausing et al. [12] gives an overview of predictive maintenance applications in thermal power plants, while Chao et al. [13] and Ngarayana et al. [14] focus on nuclear power plants. Table 1. ...
... Fausing et al. [12] 2020 Thermal Power Plant A review of PdM articles with a focus on the pumping system in power plants. ...
Full-text available
Appropriate maintenance of industrial equipment keeps production systems in good health and ensures the stability of production processes. In specific production sectors, such as the electrical power industry, equipment failures are rare but may lead to high costs and substantial economic losses not only for the power plant but for consumers and the larger society. Therefore, the power production industry relies on a variety of approaches to maintenance tasks, ranging from traditional solutions and engineering know-how to smart, AI-based analytics to avoid potential downtimes. This review shows the evolution of maintenance approaches to support maintenance planning, equipment monitoring and supervision. We present older techniques traditionally used in maintenance tasks and those that rely on IT analytics to automate tasks and perform the inference process for failure detection. We analyze prognostics and health-management techniques in detail, including their requirements, advantages and limitations. The review focuses on the power-generation sector. However, some of the issues addressed are common to other industries. The article also presents concepts and solutions that utilize emerging technologies related to Industry 4.0, touching on prescriptive analysis, Big Data and the Internet of Things. The primary motivation and purpose of the article are to present the existing practices and classic methods used by engineers, as well as modern approaches drawing from Artificial Intelligence and the concept of Industry 4.0. The summary of existing practices and the state of the art in the area of predictive maintenance provides two benefits. On the one hand, it leads to improving processes by matching existing tools and methods. On the other hand, it shows researchers potential directions for further analysis and new developments.
... Thermal power plants (TPPs) represent an important asset of the current energy infrastructure with particular reference to developing countries (Fausing et al., 2020). According to the statistical bulletin on National Economic and Social Development in 2020 released by the National Bureau of Statistics of China, the country's electricity generation capacity in 2020 was 7,779.06 billion kWh, of which, the thermal power generation capacity was 5,330.25 billion kWh, accounting for 68.52% of the national electricity generation capacity (National Bureau of Statistics of China, 2021). ...
Purpose Lubricating oil leakage is a common issue in thermal power plant operation sites, requiring prompt equipment maintenance. The real-time detection of leakage occurrences could avoid disruptive consequences caused by the lack of timely maintenance. Currently, inspection operations are mostly carried out manually, resulting in time-consuming processes prone to health and safety hazards. To overcome such issues, this paper proposes a machine vision-based inspection system aimed at automating the oil leakage detection for improving the maintenance procedures. Design/methodology/approach The approach aims at developing a novel modular-structured automatic inspection system. The image acquisition module collects digital images along a predefined inspection path using a dual-light (i.e. ultraviolet and blue light) illumination system, deploying the fluorescence of the lubricating oil while suppressing unwanted background noise. The image processing module is designed to detect the oil leakage within the digital images minimizing detection errors. A case study is reported to validate the industrial suitability of the proposed inspection system. Findings On-site experimental results demonstrate the capabilities to complete the automatic inspection procedures of the tested industrial equipment by achieving an oil leakage detection accuracy up to 99.13%. Practical implications The proposed inspection system can be adopted in industrial context to detect lubricant leakage ensuring the equipment and the operators safety. Originality/value The proposed inspection system adopts a computer vision approach, which deploys the combination of two separate sources of light, to boost the detection capabilities, enabling the application for a variety of particularly hard-to-inspect industrial contexts.
... In the case of dams and hydropower, sensors and monitoring devices can be installed to gather data on various parameters such as water level, flow rate, and pressure. This data can then be analyzed using AI and ML algorithms to identify patterns and anomalies that may indicate potential issues (Vallim Filho et al., 2022;Fausing Olesen and Shaker, 2020). For example, machine learning algorithms can be trained on historical data to detect patterns that lead to specific types of equipment failures. ...
Full-text available
In the manufacturing process, equipment failure is directly related to productivity, so predictive maintenance plays a very important role. Industrial parks are distributed, and data heterogeneity exists among heterogeneous equipment, which makes predictive maintenance of equipment challenging. In this paper, we propose two main techniques to enable effective predictive maintenance in this environment. We propose a 1DCNN-Bilstm model for time series anomaly detection and predictive maintenance of manufacturing processes. The model combines a 1D convolutional neural network (1DCNN) and a bidirectional LSTM (Bilstm), which is effective in extracting features from time series data and detecting anomalies. In this paper, we combine a federated learning framework with these models to consider the distributional shifts of time series data and perform anomaly detection and predictive maintenance based on them. In this paper, we utilize the pump dataset to evaluate the performance of the combination of several federated learning frameworks and time series anomaly detection models. Experimental results show that the proposed framework achieves a test accuracy of 97.2%, which shows its potential to be utilized for real-world predictive maintenance in the future.
Full-text available
One way to improve the infrastructure, operations, monitoring, maintenance, and management of wastewater treatment systems is to use machine learning modelling to make smart forecasting, tracking, and failure prediction systems. This method aims to use industry data to treat the wastewater treatment model. Gradient-Boosted Decision Tree (GBDT) algorithms were used gradually to predict wastewater plant parameters. In addition, we used the Slime Mould Algorithm (SMA) for feature extraction and other acceptable tuning procedures. The input and effluent Chemical Oxygen Demand (COD) prediction for effluent treatment systems applies to the GBDT approaches employed in this study. GBDT-SMA employs artificial intelligence to provide precise method modelling for complex systems. Several training and model testing techniques were used to determine the best topology for the neural network models and decision trees. The GBDT-SMA model performed best across all methods. With 500 data, GBDT-SMA achieved an accuracy of 96.32%, outperforming other models like Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Deep Convolutional Neural Network (DCNN), and K-neighbours RF, which reached an accuracy of 82.97, 87.45, 85.98, and 91.45%, respectively.
Data-driven remaining useful life (RUL) prediction is critical for industrial devices. There is an important assumption for classic machine learning methods that the training and test sets need to follow independent and identical distribution (IID), which does not hold under multiple working conditions. To relax the IID assumption, transfer learning is a key technique, which is also limited by the knowledge of the target domain data distribution. This paper proposes a novel transfer ensemble learning (TEL) framework, which can effectively utilize the information of source domain and improve the generalization ability of the model to unknown target domain. The framework mainly relies on the knowledge of metric learning, and adopts Kullback-Leibler (KL) divergence to measure the differences in data distributions. A domain dissimilarity metric is proposed to ensure that sub-models of similar datasets have a greater impact on the results. To verify the performance of this framework, a real filtering system from the PHM 2020 competition is used. Meanwhile, the information of time series data can be fully utilized by using the bidirectional long short-term memory (Bi-LSTM) model. Experimental results show that the proposed TEL-Bi-LSTM method outperforms existing machine learning methods.
Full-text available
The deployment of intelligent systems in the management and monitoring of the components of production systems have led to improved quality and enhanced productivity on the manufacturing shop floor. This paper presents a systematic review of the digital twin and other intelligent systems for use in the predictive maintenance of equipment on the shop floor. Many databases, such as the Google Scholar, Scopus, IEEE Xplore, Research Gate, and Science Direct were used for data collection. The study revealed that intelligent systems such as the digital twin are effective tools for predictive maintenance of equipment in production systems. This has been found to improve productivity and reduce downtime in production systems. The study highlights the current trends, benefits and limitations in the deployment of intelligent systems such as the Digital Twin, for use in the predictive maintenance of equipment in smart factories.
Full-text available
Determination of the right time for machine maintenance is a major challenge for many industrial companies. Currently, most companies react on occurring breakdowns (reactive maintenance) or maintenance is carried out in scheduled time intervals (preventive maintenance). These results in either unexpected production stops, or a waste of machine working hours, because components are switched too early. Consequently, predictive maintenance strategies offer a big potential. An essential part of predictive maintenance is the estimation of the Remaining Useful Life (RUL) of machine assets. RUL estimation approaches are based on statistical methods and derived algorithms. Thus, a lot of data is needed for a good estimation. Additionally, data can be generated by means of simulation to improve the RUL estimation. However, companies hardly have an overview of available data and according modules, which are needed for a holistic predictive maintenance strategy. This paper shows an approach for a predictive maintenance strategy dealing with acquisition, processing, and analysis of historical field data as well as the generation of respective simulation data. A structured process map with a derived systematic strategy will give companies an idea of how they can integrate predictive maintenance into existing processes. By incorporating the concept of a digital twin of a production machine, the interaction of measured and estimated as well as generated data by means of simulation, are shown. The digital twin could deliver results to retrofit data-driven prediction models, in order to improve the estimation of the RUL.
Full-text available
IoT enabled predictive maintenance allows companies in the energy sector to identify potential problems in the production devices far before the failure occurs. In this paper, we propose a method for early detection of faults in boiler feed pumps using existing measurements currently captured by control devices. In the experimental part, we work on real measurement data and events from a coal fired power plant. The main research objective is to implement a model that detects deviations from the normal operation state based on regression and to check which events or failures can be detected by it. The presented technique allows the creation of a predictive system working on the basis of the available data with a minimal requirement of expert knowledge, in particular the knowledge related to the categorization of failures and the exact time of their occurrence, which is sometimes difficult to identify. The paper shows that with modern technologies, such as the Internet of Things, big data, and cloud computing, it is possible to integrate automation systems, designed in the past only to control the production process, with IT systems that make all processes more efficient through the use of advanced analytic tools.
Full-text available
Deep Learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contribution using deep learning is largely focused on the model’s architecture. However, contributions regarding the improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is, therefore, an opportunity to improve upon the effectiveness of deep learning for system's prognostics and diagnostics without modifying the models' architectures. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and focal loss function for prognostics and diagnostics task are investigated. Dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, Deep Feedforward Neural Network, 1-Dimensional Convolutional Neural Network, Bidirectional Gated Recurrent Unit and Bidirectional Long Short-Term Memory on the Commercial Modular Aero-Propulsion System Simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions help us achieve significant improvement for Remaining Useful Life prediction and fault detection rate over non-weighted loss function predictions.
Full-text available
Nuclear infrastructure systems play an important role in national security. The functions and missions of nuclear infrastructure systems are vital to government, businesses, society and citizen's lives. It is crucial to design nuclear infrastructure for scalability, reliability and robustness. To do this, we can use machine learning, which is a state of the art technology used in various fields ranging from voice recognition, Internet of Things (IoT) device management and autonomous vehicles. In this paper, we propose to design and develop a machine learning algorithm to perform predictive maintenance of nuclear infrastructure. Support vector machine and logistic regression algorithms will be used to perform the prediction. These machine learning techniques have been used to explore and compare rare events that could occur in nuclear infrastructure. As per our literature review, support vector machines provide better performance metrics. In this paper, we have performed parameter optimization for both algorithms mentioned. Existing research has been done in conditions with a great volume of data, but this paper presents a novel approach to correlate nuclear infrastructure data samples where the density of probability is very low. This paper also identifies the respective motivations and distinguishes between benefits and drawbacks of the selected machine learning algorithms.
Successful diagnosis of system failures in nuclear power plants plays a central role in emergency response. Existing research focuses on diagnosis of operational failures that initiate an incident. During the incident progression, on-demand failures may occur and lead to severe consequences. However, little attention has been paid to this subject. In this paper, an approach for diagnosis of both operational and on-demand failures based on dynamic Bayesian networks is proposed. The general method of developing the dynamic Bayesian network model of a plant, the application of fuzzy sets theory in transforming real-valued sensor signals to discrete states, and the procedure for real-time inverse inference based on evidence is introduced. A case study of the proposed approach is conducted with the high temperature gas-cooled reactor nuclear power plant. The results from complete evidence and incomplete case that loses the most valuable sensor signals both demonstrate the effectiveness of the proposed approach.
LSTM network is an effective RNN model to predict the system RUL for its superior performance in sequential data processing. Usually, networks trained by life-cycle labeled dataset would possess similar RUL predicting accuracies, because the network training algorithm could ensure the network optimality for the whole training dataset. However, for networks trained by non-life-cycle labeled samples, the network uncertainty caused by different training conditions could lead to degradation prediction uncertainty for some local points. Further, the RUL predicting results that are computed by these uncertain local points may shows relatively large differences. Therefore, in order to obtain an accurate RUL prediction with networks trained by non-life-cycle labeled samples, our paper proposes a novel network model averaging method to deal with the network uncertainty. What's more, to learn the temporal correlation information of training samples sufficiently, we adopt the Bi-LSTM network to illustrate the application of the proposed network model averaging method. Finally, degradation values of Graphite/LiCoO2 battery are used to verify the effectiveness of the proposed method. The results show that the proposed method could improve the RUL prediction accuracy and reduce the prediction error.
Estimating the performance of base load combined cycle power plants and detecting early-stage malfunctions in equipment and processes is a difficult task that depends on complex thermodynamics. Herein, we demonstrate the efficacy of several machine learning methods in by-passing physics-based models to reliably estimate performance and detect anomalies in a representative combined cycle power plant with five years of recorded data. We model the full load power output of the plant by using ambient temperature, atmospheric pressure, relative humidity and exhaust vacuum pressure as input features using linear regression, support vector machines, random forests and artificial neural networks. Our results show that all the models estimate the power output with reasonable R² accuracy (>92%), while random forests perform the best (~96%) using less than half of the ~10,000 datapoints collected from the field. Finally, we show that unsupervised anomaly detection algorithms such as elliptical envelopes and isolation forests can be potential game changers for non-destructive health monitoring of equipment via identifying obscure sparse synthetic anomalies through investigating merely 1.5% of the dataset. This work presents a data science approach that can take advantage of the subtle interdependencies among the sensor data in power plants and extract useful insights which are unintelligible to humans. The methods presented here help in enabling better control over everyday operations and monitoring and reliable forecasting of hourly energy output.
For battery management system, accurate estimation of state of charge (SOC) and state of health (SOH), as well as prediction of remaining useful life (RUL) are of great significance. Herein, backward smoothing square root cubature Kalman filter (BS-SRCKF) is proposed to improve accuracy and convergence speed of SOC estimation. Then the multiscale hybrid Kalman filter (MHKF), which consists of BS-SRCKF and extended Kalman filter (EKF), is employed for the joint estimation of SOC and SOH. Furthermore, improved cuckoo search (ICS) algorithm is embedded in the standard particle filter (PF) to improve its performance, by transferring the particles in the prior distribution region to the maximum likelihood region. Eventually, RUL prediction is achieved based on the SOH information estimated by the joint estimation of SOC and SOH and the improved cuckoo search particle filter (ICS-PF). The simulation results demonstrate that the method for RUL prediction present in this paper has improved accuracy, confidence level and resampling rate compared with two existing methods based on PF and unscented particle filter (UPF).
Developing an accurate and reliable multi-step ahead prediction model is a key problem in many Prognostics and Health Management (PHM) applications. Inevitably, the further one attempts to predict into the future, the harder it is to achieve an accurate and stable prediction due to increasing uncertainty and error accumulation. In this paper, we address this problem by proposing a prediction model based on Long Short-Term Memory (LSTM), a deep neural network developed for dealing with the long-term dependencies in time-series data. Our proposed prediction model also tackles two additional issues. Firstly, the hyperparameters of the proposed model are automatically tuned by a Bayesian optimization algorithm, called Tree-structured Parzen Estimator (TPE). Secondly, the proposed model allows assessing the uncertainty on the prediction. To validate the performance of the proposed model, a case study considering steam generator data acquired from different French nuclear power plants (NPPs) is carried out. Alternative prediction models are also considered for comparison purposes.
The maintenance, repair, and rehabilitation of industrial reactors are expensive and time-consuming. Sudden interruptions may adversely affect the production process and may lead to harmful effects and disastrous results. Therefore, lifetime prediction is extremely important to prevent catastrophic breakdowns leading to complete cessation of production. This paper aims to propose a prognosis reliable method that can be used to estimate the degradation path of a distillation column and calculate the lifetime percentage of this system. The work presents a direct monitoring approach based on the technique of adaptive neuro-fuzzy inference system (ANFIS) combined with fuzzy C-means algorithm (FCM). At the beginning, ANFIS is used to detect the small variations in the signal over time. Secondly, a new strategy is proposed to find the system degradation path. Thirdly, ANFIS is combined with FCM to predict the future path and calculate the lifetime percentage of the system. The methodology is tested on real experimental data obtained from a distillation column. Results demonstrate the validity of the proposed technique to achieve the needed objectives with a high-level accuracy, especially the ability to determine a more accurate Remaining Useful Life (RUL) when it applied on the automated distillation process in the chemical industry.