No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A review on machinery diagnostics and prognostics implementing condition-based maintenance
Abstract
Condition-based maintenance (CBM) is a maintenance program that recommends maintenance decisions based on the information collected through condition monitoring. It consists of three main steps: data acquisition, data processing and maintenance decision-making. Diagnostics and prognostics are two important aspects of a CBM program. Research in the CBM area grows rapidly. Hundreds of papers in this area, including theory and practical applications, appear every year in academic journals, conference proceedings and technical reports. This paper attempts to summarise and review the recent research and developments in diagnostics and prognostics of mechanical systems implementing CBM with emphasis on models, algorithms and technologies for data processing and maintenance decision-making. Realising the increasing trend of using multiple sensors in condition monitoring, the authors also discuss different techniques for multiple sensor data fusion. The paper concludes with a brief discussion on current practices and possible future trends of CBM.
... Systemic maintenance involves performing maintenance tasks at predetermined intervals or based on established criteria to prevent failures. CBM relies on the real-time monitoring and analysis of equipment conditions to schedule maintenance activities precisely when needed [7]. maintenance has been emphasized for its role in enhancing cost effectiveness, availability, process quality, and safety compliance [2,3]. ...
... Systemic maintenance involves performing maintenance tasks at predetermined intervals or based on established criteria to prevent failures. CBM relies on the real-time monitoring and analysis of equipment conditions to schedule maintenance activities precisely when needed [7]. Given that at its core maintenance is about restoring a degraded entity to a useful state [8], degradation modeling is a major step in CBM [9]. ...
... Optimize Xt using Equations (7) to (9) 11: Else, set = 0 ...
To enhance maintenance endeavors, it is imperative to gain a deep understanding of system degradation. In systems with degradation-aware control, observing degradation becomes particularly challenging. Even with sensors, such controllers continuously mitigate deviations to ensure the system operates within optimal limits. Here, we propose a framework explicitly tailored for degradation-aware control systems, built upon two main components: (1) degradation modeling to estimate and track hidden degradation over time and (2) a Long Short-Term Memory Autoencoder-Degradation Stage Detector (A-LSTMA-DSD) to define alarm and failure thresholds for enabling condition-based maintenance. In degradation modeling, the framework utilizes actuator measurements to model hidden degradation. Next, an A-LSTMA-DSD model is developed to flag anomalies, based on which alarm and failure thresholds are assigned. These dynamic thresholds are defined to ensure sufficient time for addressing maintenance requirements. Working with real data from a boiler unit in an oil refinery and focusing on steam leakages, our proposed framework successfully identified all failures and on average triggered alarm and failure thresholds 15 and 8 days in advance of failures, respectively. In addition to triggering these thresholds, our system outperforms baseline models, such as CNN, LSTM, ANN, ARIMA, and Facebook Profit, in identifying failures by 60% and 95%, respectively.
... For example, when will a component fail? Use statistics of historical performance and current readings of multiple sensors to build a model to predict failure periods such that the resource is able to put plans in place proactively (Jardine et al, 2006). ...
... Risk Classification: Algorithms also pinpoint higher risk parts which will focus the maintenance effort on the most critical components (Jardine et al., 2006). ...
A detailed investigation of shipyard operations was conducted during a laborious internship at Hindustan Shipyard in Visakhapatnam. The research uses cutting-edge methodologies to investigate shipyard operations, providing new perspectives on procedures not before examined in similar industrial settings. The study provides novel equipment maintenance and monitoring approaches by integrating real-time sensor technology, statistical analysis, Deep Learning/Machine Learning algorithms, and cutting-edge data analytics. Using these techniques, maintenance plans can be improved, prospective problems can be predicted, and equipment reliability, cost reduction and operating efficacy can all be increased. These advancements significantly improve project management efficiency by streamlining workflows, shortening turnaround times, and enabling proactive decision-making. The research employs data-driven methodologies to analyze operational parameters, detect anomalies, and predict maintenance needs, reducing emergency repairs and operational disruptions. The findings underscore the critical role of Al in modernizing shipyard Maintenance, Repair, and Overhaul (MRO) services, offering a scalable solution for cost-effective, efficient maritime operations.
... Next, we move on to the details of smart maintenance implementation for BMC. Since managers rely on predicted improvements in KPIs and ROI for making key decisions such as smart maintenance adoption, a sufficiently detailed performance model for BMC is developed and illustrated in Figure 7. Studies have shown that benefits to implementing CBM include lower maintenance costs due to non-redundant maintenance efforts and lower machine downtimes [33,47]. From a system performance point of view, CBM reduces production uncertainty and provides stable and higher throughput. ...
... More specifically, the performance model is used to estimate the change in process variability under CBM. as smart maintenance adoption, a sufficiently detailed performance model for BMC is developed and illustrated in Figure 7. Studies have shown that benefits to implementing CBM include lower maintenance costs due to non-redundant maintenance efforts and lower machine downtimes [33,47]. From a system performance point of view, CBM reduces production uncertainty and provides stable and higher throughput. ...
This paper proposes a pathway for smart maintenance by addressing overarching questions and key impediments that arise when manufacturing companies are exploring investments in such projects. The proposed pathway consists of seven distinct steps at which analytical models are used to predict the impact of smart maintenance on system-level operational key performance indicators (KPIs) and the resulting return on investment (ROI). The key advantage of this approach is that the analytical models rely on a few parameters and, therefore, can be used even when there are no sophisticated data collection systems in place, such as in the case of many small and medium enterprises (SMEs). Furthermore, the proposed approach allows for the development of a “personalized” pathway along with the prediction of performance improvement and ROI impact, enabling management to make investment decisions with greater confidence. The proposed pathway also consists of a three-step detour for companies unprepared to embark on their journey towards smart maintenance. The application of the proposed smart maintenance pathway is illustrated through case studies consisting of three real SMEs. First, for companies that are unprepared for smart maintenance, we suggest traditional variance reduction methods and appropriate performance improvement goals along with predicted improvements in operational and financial KPIs. Next, for companies that are prepared to embark on smart maintenance, we provide a detailed evaluation of the impact of condition-based maintenance (CBM) by analyzing various machine combinations that maximize performance-to-cost ratio. In the case of one SME, our analysis shows that an improvement in throughput (0 to 3%) with an ROI (26:1) is achievable through the adoption of smart maintenance, which can be visualized using the DuPont Model.
... Historically, preventive maintenance techniques have typically been used to minimize failures in manufacturing cells using maintenance strategies such as breakdown maintenance, preventive maintenance, and condition-based maintenance, including models and algorithms in manufacturing [12][13][14]. However, nowadays, other kinds of strategies are also considered. ...
... Examples of these techniques are cloud-based predictive maintenance [15] and mobile agent technologies [16]. According to [12], maintenance approaches capable of monitoring equipment conditions for diagnostic and prognostic purposes can be grouped into three main categories: statistical approaches, artificial intelligence approaches and model-based approaches. As model-based approaches need mechanistic knowledge and theory of the equipment to be monitored, and statistical approaches require mathematical background, artificial intelligence approaches, and machine learning techniques in particular, have been increasingly applied in predictive maintenance applications [17,18]. ...
Predictive maintenance in manufacturing industry applications is a challenging research field. Packaging machines are widely used in a large number of logistic companies’ warehouses and must be working uninterruptedly. Traditionally, preventive maintenance strategies have been carried out to improve the performance of these machines. However, these kinds of policies do not take into account the information provided by the sensors implemented in the machines. This paper presents an expert system for the automatic estimation of work orders to implement predictive maintenance policies for packaging machines. The central innovation lies in a two-stage process: a classifier generates a binary decision on whether a machine requires maintenance, and an unsupervised anomaly detection module subsequently audits the classifier’s probabilistic output to refine and interpret its predictions. By leveraging the classifier to condense sensor data and applying anomaly detection to its output, the system optimizes the decision reliability. Three anomaly detection methods were evaluated: One-Class Support Vector Machine (OCSVM), Minimum Covariance Determinant (MCD), and a majority (hard) voting ensemble of the two. All anomaly detection methods improved the baseline classifier’s performance, with the majority voting ensemble achieving the highest F1 score.
... 104 The CBM includes all those innovative maintenance methods in which interventions are planned based on the actual health status of the system, this is the core of modern PdM that significantly reduces maintenance costs by decreasing the number of unnecessary planned interventions and optimising availability at the same time, interrupting the service only in the event of proven criticality. 105 Although there is no canonical methodology for the implementation of a PHM strategy, several authors have investigated the field of prognostics, looking for common aspects. 106,107 Some authors have even suggested a global architecture for PHM. ...
... The models used to evaluate the conditions of the railway infrastructure for diagnostic and prognostic purposes can be grouped into three categories: mechanical, Data-Driven and hybrid prognostics models. 102,105 Mechanical models are developed starting from physical models that describe the behaviour of the system in steady state considering the possible occurrence of faults. Designing models of this type requires excellent knowledge of the system and the failure mechanisms, which is often not exhaustively available due to the numerous variables that influence the system. ...
The efficiency and availability of modern railway infrastructure plays an increasingly strategic role in the sustainability, development and prosperity of communities and nations. Recent Artificial Intelligence (AI) algorithms, which enable the use of digital tools such as Data-Driven models that can automatically adapt system operation, make decisions and suggest strategies based on collected data, form the basis of modern Predictive Maintenance (PdM). PdM is considered a key opportunity for accurate Structural Health Monitoring (SHM), especially for railway infrastructure, where the transition from traditional preventive or periodic maintenance to PdM will reduce intervention times and costs. Furthermore, by directly correlating actual infrastructure conditions with measured information, SHM can utilise a limited number of sensors installed on critical components such as insulated rail joints. This review starts by clearly describing the different components that make up the railway infrastructure, the monitoring systems currently in use and the technical performance parameters that indicate their health status and goes on to examine the issues related to the SHM and related modern digital tools. All these topics are summarised to provide an effective theoretical and practical knowledge of SHM for railway infrastructure, to better understand the current transformation of the sector and to predict future developments.
... CBM bergantung pada asumsi bahwa sebagian besar kerusakan tidak terjadi secara instan, dan mungkin untuk mendeteksi kemunculannya pada tahap awal proses kerusakan (Teixeira et al., 2020). Tujuan utama CBM adalah untuk merekomendasikan keputusan pemeliharaan berdasarkan informasi yang diperoleh melalui pemantauan kondisi (Jardine et al., 2006). ...
Condition-Based Monitoring (CBM) merupakan metode pemeliharaan prediktif yang mengandalkan pemantauan parameter operasional untuk mendeteksi dini potensi kerusakan. Penelitian ini mengembangkan model CBM multi-parameter untuk memantau kondisi pompa sentrifugal pada sistem distribusi air bersih. Parameter yang diamati mencakup getaran, suhu, dan tekanan, yang dikumpulkan secara berkala dari empat unit pompa. Pengukuran dilakukan menggunakan vibration meter, infrared thermometer, dan manometer. Data dianalisis untuk mendeteksi tren degradasi dan anomali operasional. Hasil penelitian menunjukkan bahwa suhu dan tekanan pada beberapa pompa mengalami fluktuasi, sedangkan nilai getaran tetap berada dalam ambang batas aman. Pompa dengan suhu dan tekanan tidak stabil berpotensi mengalami degradasi performa yang lebih cepat. Penerapan CBM memungkinkan deteksi dini terhadap potensi kegagalan, sehingga dapat mengurangi risiko downtime dan meningkatkan efisiensi pemeliharaan. Studi ini menekankan pentingnya pemantauan berbasis kondisi dalam menjaga keandalan sistem distribusi air bersih, terutama di lingkungan pendidikan yang memiliki keterbatasan anggaran pemeliharaan. Penelitian ini merekomendasikan pemantauan jangka panjang serta analisis lebih lanjut terhadap hubungan antara performa pompa dan konsumsi energi.
... The conventional maintenance strategies for PV systems have predominantly been reactive, where maintenance activities are only performed following a system failure or noticeable reduction in performance [4]. However, the approach often leads to unplanned system downtime, potential losses in energy production, and significant repair costs, thus hindering the economic viability and sustainability of PV power systems [5]. The need for a more effective maintenance strategy has led to an increasing interest in predictive maintenance approaches [6]. ...
... 4 shows the case analysis results of battery life prediction, including prediction error and prediction interval.(Jardine, A. K. S., Lin, D. & Banjevic, D., 2006) ...
With the rapid development of the new energy vehicle industry, the reliability and life of its parts have become the key factors affecting the performance and safety of the whole vehicle. This paper aims to provide a scientific basis for the maintenance and life management of new energy vehicles through the research on the reliability analysis and life prediction model of new energy vehicle parts. Firstly, the basic theory of reliability engineering is reviewed, and the research progress and existing problems of the existing life prediction models are comprehensively analyzed. On this basis, a data-driven life prediction model is proposed in this paper, which comprehensively uses the methods of machine learning, statistical analysis and reliability engineering to improve the accuracy and practicability of the prediction. In the research, the operation and maintenance data of new energy vehicle parts are collected, and the failure modes of the parts are deeply analyzed. Using fault tree analysis (FTA) and reliability parameter estimation methods, the key factors affecting the life of the parts are identified. Furthermore, the key features affecting the life are extracted through feature engineering, and the life prediction model is constructed by using machine learning methods. In the process of model construction, special attention is paid to the generalization ability and robustness of the model to ensure its applicability under different working conditions and environments. In order to verify the effectiveness of the model, this paper selects the battery and motor of new energy vehicles as cases to carry out the practical application and verification of the model. The results show that the proposed model is superior to the traditional methods in prediction accuracy and can provide strong support for the maintenance decision of new energy vehicle parts. Finally, this paper discusses the challenges that the model may face in practical application and puts forward suggestions for future research directions.
... As a result, conventional vibration analysis methods, such as time domain and frequency domain analysis, become less effective in detecting faults within the gearbox. The presence of high levels of noise obscures the patterns that these methods rely on, complicating the identification of potential issues [12,13]. To handle fault detection difficulties, artificial neural networks (ANN) [6,14], support vector machines (SVM) [15], genetic algorithms (GA) [16], signal decomposition approaches [17], and support vector data descriptions [18] have all been developed recently. ...
Gearbox, which is one of the most important and frequently used components among mechanical power transmission systems, has often been observed to occur in gear surface pitting faults in industrial applications that require high torque. For the diagnosis of gear pitting faults, vibration analysis is one of the commonly utilized techniques. Recently, there has been an increasing interest in applying deep learning approaches for classification and learning feature representations. Deep learning provides an excellent opportunity to integrate vibration signals for gear pitting fault diagnosis. Therefore, in this study, autoencoder models Contractive Autoencoder (CAE), Sparse Autoencoder (SAE) and Variational Autoencoder (VAE) are used to extract deep feature representations of gear pitting data. Without using any additional feature extraction techniques, in this study uses the raw vibrational data directly to identify the local gear pitting faults. Experimental results have shown that Sparse Autoencoder is a viable and efficient feature extraction method and provides a new research method for gear pit fault diagnosis.
... Predictive maintenance is an advanced approach that uses condition monitoring techniques and data analysis to predict when equipment failure might occur. This strategy aims to perform maintenance at the optimal time, just before a failure is likely to happen [4]. ...
This article presents a comprehensive review of predictive maintenance strategies enhanced by real-time data processing in industrial settings. As industries transition from reactive and preventive maintenance approaches to more sophisticated predictive methods, the integration of advanced data-driven techniques has become crucial. We explore the evolution of maintenance strategies, highlighting the limitations of traditional methods and the transformative potential of predictive maintenance. The article emphasizes the pivotal role of real-time data processing in enabling accurate failure predictions and timely interventions. By examining various real-time data handling techniques such as edge computing, stream processing, and in-memory computing, we illustrate how these technologies contribute to reducing unplanned downtime, extending equipment lifespan, and optimizing maintenance costs. Case studies from manufacturing, energy, and transportation sectors demonstrate the practical implementation and benefits of these advanced maintenance systems. Furthermore, we discuss future trends, including the integration of artificial intelligence and machine learning, while addressing challenges related to cybersecurity, scalability, and standardization. This article provides valuable insights for researchers and practitioners seeking to leverage real-time data processing to enhance predictive maintenance strategies and improve overall operational efficiency in industrial environments.
... The primary aim of scheduled maintenance is to maintain equipment in its optimal condition, ensuring optimal functionality and extending its operational lifespan for an extended period (Arunraj & Maiti, 2007;Smith & Hawkins, 2004). In contrast, condition-based maintenance relies on data collected during monitoring periods to determine suitable maintenance recommendations (Jardine et al., 2006). Maintenance tasks are performed upon reaching predetermined thresholds, guided by specific indicators identified beforehand. ...
Arduino microcontroller and ADXL accelerometer are commonly paired devices, often considered for creating inexpensive vibration analysers. Many researchers have proven that both pairing devices have good performance in vibration measurement and have the potential for commercialisation. This study evaluates the feasibility of vibration measurement and monitoring using an Arduino microcontroller with an inexpensive accelerometer in detecting anomalies during water pump operation. A dedicated Arduino Mega and an ADXL345 accelerometer were attached to a water pump motor to facilitate continuous monitoring of vibrations. The vibration measurement was set at a sampling rate of 530 Hz. Vibration data in RMS value was sent to the cloud storage for monitoring. Raw data captured during normal and abnormal conditions were collected at the site when anomalies were detected for further analysis. The results showed that the abnormal conditions could be clearly differentiated from normal conditions using the Fast Fourier Transform method and spectrogram analysis. In summary, this study confirms that integrating the Arduino Microcontroller with the ADXL accelerometer effectively detects irregularities in the operating conditions of the water pump.
... A program based on Condition-Based Maintenance (CBM) offers valuable insights to inform maintenance decisions, thereby enhancing the safety, reliability, and maintainability of engineering systems [2][3][4][5]. Therefore, system-level real-time condition assessment is becoming more attractive. ...
To enable early identification of failure risks in ship systems and equipment, a dynamic cloud center of gravity model is developed for real-time system-level health assessment. First, the Functional Analysis System Technique (FAST) was applied to decompose the operational functions and dependencies of the intelligent machinery room system, enabling the structured establishment of a hierarchical evaluation index system. The comprehensive weight is derived through synergistic application of the fuzzy set (FS) theory and entropy weight. This process integrated expert-defined functional boundaries with measurable parameters critical to system performance. Then, an improved cloud center of gravity method based on the Gaussian cloud model and sliding time window method is used for the system’s adaptive health value calculation. The dynamic health model can achieve continuous online assessment and track the further evolution of the system. Finally, the proposed model is applied to the Fuel Oil Supply System (FOSS). The integration of system performance output and disassembly inspection results demonstrates that the method proposed in the article more accurately reflects the true health status changes in the system when mapping health values.
... Recently, prognostics and health management (PHM) have been key in intelligent operation and maintenance. Particularly, in terms of remaining useful life (RUL) prediction, the application of PHM is key in ensuring operational safety, extending service life, and reducing maintenance costs [1]. ...
Remaining useful life (RUL) prediction is the core of intelligent operation and maintenance, improving operation and maintenance efficiency and reducing maintenance costs. Aiming at the limitations of RUL prediction methods based on mathematical derivation in terms of adaptability and flexibility, this paper proposes a probabilistic RUL simulation method for complex systems or complex degradation processes. The method constructs a degradation model using a complex nonlinear Wiener process, estimates the model parameters using maximum likelihood estimation, and updates the stochastic parameters based on the Bayesian updating strategy. On this basis, the prediction of probabilistic RUL is realized by the simulation algorithm. Compared with the mathematical derivation method, the prediction of the method proposed in this paper is accurate, which verifies the effectiveness and practicality of the simulation method. In a complex system or complex degradation process, the method in this paper can construct the probabilistic RUL prediction model faster.
... Subsequently, pointwise convolution performs multi-scale fusion of these preprocessed local features across multiple parallel branches, avoiding the parameter explosion and local information loss problems that would occur with direct pointwise convolution [29]. The operation can be expressed as ...
Vibration signals serve as the primary data source for bearing fault diagnosis. However, when collected in complex industrial environments, these signals are often contaminated by noise interference, posing significant challenges to fault feature extraction and diagnostic accuracy. To address these issues, this paper proposes a novel bearing fault diagnosis network architecture: the Multi-Resolution Fusion Selection Network (MR-FuSN). The MR-FuSN effectively extracts domain-invariant features from input data through multi-resolution feature extraction and incorporates an adaptive kernel convolution strategy, thereby enhancing its robustness against environmental noise. Experimental results demonstrate that the MR-FuSN achieves outstanding performance in noisy environments with signal-to-noise ratios (SNRs) ranging from −5 dB to 10 dB, particularly attaining a diagnostic accuracy of 99.97% under 0 dB conditions. This study provides technical support for practical fault diagnosis applications.
... Traditional maintenance practices often rely on scheduled maintenance or manual inspections, which can be both costly and inefficient. Predictive maintenance, powered by IIoT and data-driven techniques, seeks to address this challenge by enabling the real-time monitoring and early detection of anomalies, including bearing faults [3]. The ability to detect bearing issues in their early stages allows for timely intervention, reducing downtime and maintenance costs. ...
In the realm of Industrial Internet of Things (IIoT), where reliability of machinery is paramount, the early fault detection of bearing is a critical aspect of predictive maintenance. In our innovative approach, we have seamlessly integrated Rule-Engine-based logic into the Industrial Internet of Things (IIoT) framework, harnessing the power of Machine Learning (ML) and Deep Learning (DL) algorithms for bearing fault detection. Our study demonstrates remarkable results, showcasing substantial improvements in predictive accuracy. Specifically, we observed that employing traditional ML algorithms along with rule engine staggering significant accuracy boost. Furthermore, by using DL algorithms, we achieved similarly impressive outcomes, albeit with considerably larger computational overheads. Intriguingly, the incorporation of Rule-Engine-based (RE) logic allowed us to attain the same level of performance as normal ML, all while significantly reducing processing requirements. This transformative methodology has been meticulously validated using the widely recognized Case Western Reserve University (CWRU) dataset, substantiating its practical feasibility and effectiveness. Our research underscores the potential of integrating Rule-Engine-based systems within IIoT environments, illustrating how this synergy can yield substantial enhancements in bearing fault detection accuracy, rivaling the results achieved through resource-intensive DL techniques. By presenting compelling evidence of the efficacy of our approach with the CWRU dataset, we provide valuable insights into the optimization of predictive maintenance strategies in industrial settings. This work not only contributes to the advancement of IIoT-driven predictive maintenance but also highlights the importance of judiciously combining established Rule-Engine-based logic with state-of-the-art ML algorithms for achieving reliable and efficient fault detection.
... challenging due to their inaccessibility for visual inspection and their close integration with other components of rotating machinery. Analyzing the vibration signals of rotating machinery offers a viable solution for monitoring bearing health without the need for visual inspection [2]. Faulty bearings typically produce distinct abnormal impulsive signals, caused by rolling elements striking damaged areas. ...
This paper presents a bearing fault diagnosis model based on a simulated data-driven time-domain and frequency-domain feature fusion using a one-dimensional convolutional neural network (1D CNN). The proposed simulation data-driven time–frequency feature fusion 1D CNN multiscale attention (TFF-MSA) model solves the problem of insufficient generalization ability due to the scarcity of experimental data through the simulation data of the dynamic model of bearings, and accurately classifies the bearing faults in a strong noise environment. Traditional 1D CNN-based bearing fault diagnosis models often focused on either time-domain signals or frequency-domain spectra. The proposed model incorporates a parallel 1D CNN structure that simultaneously extracts features from both the time and frequency domains. These multi-domain features are then fused to capture comprehensive information from the bearing vibration signals. Specifically, to enhance the extraction of time-domain features, we introduce the pyramid attention module to mine multiscale features. Meanwhile, in the frequency-domain feature extraction, a specific fault feature frequency weighting method, allowing the proposed model to extract specific fault-related frequencies from the signals, is also proposed. Experimental results demonstrate that the proposed model which is only driven by simulated signals from dynamic model achieves an average diagnostic accuracy of 94%.
... Continuous analysis of a system's operational life-cycle can bring several benefits, such as improving machine availability and productivity, and decreasing maintenance expenses. [1]. To achieve these objectives, a CM program, based on diagnostics and prognostics, can minimize the number of maintenance operations using three main steps: data acquisition, processing and informed decision making [2]. ...
Recently, several machine learning approaches have been proposed to provide predictions of the remaining useful life of rotating machine. This study presents a strong framework that employs machine learning algorithms to predict the useful life of rotating machine bearings by evaluating their vibration signals. In this approach, the raw vibration signal undergoes feature extraction through auxiliary methods, trend analysis through statistical methods, and time-dependent feature extraction through a specialized hybrid neural network algorithm. The architecture is composed of three distinct phases: Feature analysis, where the raw vibration data are processed to extract important characteristics for the definition of the signal trend creating a time series and Modeling, where the training data is processed in a hybrid convolutional neural network, which returns a degradation model aiming at estimating the instant of total failure. The neural network is also utilized to analyze test data and identify the moment just prior to the occurrence of failure; and finally the Prediction, phase where the future failure trend of the test data is identified, using the failure threshold extracted from the training data. We used the architecture to predict the remaining useful life of rotating machines in various cases, and the results error ranged between 3 and 4%, which is considered a good result.
... Al proporcionar datos en tiempo real sobre el estado de los equipos, el IoT facilita la implementación de estrategias de mantenimiento predictivo y el mantenimiento autónomo, lo que se traduce en una mejora de la eficiencia general de los equipos (OEE) (Pomorski, 2004) . Se da un proceso de evolución así los CMMS también han evolucionado para incluir funcionalidades avanzadas, como el mantenimiento predictivo basado en el análisis de datos de sensores (Jardine et al., 2006). Estas nuevas capacidades han permitido a las empresas anticipar y prevenir fallas de los equipos, lo que contribuye a mejorar la confiabilidad y disponibilidad de los activos. ...
Resumen El Mantenimiento Productivo Total (TPM) como estrategia integral ha demostrado reducir los costos de mantenimiento, aumentar la disponibilidad de equipos y mejorar la calidad. Sin embargo, su adopción global ha sido desigual: algunas regiones lideran su implementación, mientras que otras enfrentan desafíos como la falta de compromiso de la alta dirección, resistencia al cambio y capacitación insuficiente del personal. La tecnología IoT ha sido fundamental en la evolución del TPM, permitiendo la recopilación de datos en tiempo real que facilita el mantenimiento predictivo, mejora la eficiencia general de los equipos y permite la detección temprana de problemas. Además, el desarrollo de software de gestión de mantenimiento (CMMS) también ha sido clave, ya que permite a las empresas gestionar de manera más eficiente las actividades de mantenimiento. La integración del CMMS con otros sistemas empresariales ha mejorado la alineación con los objetivos generales. La estrategia de Mejora Continua (MC) es fundamental para maximizar la eficiencia y calidad en el contexto del TPM, ya que identifica y corrige fallas, facilita la participación de los operadores y crea un entorno de aprendizaje continuo. La aplicación de la MC en la gestión de calidad permite identificar y corregir defectos en los productos antes de su envío al cliente, mejorando la calidad y reduciendo costos. Las tendencias actuales resaltan la importancia de la estrategia integral del TPM, la tecnología IoT, los sistemas CMMS y la mejora continua para lograr una mayor eficiencia, confiabilidad y productividad, aunque aún persisten desafíos en la adaptación a diferentes contextos geográficos. Abstract Total Productive Maintenance (TPM) as a comprehensive strategy has been proven to reduce maintenance costs, increase equipment availability, and improve quality. However, its global adoption has been uneven: some regions lead its implementation, while others face challenges such as lack of senior management commitment, resistance to change, and insufficient staff training. IoT technology has been instrumental in the evolution of TPM, enabling real-time data collection that facilitates predictive maintenance, improves overall equipment efficiency, and allows for early problem detection. In addition, the development of computer maintenance management software (CMMS) has also been key, as it allows companies to more efficiently manage maintenance activities. Integrating CMMS with other business systems has improved alignment with overall goals. The Continuous Improvement (CI) strategy is critical to maximizing efficiency and quality in the context of TPM, as it identifies and corrects faults, facilitates operator engagement, and creates a continuous learning environment. The application of MC in quality management allows for the identification and correction of defects in products before they are sent to the customer, improving quality and reducing costs. Current trends highlight the importance of a comprehensive TPM strategy, IoT technology, CMMS systems and continuous improvement to achieve greater efficiency, reliability and productivity, although challenges remain in adapting to different geographical contexts.
... The approach of CBM includes constant or discrete monitoring of features that indicate the health state of an object. Consequently, faulty or conspicuous components can be replaced before a critical failure occurs (Erbe et al. 2005;Jardine et al. 2005;Mehta et al. 2015). While CBM offers a good starting point for data-driven maintenance, this strategy does not estimate the future state. ...
Predictive maintenance (PdM) is a data-driven maintenance strategy that aims to avoid unplanned downtimes by predicting the remaining lifetime of maintenance objects. Thus, unnecessary replacements of spare parts and critical process disturbances due to breakdowns can be avoided. Despite the widely recognized advantages of this technology, the number of successful applications in practice is still very limited. Our study aims to address the theory-practice gap by conducting a comprehensive case study involving 15 expert interviews with industry professionals to uncover critical factors that hinder the successful implementation of PdM. Our findings shed light on the underlying reasons for a hesitant PdM implementation, including challenges related to digital readiness, data quality and accessibility, technological integration, and maintenance organization. By providing an in-depth analysis of these factors, our study offers valuable insights and guidelines to improve the implementation success rate of PdM in the industrial context. Based on the empirical findings, we present critical implementation factors and develop a framework with ten propositions that aim to dismantle barriers in the industrial application process of PdM and stimulate further research in academia.
... In industrial applications, predictive maintenance and quality estimation are areas where both OPC and FL methods can be effectively applied. Predictive maintenance aims to monitor the performance of machines and equipment to anticipate failure risks [10]. The use of FL in predictive maintenance applications ensures data security by processing data locally [11]. ...
This study examines the benefits of applying federated learning (FL) technology to OPC (Operational Performance Control) systems within industrial automation and data analysis processes. FL enables each production facility to process its data locally while only transmitting model parameters to a central server, thereby preserving data privacy. This approach provides significant advantages in industrial environments, particularly concerning data privacy and communication costs. The study evaluates FL's potential to ensure data privacy, reduce communication costs, improve efficiency in training time, and deliver high performance in predictive maintenance and quality estimation. Model performance was analyzed using accuracy, F1 score, precision, and loss metrics; the results demonstrated that FL achieved a 90% accuracy rate, offering competitive performance compared to centralized modeling. In predictive maintenance and quality analysis specifically, FL achieved 85-88% accuracy while reducing network data load by 65%. These findings validate that FL provides a secure, cost-effective, and efficient solution for industrial data analysis processes by eliminating the need for centralized data collection. In conclusion, FL and OPC integration supports data privacy, cost savings, and communication efficiency in industrial processes. The study highlights that FL could become a prevalent technology in industrial data analysis, establishing a new standard particularly in digital manufacturing processes.
... • Mobley [38] indicates that predictive maintenance can reduce maintenance costs by 12% to 18% compared to preventive maintenance while improving operational efficiency. Additionally, Jardine et al. [39] show that predictive maintenance can reduce downtime and increase equipment lifespan through continuous monitoring of machine conditions. ...
Optimizing maintenance and enhancing the performance of businesses are significant concerns in the modern industrial world. Predictive maintenance is emerging as an innovative approach to address these challenges, allowing companies to shift from corrective maintenance to preventive maintenance. Predictive maintenance relies on the use of advanced technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML) to collect and analyse real-time data from equipment. Through this predictive analysis, it becomes possible to identify early warning signals of failures, enabling the anticipation of potential issues and the proactive planning of maintenance interventions. In this study, we will thoroughly examine the impact of predictive maintenance on the performance of businesses. We will explore the benefits and opportunities it offers in terms of reducing downtime, optimizing maintenance costs, and enhancing productivity. We will also investigate the various technologies and methods used in the implementation of predictive maintenance, along with potential challenges and best practices for successful adoption. This research focuses on studying the application of predictive maintenance within a company using data science and machine learning methods. Predictive maintenance represents an innovative approach aimed at anticipating equipment failures by leveraging real-time collected data. Through the analysis of this data using sophisticated algorithms, it becomes possible to identify early signals of potential problems and implement preventive maintenance actions before breakdowns occur. This approach not only reduces unexpected downtime but also optimizes maintenance operations by avoiding unnecessary interventions and maximizing resource utilization. The ultimate goal is to improve equipment availability, optimize operational performance, and maximize the overall yield of the company.
Industrial pumps are essential components in various sectors, such as manufacturing, energy production, and water treatment, where their failures can cause significant financial and safety risks. Anomaly detection can be used to reduce those risks and increase reliability. In this work, we propose a novel enhanced convolutional neural network (ECNN) to predict the failure of an industrial pump based on the vibration data captured by an acceleration sensor. The convolutional neural network (CNN) is designed with a focus on low complexity to enable its implementation on edge devices with limited computational resources. Therefore, a detailed design space exploration is performed to find a topology satisfying the trade-off between complexity and accuracy. Moreover, to allow for adaptation to unknown pumps, our algorithm features a pump-specific parameter that can be determined by a small set of normal data samples. Finally, we combine the ECNN with a threshold approach to further increase the performance and satisfy the application requirements. As a result, our combined approach significantly outperforms a traditional statistical approach and a classical CNN in terms of accuracy. To summarize, this work provides a novel, low-complex, CNN-based algorithm that is enhanced by classical methods to offer high accuracy for anomaly detection of industrial pumps.
Reliability modeling plays a crucial role in assessing the performance and lifespan of industrial systems, especially when subjected to environmental factors such as particulate matter and operational time constraints. This study examines the impact of prolonged operational periods on system reliability, integrating environmental degradation factors into predictive maintenance strategies. Traditional reliability models often overlook the influence of environmental stressors, leading to inaccurate failure predictions and inefficient maintenance schedules. This research incorporates environmental failure parameters, including particulate contamination and temperature fluctuations, into reliability modeling to enhance accuracy in failure forecasting. By integrating data-driven approaches and statistical failure models, the study proposes a framework that improves predictive maintenance strategies, minimizes unplanned downtimes, and optimizes system performance. The findings emphasize the necessity of accounting for environmental conditions in reliability analysis, ensuring a more comprehensive assessment of manufacturing and industrial equipment reliability. The study contributes to advancing maintenance decision-making processes, reducing operational risks, and increasing the efficiency of industrial systems operating under challenging environmental conditions.
Purpose
This paper aims to propose a methodology to assist manufacturing companies in the implementation of condition-based maintenance (CBM) to their equipment. The developed methodology intends to consider the use of sensors already installed on the equipment and, when required, to support the selection of sensors available on the market. Since CBM using sensors is not always feasible, the information gathered for the feasibility study of CBM implementation is also used to assign other maintenance strategies.
Design/methodology/approach
Based on the literature review, requirements and specifications were established for endowing the methodology with relevant and distinctive characteristics. The structure of the methodology and the associated steps were defined based on this information. Then, the methodology was validated and refined using a case study.
Findings
In the case study company, following the methodology and the respective steps, appropriate maintenance strategies were assigned to a selected manufacturing machine, considering information related to the failure modes with the most significant impact, and CBM was applied to a selected component for which the benefit outweighs the costs involved, using data acquired by sensors subsequently installed on the analyzed machine.
Practical implications
Due to its comprehensiveness, this methodology can contribute to make CBM implementation accessible to a high number of companies and encourage the application of a wide variety of monitoring techniques.
Originality/value
This new methodology can be easily integrated into a computerized maintenance management system and has the advantage of facilitating the collection, organization and standardization of technical knowledge required to support CBM implementation and define the most appropriate maintenance strategy systematically and automatically. It guides the prioritization of equipment and failure modes, and the decision-making regarding the selection of sensors and the allocation of maintenance strategies with the aim of reducing costs.
In the literature, maintenance plan efficacy is often assessed based on the long-term predicted maintenance cost rate, indicating a performance-centric approach. However, this criteria does not account for the fluctuation in maintenance costs over renewal cycles, and typical solutions may not be adequate from a risk management standpoint, a robustness viewpoint. This study tries to rethink standard solutions considering both performance and robustness, and thus, offer more suitable maintenance options.Specifically, using the long-term expected maintenance cost rate as the performance metric and the variance of maintenance cost per renewal cycle as the robustness metric, the study examines two representatives of time-based and condition-based maintenance approaches: a block replacement strategy and a periodic inspection and replacement strategy. Mathematical cost models are created based on the homogeneous Gamma degradation process and probability theory.Comparative study of both maintenance techniques demonstrates that the higher-performing approach carries a larger amount of risk. Consequently, a full examination of both performance and resilience is required in selecting a more dependent maintenance option. These maintenance solutions, together with the employment of the Monte Carlo Method, are contrasted against each other using a unique criteria that analyzes the degree of performance and robustness of each adaptation in maintenance decision-making.
It is well-known that preventive maintenance can be effective only for aging (e.g., with increasing failure rate) items. Counter-intuitively, we show that it is not the case in heterogeneous populations consisting of subpopulations of items with constant and even decreasing failure rates. However, the focus of the paper is on the case with increasing failure rates of items and a new multi-stage procedure with periodic replacements is proposed. Between consecutive periodic replacements, the failures are minimally repaired and the information on the numbers of minimal repairs in relevant intervals of time becomes a decision parameter in the corresponding optimization problems. For instance, for the 2-stage policy, an item is replaced at the optimally obtained time if the number of minimal repairs at this time is larger than the optimally obtained value. Otherwise, the replacement is postponed until the optimally obtained time. The proposed maintenance policy can be effective because the large number of minimal repairs indicates that the corresponding failure rate is relatively large and vice versa. Theoretical results and numerical illustrations justify the proposed approach. It will be shown that the application of the proposed maintenance policy can decrease the long-run average cost rate compared with the conventional replacement policy when the population is heterogeneous.
This paper presents a comparative study of feature extraction approaches for the condition monitoring of an electric motor. Conventional statistical analysis and image embedding approaches were employed to extract features from an established time series dataset representing healthy and seven types of faulty conditions. These conditions were tested under unloaded and loaded states at four different constant speed levels. Three machine learning techniques artificial neural networks (ANN), k-nearest neighbours (kNN), and support vector machines (SVM) were used to evaluate the performance of the feature extraction approaches. Overall, the results demonstrated that the conventional statistical analysis approach was on par with the image embedding approach, producing average accuracies of 97.38% and 96.55% for the dataset, respectively. The ANN model using the statistical analysis feature extraction approach generated the highest average accuracy, with 99.50%.
This study proposes strategies to minimize the cost of semiconductor manufacturing processes, using the total cost of ownership concept. The costs in semiconductor manufacturing are categorized into initial, operation, maintenance, downtime and production cost. Initial cost can be minimized through equipment diversification and life-cycle extension, thereby reducing capital expenditures. To reduce operation costs, a new equipment concept featuring built in valve manifold box was developed in collaboration with equipment manufacturers, significantly reducing installation costs. In addition, new methodologies were implemented to reduce energy consumption, including lowering the fan speed in the equipment front end module. Replacing existing robots with low vibration models from domestic manufacturer helped to reduce both maintenance and downtime costs by minimizing particle generation. Furthermore, equipment status monitoring and predictive maintenance should be employed wherever possible. To reduce production costs, recipe optimization activities such as minimum input steady output were conducted. Through these strategies, semiconductor manufacturing companies are able to efficiently manage costs and enhance competitiveness through reinvestment using saved capital and reduced product prices, in turn, securing long term sustainability.
The implementation of predictive maintenance (PM) in aviation presents unique challenges due to strict safety requirements, complex operational environments, and regulatory constraints. This paper develops a comprehensive decision-making framework for evaluating the feasibility of implementing PM for aircraft components, addressing the critical need for systematic integration of technical, economic, and regulatory considerations. Through expert surveys involving 78 aviation maintenance professionals and the application of multi-criteria decision analysis, this study identifies and validates 14 key criteria across four categories: technical and operational, economic and feasibility, regulatory and compliance, and organizational and human factors. The analytic hierarchy process is employed to establish criteria weights, with flight safety impact, reliability predictability, and data sufficiency emerging as primary drivers. The framework’s effectiveness is demonstrated through case studies comparing turbofan engines and avionics units, validating its ability to discriminate between components suitable for PM implementation. Results indicate that successful PM implementation requires not only technological readiness but also organizational alignment and regulatory compliance. This study contributes to aviation maintenance practice by providing a structured, evidence-based approach to PM implementation decisions, while establishing a foundation for future innovations in maintenance strategies. The framework’s practical applicability is enhanced through a detailed implementation roadmap and validation methods, ensuring its relevance for maintenance decision-makers while maintaining alignment with aviation safety standards.
Анаэробты ашыту-тазартылмаған тұнбаны өңдеуге арналған ағынды суларды тазарту станцияларында жақсы қалыптасқан құрал; оны анаэробты реакторларда биогаз жинау арқылы жаңартылатын энергия үшін де пайдалануға болады. Температура сияқты жұмыс параметрлерін әдетте қондырғы операторлары сараптамалық білімге сәйкес белгілейді. Операциялық басқару әлеуетін толық пайдалану үшін бұл зерттеуде біз алты жылдық өмірдегі уақыт қатарының деректері, сондай-ақ мемлекеттік мерекелер сияқты категориялық сипаттамалар негізінде жаңа уақытша синтез түрлендіргішін калибрледік. Дәстүрлі деректерге негізделген әдістерден айырмашылығы, модель дизайны бірнеше факторларды есепке алу арқылы нәтижелердің өзара алмастырылуын қамтамасыз етеді. Биогаз өндірісінің орташа көрсеткіштерін алдағы жеті күнге болжаумен қатар, біздің модель сандық мәндерді де береді, бұл оны күшті ауытқуларға азырақ бейім етеді. Нұсқаулық ретінде біз белгілі үш статистикалық әдісті қолдандық. Біздің болжау тәсіліміздің орташа абсолютті пайыздық қателігі 8% -дан аз.
Запропоновано вдосконалений метод діагностики несправностей у суднових електроенергетичних системах, в якому використовується нейронна мережа. Метод відрізняється безпосереднім використанням оригінальних зображень, коли не проводяться їх розкладання та вилучення функцій. Вдосконалений метод характеризується низкою переваг, у тому числі простоту застосування, високу швидкодію, автоматичне оновлення параметрів та стабільні, точні результати, за допомогою яких метод долає існуючі недоліки у традиційній діагностиці несправностей суднових електроенергетичних систем.Метою статті є розробкаметоду діагностики несправностейу суднових електроенергетичних системах, який базується на вдосконаленій згортковій нейронній мережі для забезпечення безпеки та стабільності роботи електроенергетичної системи судна. Для цього, по-перше, з використанням програмного додатку MATLAB побудована імітаційна модель суднової електроенергетичної системи для отримання нормального робочого стану та стану генератора та навантаження в енергосистемі. По-друге, промодельована крива реакції на несправності, і з цього отримано набір даних для навчання згорткової нейронної мережі. Третім кроком є розробка моделі діагностики несправностей на основі вдосконаленої згорткової нейронної мережі з використанням відкритого фреймворку глибокого навчання TensorFlow. На заключному етапі було проведено навчання згорткової нейронної мережі та отримано оптимальні результати діагностики електроенергетичної системи судна з метою оптимізації структурних параметрів та діагностики суднової електроенергетичної системи. Результати показали, що запропонована імітаційна модель на основі вдосконаленої згорткової нейронної мережі дозволяє забезпечити підтримку діагностики несправностей електроенергетичної системи судна, підвищити стабільність роботи та безпеку електроенергетичної системи судна, і, таким чином, забезпечити безпеку екіпажу. Подальшим напрямком дослідження є вдосконалення в плані часу навчання моделі. У майбутньому імітаційна модель може бути вдосконалена таким чином, щоб вона більше відповідала реальним судновим електроенергетичним системам. На основі оптимізованої моделі згорткової нейронної мережі точність діагностики може бути також відповідно покращена. Ключові слова: метод, діагностика несправностей, вдосконалена згорткова нейронна мережа, суднова електроенергетична система, набір даних, навчання, моделювання
This study focuses on the criticality of failure detection and condition-based maintenance (CBM) within the semiconductor industry, employing Fault Detection and Classification (FDC) systems and Machine Learning (ML) techniques for equipment log analysis to anticipate equipment conditions and timely maintenance. Initiatives emphasize the cultivation of data engineering experts, enhancing depth in data analytics and equipment monitoring. Moreover, the imperative to advance the field lies in the development of innovative sensor technologies, a task that necessitates close collaboration with equipment manufacturers. This strategic partnership is indispensable for augmenting the precision and breadth of data acquisition. It ultimately enables more sophisticated analytics, thereby facilitating the creation of advanced predictive failure models through enhanced data capture and analysis. This paper illustrates the semiconductor sector’s competitive adoption of diverse strategies and technologies for maintenance innovation, aiming to bolster industry productivity, equipment reliability, and sustainability. Such endeavors are pivotal for outlining the future trajectory of manufacturing and ensuring sustainable growth within the industry.
The significance of the Internet of Things (IoT) has grown considerably due to the expanding user base apprehensive computing and universal applications. It includes a wide range of devices, from simple objects to sophisticated sensor nodes, which can be used to deliver multirange services. Cloud computing and IoT offer life-changing potential for animal husbandry and agriculture by improving sustainability, efficiency, and productivity. The vast amount of data generated by IoT necessitates cloud computing, as standalone systems may struggle to manage it effectively. Integrating IoT with the cloud, known as the Cloud of Things (CoT), proves instrumental in achieving the optimal objectives reliant on IoT. In animal sciences, integrating the CoT may help in a transformative era for animal care, monitoring, and research. With the utilization of IoT devices and sensors, veterinarians and researchers can gather real-time data on various aspects of animal health, behavior, and environmental conditions. The cloud-based infrastructure of CoT enables the storage and analysis of vast datasets, allowing for comprehensive perceptions of animal well-being, early disease detection, and behavior patterns, which not only enhance the efficiency of veterinary care but also opens new vistas for research in understanding and addressing the complex health dynamics of diverse species. The use of CoT/IoT in animal sciences may help to provide complete data-driven solutions for meeting the rising global demand for food and other agricultural products by improving the growth, welfare, and health of animals. However, addressing challenges like infrastructure, data security, and costs will help to fully understand the benefits.
The significance of the internet of things (IoT) has grown considerably due to the expanding user base apprehensive computing and universal applications. It includes a wide range of devices, from simple objects to sophisticated sensor nodes, which can be used to deliver multirange services. Cloud computing and IoT offer life-changing potential for animal husbandry and agriculture by improving sustainability, efficiency, and productivity. The vast amount of data generated by IoT necessitates cloud computing, as standalone systems may struggle to manage it effectively. IoT with the cloud, known as the Cloud of Things (CoT), proves instrumental in achieving the optimal objectives reliant on IoT. In animal sciences, integrating the CoT may help in a transformative era for animal care, monitoring, and research. With the utilization of IoT devices and sensors, veterinarians and researchers can gather real-time data on various aspects of animal health, behavior, and environmental conditions. The cloud-based infrastructure of CoT enables the storage and analysis of vast datasets, allowing for comprehensive perceptions of animal well-being, early disease detection, and behavior patterns, which not only enhance the efficiency of veterinary care but also opens new vistas for research in understanding and addressing the complex health dynamics of diverse species. The use of CoT/IoT in animal sciences may help to provide complete data-driven solutions for meeting the rising global demand for food and other agricultural products by improving the growth, welfare, and health of animals. However, addressing challenges like infrastructure, data security, and costs will help to fully understand the benefits.
Aircraft engines are intricate, their malfunction can induce operational disruptions and endanger flight
safety. Consequently, airlines may encounter financial drawbacks. Aircraft maintenance assures the
implementation of actions and procedures essential to flight safety and efficiency.
This thesis aims to predict airplane engine failures for minimizing operational disruptions, enhancing
flight security and quality, and reducing excessive maintenance costs.
Within predictive maintenance solution is proposed using the Federated Fleet Learning and distributed
Machine Learning algorithms. It utilizes less data and yet ensures data privacy.
The Federated Fleet Learning accurately predicts engine failures and remaining useful life by using
FedSVM and FedLSTM algorithms for anomaly detection. This approach boosts the analysis and usage
of real-time engine data to prevent operational disruptions, potential life losses, and to reduce
maintenance costs.
At the core of these solutions, high-accuracy models, supported by low-latency, high-bandwidth, and
constant coverage from low-altitude satellites and ATG-5G redundant internet, are aimed to be
established.
Within the framework of Industry 5.0, the augmentation of collaboration among airlines, their sectoral
growth, and operational efficiency are anticipated. In this context, a holistic approach to predictive
maintenance management solutions is promising.
1. Introduction.- 2. Model-based Fault Diagnosis Techniques.- 3. System Identification for Fault Diagnosis.- 4. Residual Generation, Fault Diagnosis and Identification.- 5. Fault Diagnosis Application Studies.- 6. Concluding Remarks.- References.
In the last years new technologies and methodologies have been developed for increasing the reliability of fault diagnosis in mechanical equipment, mainly in rotating machinery. Global vibration indexes as RMS, Kurtosis, etc., are widespread known in industry and in addition, are recommended by international norms. Despite that, these parameters do not allow reaching reliable equipment condition diagnosis. They are attractive for their apparent simplicity of interpretation. This work presents a discussion about the diagnosis possibilities based on these traditional parameters. The database used comprises rolling bearings vibration signals taking into account different fault conditions, several shaft speeds and loading. The obtained results show that these global vibration parameters are limited regarding correct fault diagnosis, especially in initial faults condition. As an alternative method a new technique is proposed. This technique seeks to obtain a global parameter that makes better characterization of fault condition. This methodology, named Residual Energy, uses integration of the difference between the power spectrum density of the fault condition and the normal one. The results obtained with this technique are compared with the traditional RMS and Kurtosis.
Condition monitoring allows maintenance actions to be based on changes of a trend of machine or process parameters. The identification, monitoring and fusion of data from key parameters can provide greater confidence in decisions. Data fusion is a relatively new term to the condition monitoring community. In defence and other applications the field is mature and has seen extensive application. The advances in methods and frameworks for applications, in terms of condition monitoring, include: • the crystallisation of a cohesive scheme for problem definition; • structured solution selection; • comparisons with dissimilar application fields which have similar problem structures or solution methods; • the blending of quantitative and qualitative methods. This paper briefly reviews architectures or frameworks, and draws examples from manufacturing and plant applications. The chief application shown establishes the key vibration monitoring parameters for equipment within a paper mill and aids the maintenance optimisation process.
This paper explores a method to assess assets performance and predict the remaining useful life, which would lead to proactive maintenance processes to minimize downtime of machinery and production in various industries, thus increasing efficiency of operations and manufacturing. At first, a performance model is established by taking advantage of logistic regression analysis with maximum-likelihood technique. Two kinds of application situations, with or without enough historical data, are discussed in detail. Then, real-time performance is evaluated by inputting features of online data to the logistic model. Finally, the remaining life is estimated using an ARMA model based on machine performance history; degradation predictions are also upgraded dynamically. The results such as current machine running condition and the remaining useful life, are output to the maintenance decision module to determine a window of appropriate maintenance before the machine fails. An application of the method on an elevator door motion system is demonstrated.
Ferrographic analysis is required in order to detect wear particles in lubricating oil automatically, because the customary approach takes a great deal of time. We propose a new method to detect wear particles in lubricating oil in order to diagnose bearings, by means of local spatial frequency analysis using the wavelet transform. The Gabor function and cylindrical Gabor function are used as the mother functions of the wavelet transform in this paper. The Gabor function is effective in detecting particles which distribute along the lines of magnetic force on the ferrogram slide. The cylindrical Gabor function can detect circular particles. To discriminate the particles, we apply fuzzy system theory to the image transformed by two Gabor functions and show the effectiveness of this method.
The On-line Operator Aid SYStem (OASYS) has been developed to support the operator’s decision making process and to ensure the safety of a nuclear power plant by providing operators with proper guidelines in a timely manner, according to the plant operation mode. The OASYS consists of four systems such as a signal validation and management system (SVMS), a plant monitoring system (PMS), an alarm filtering and diagnostic system (AFDS), and a dynamic emergency procedure tracking system (DEPTS). The SVMS and the PMS help operators to maintain a plant in a condition to withstand the adverse events during a normal operation condition. The AFDS covers the abnormal events until it exceeds the limit range of reactor trip signals, while after a reactor trip, the DEPTS aids operators with proper guidelines so as to shut down safely.
The OASYS uses a rule-based expert system and fuzzy logic. The rule-based expert system is used to classify the predefined events and track the emergency operating procedures (EOPs) through data processing, and the fuzzy logic is used to generate the conceptual high-level alarms for the prognostic diagnosis and to evaluate the qualitative fuzzy criteria used in the EOPs. Evaluation results show that the OASYS is capable of diagnosing plant abnormal conditions and providing operators appropriate guidelines with fast response time and consistency.
The proposed system is implemented on a SUN-4/75 workstation using C language and Quintus prolog language. Currently, the OASYS is installed in the realtime full scope simulator for validation. After sufficient validation, the OASYS will be installed in the main control room for the unit one nuclear power plant at Young Gwang.
This paper is concerned with a research about fuzzy neural networks and application in fault diagnosis of rotary machine. To build robust fault diagnosis by neural networks, fuzzy neural networks are proposed. Fuzzy neural networks can memorize fault patterns and recognize fault patterns by association, and have good tolerance to unstable practical sample data. Through application in monitoring and fault diagnosis of pump sets of oil plants, it was verified that fuzzy neural networks are effective to handle practical sample data and make accurate fault diagnosis.
This paper reveals some experiences gained during the development of a knowledge-based expert system for on-line fault detection and diagnosis. The symptom tree model and fault-consequence digraph developed in our previous research showed that they can be applied effectively in real-time fault diagnosis of plants, particularly for large and complex ones.
The second edition of this highly successful text focuses on the major changes that have taken place in this field in recent times. Data Acquisition Techniques Using PCs, Second Edition, recognises that data acquisition is the core of most engineering and many life science systems in measurement and instrumentation. It will prove invaluable to scientists, engineers, students and technicians wishing to keep up with the latest technological developments. Teaches the reader how to set up a PC-based system that measures, analyzes, and controls experiments and processes through detailed design examples. Geared for beginning and advanced users, with many tutorials for less experienced readers, and detailed standards references for more experienced readers. Fully revised new edition discusses latest programming languages and includes a list of over 80 product manufacurers to save valuable time.
In this paper, we study the on-line parameter estimation problem for a partially observable system subject to deterioration and random failure. The state of the system evolves according to a continuous-time homogeneous Markov process with a finite state space. The state of the system is hidden except for the failure state. When the system is operating, only the information obtained by condition monitoring, which is related to the working state of the system, is available. The condition monitoring observations are assumed to be in continuous range, so that no discretization is required. A recursive maximum likelihood (RML) algorithm is proposed for the on-line parameter estimation of the model. The new RML algorithm proposed in the paper is superior to other RML algorithms in the literature in that no projection is needed and no calculation of the gradient on the surface of the constraint manifolds is required. A numerical example is provided to illustrate the algorithm.
The analysis of vibration spectra is an extensively used tool in machinery condition-based maintenance looking for early failure prevention and diagnosis. The cluster analysis is a statistical technique widely used in a variety of scientific fields and rarely employed in the investigation of machine vibrations. This paper tries to examine the potential of the cluster analysis in the detection of machine failure and compares its advantages and disadvantages in the discrimination of the data obtained from a series of vibration spectra. Results of the application of this technique in failure detection of two common components in rotating machinery (rolling bearings and spur gears) are presented. The vibration spectra from these elements, having in each case a known failure, are obtained from the test rig hold in the Mechanics Department of UNED. From a series of observations (vibration amplitude at different frequencies), they are classified into groups as homogeneous as possible, according to the different measured variables. The results obtained have the sufficient precision as to show that cluster analysis is an efficient criterion in the discrimination of the state of rotating machinery.
During the run-up process of rotating machinery, there is large amount information in the rotor system, which does not appear in the steady wheeling stage. Hence the run-up process faults diagnosis is an active subject of research nowadays. This paper shows how 2-dimension hidden Markov model can be used to build a fault diagnosis system based on time-frequency analysis to the process signal. The topology of this model and its parameters are introduced. Meanwhile how to select the features by time-frequency analysis is discussed here. Finally, the new model was tested with experimental data collected from Benty-Nevada rotor experimental system (Model 24755) and the new method was found to outperform previously proposed classifiers based on the average spectrum of the machinery fault signal with much more correct classifications.
This chapter introduces signals and the mathematical tools needed to work with them, and combines discussions of analog signals, discrete signals, digital signals and the methods to transition from one of these realms to another. All that it requires of the reader is a familiarity with calculus. There are a wide variety of examples. They illustrate basic signal concepts, filtering methods, and some easily understood techniques for signal interpretation. The first section introduces the terminology of signal processing, the conventional architecture of signal processing systems, and the notions of analog, discrete, and digital signals. It describes signals in terms of mathematical models – functions of a single real or integral variable. Next, we cover the two basic signal families: analog and discrete, respectively. Later, we discuss sampling and interpolation. Next we cover periodicity, and foremost among these signals is the class of sinusoids. The chapter concludes with a discussion of the mathematics that arises in the detailed study of signals. A summary, a list of references, and a problem set complete the chapter.
The focus of the paper is the optimization of condition-based maintenance decisions within the contexts of physical asset management. In particular, the analysis of a preventive replacement policy of the control-limit type for a deteriorating system subject to inspections at discrete points of time is presented. Cox's PHM with a Weibull baseline hazard function and time dependent stochastic covariates is used to describe the failure rate of the system. The methods of estimating model parameters and the calculation of the optimal policy are given. The structure of the decision-making software EXAKT is presented. Experience with collecting, processing and using real oil and vibration data is reported.
Condition-based maintenance (CBM) is an effective preventive maintenance policy since the policy enhances system reliability and decreases the unwanted breakdown of the target maintained system and the maintenance cost. We propose a simultaneous optimisation method of the inspection time vector, which is a time series of inspection, and a warning level of the target system under the constraint of preventive replacement probability. The developed CBM model considers the residual life loss, which is related to the average remaining time from the preventive replacement conduction time until the expected breakdown time of a maintained system, as well as the incurred replacement and inspection costs, whereby the long-run average incurred cost per unit time is derived as an objective function for minimisation. An algorithm to solve the optimal inspection time vector and optimal warning level is established. Numerical examples to which the constructed CBM model and the solution algorithm have been applied are shown with a variety of parameters in the CBM model, together with the comparison of the results obtained in breakdown maintenance and optimal time-based maintenance.
The following describes a spectroscopic approach for achieving condition-base maintenance (CBM) through the monitoring of lubricant degradation in machinery. The approach uses infrared and fluorescence spectroscopy to monitor lubricant condition as a function of changing spectral variance. The use of two different spectroscopies has been pursued because varying CBM requirements within the industrial and military communities can be met with the complimentary advantages of each approach. Because the spectroscopic methods are inherently multivariate, the authors have also chosen to pursue a multivariate analysis of the data. The authors results show that multivariate infrared spectroscopy offers certain advantages over multivariate fluorescence spectroscopy and vice versa. It is shown that the two approaches fulfill different CBM requirements. This is an important and useful result because the CBM requirements for monitoring a given lubricant can vary greatly from one field application to the next. The authors have monitored a synthetic aircraft lubricant, Hatco Corporation (MIL-L-23699D), that is found in the rotary gearboxes of several military helicopters. The authors show that when used in conjunction with multivariate analysis techniques, such as PCA, that both infrared and fluorescence spectroscopy can provide an ideal means of monitoring the condition of a lubricant as it degrades. The authors confirm that infrared absorption can provide a means of monitoring the breakdown of the additive package, the decomposition of an ester functionality, and the production of a degradation breakdown product as a function of degradation time. The authors also show that fluorescence emission can provide a rapid, low-cost, easy-to-implement means of monitoring the 'integrated' condition of a lubricant as a function of degradation time.
Vibratory effects are sensed quite easily by most people, they are tiring and unpleasant, at the extreme they can be frightening. It is not surprising that vibration analysis occupies a prominent place in machine diagnostics.
Prognostics, which refers to the inference of an expected time-to-failure for a mechanical system, is made difficult by the need to track and predict the trajectories of real-valued system parameters over essentially unbounded domains, and by the need to prescribe a subset of these domains in which an alarm should be raised. In this paper we propose a novel technique whereby these problems are avoided: instead of physical system or sensor parameters, sensor-level test-failure probability vectors (bounded within the unit hypercube) are tracked; and via a close relationship with the TEAMS suite of modeling tools, the terminal states for all such vectors can be enumerated. To perform the tracking, a Kalman filter with associated interacting multiple model switching between failure regimes is proposed, and simulation results indicate that performance is promising.
Foreword. Preface. 1. Introduction/Background 2. The Wavelet Transform. 3. Practical Resolution, Gain, and Processing Structures. 4. Wavelet Theory Extentions and Ambiguity Functions. 5. Linear Systems Modelling with Wavelet Theory. 6. Wideband Scattering and Environmental Imaging. Related Research. References. Subject Index.
Vibration based machine fault diagnosis is widely adopted in machine condition monitoring. Since a machine is usually composed of many mechanical components, during the machine running, each component will generate its vibration and transmit to other components thru the shaft or linkages. Hence, the vibration signal collected from a sensor is the aggregation of all generated vibrations. To enhance the accuracy in vibration based machine fault diagnosis, the vibration generated by each component must be isolated and identified. In this paper, the performance of blind-source-separation (BSS) in separating various mixed sources is discussed. The BSS based method of second order statistics (SOS) has been applied to separate the aggregated vibration signals generated from a number of mechanical components. To verify the effectiveness of the BSS based SOS, a number of experiments were conducted using both simulated data and vibration generated form the industrial machines. The results show that the BSS possesses the ability to separate both artificially and naturally mixed signals. Such ability is definitely welcome in the fields of condition monitoring and maintenance. Moreover, the paper also discusses the advantages and disadvantages of the algorithm in the applications of machine fault diagnosis and future improvements.
This paper provides an overview of the current available technologies for automated machinery condition evaluation and fault diagnosis within an overall plant asset management system. The paper presents a basic overview of an integrated plant asset management system, and focuses on the available technologies for automated diagnostics including statistical analysis of data, parametric model diagnosis, non-parametric model diagnosis (artificial neural networks), and rule-based diagnostics including expert systems and fuzzy logic. The current state-of-the-art and the expected realistic future developments are discussed.
Statistical pattern recognition is a term used to cover all stages of an investigation from problem formulation and data collection through to discrimination and classification, assessment of results and interpretation. This chapter introduces some of the basic concepts in classification and describes the key issues. It presents two complementary approaches to discrimination, namely a decision theory approach based on calculation of probability density functions and the use of Bayes theorem, and a discriminant function approach. Many different forms of discriminant function have been considered in the literature, varying in complexity from the linear discriminant function to multiparameter nonlinear functions such as the multilayer perceptron. Regression is an important part of statistical pattern recognition. Regression analysis is concerned with predicting the mean value of the response variable given measurements on the predictor variables and assumes a model of the form. Bayes' theorem; regression analysis; statistical process control
We examine a replacement problem for a system subject to stochastic deterioration. Upon failure the system must be replaced by a new one and a failure cost is incurred. If the system is replaced before failure a smaller cost is incurred. The failure of the system depends both on its age and also on values of a diagnostic stochastic process observable at discrete points of time. Cox’s proportional hazards model is used to describe the failure rate of the system. We consider the problem of specifying a replacement rule which minimizes the long-run expected average cost per unit time. The form of the optimal replacement policy is found and an algorithm based on a recursive computational procedure is presented which can be used to obtain the optimal policy and the optimal expected average cost.
A closer look has been taken into repair and maintenance actions (RMAs) that affect systems in an industrial environment. It has been discussed that the classical definition of 'repair' is complex. Virtually every RMA affects the system in some way. To model repairable systems, a concept is needed that reflects the state of the system incorporating the scale of RMAs. A few concepts and their possible incorporations are proposed. The repair and maintenance indicator type 'a' (RMIa) is introduced as the weighted accumulated operating time of all or the most important parts of the system. The indicator type 'b' (RMIb) is introduced as a state of a system depending on its age and RMA history. The indicator type 'c' is introduced to reflect the degree of repair of an RMA, These indicators can be useful for the modelling and comparison of repairable systems. Several methods to incorporate repair and maintenance indicators into intensity process models for repairable system reliability are discussed. The indicators may be used as covariates in a proportional intensity model (PIM), or as reduction factors in a virtual age process model.
A new approach to the development of a more robust diagnosis and
prognostic capability is described. This approach is based fusion of
sensor-based and model-based information. These micromechanical models
must account for initial flow size distribution and other
microstructural parameters describing initial component condition. A
specific application of this approach is addressed, the diagnosis of
mechanical failure in meshing gears. Four specific issues are considered
are these issues are presented.
Vibration-based machine condition monitoring incorporates a number of machinery fault detection and diagnostic techniques. Many machinery fault diagnostic techniques use automatic signal classification in order to increase accuracy and reduce errors caused by subjective human judgment. In this paper, fuzzy logic techniques have been applied to classify frequency spectra representing various rolling element bearing faults. The frequency spectra representing a number of different fault conditions have been processed using a variety of fuzzy set shapes. The application of basic fuzzy logic techniques has allowed fuzzy numbers to be generated which represent the similarity between frequency spectra. Correct classification of different bearing fault spectra was observed when the correct combination of fuzzy set shapes and range of membership domains were used. The problem of membership overlapping found in previous studies, where classifying individual spectrum with respect to spectra that represent true fault classes was not conclusive, has been overcome. Further work is described which will extend this technique to other classes of machinery using generic software.
A prototype condition monitoring and diagnostic system has been developed for compression refrigeration plants, which can be used under variable operational conditions. Based on a combination of causal analysis, expert knowledge and simulated failure modes, a failure mode symptom matrix has been created. Healthy system behaviour is predicted based on a regression analysis model. Using multi-valued (or ‘fuzzy’) logic, real-time recognition of failure modes, at an early stage, proved to be possible. Future developments for improvement of diagnostic systems in compression refrigeration plants are discussed.RésuméOn a mis au point un système prototype de suivi et de diagnostic pour les installations de refroidissement à compression, qui peut être utilisé dans plusieurs conditions de fonctionnement. En se fondant sur la combinaison d'une analyse causale, sur la connaissance des experts et sur les modes de simulation des pannes, on a créé une matrice dite de ‘symptôme’ en matière de panne. On prv́oit le comportement du système en bon état en se basant sur un modèle d'analyse par régression. En utilisant la logique floue, la détection précoce des pannes en temps réel s'est avérée possible. On examine les réalisations futures qui permettront d'améliorer ces systèmes de diagnostic dans les installations de refroidissement à compression.
This paper is concerned with diagnostic methods for gears and bearings, the goals of which are to detect incipient structural and metallurgical faults, characterize their nature and severity, and isolate them to particular components. Such information is invalu- able for prognostic purposes. The methodology presented herein focuses on the analysis of vibration signals induced by gears and bearings and, specifically, on a means of extracting from such vibration patterns amplitude and phase modulation signals. Such modulation terms, we conjecture, are simple indicators of the severity of a particular type of localized component defect. We show that such amplitude and phase modulation information can be extracted using a neural network computational methodology that relies on nothing more than knowledge of the bearing geometry and the frequency tones at which a given type of defect will manifest itself. We present numerical simulation examples and show that the technique requires extremely few a priori assumptions. Introduction: The topics addressed herein pertain to the general problem of machinery prognostics, i.e., estimating the remaining useful life of machinery components based on knowledge of their present condition and assumptions about future usage. The ability to diagnose particular machine components and understand the implications of diagnostic information vis-` a-vis future usage of the machine is of immense practical importance in industrial, commercial, and military applications. Component failures contribute to the majority of machine operation safety incidents and are responsible for a substantial fraction of the on-going maintenance costs accruing to machinery usage. This underscores the need for condition-based maintenance (CBM), wherein knowledge regarding the condition of machinery, rather than fixed time intervals, is used to schedule maintenance, thus averting unnecessary inspections. The quality of the diagnostic information acquired (i.e., fault detection, type and sever- ity characterization, and component isolation) plays a paramount role in determining the ecacy of prognostication. Use of inaccurate diagnostic information in, say, a prognostic decisional algorithm driving a CBM policy for a fleet of helicopters may result in ill-fated missions. Prompt and accurate detection of structural and metallurgical faults in machinery components (e.g., gears and bearings) is an important category of such diagnostic informa- tion that is our focus herein. Almost all physical techniques for detecting the onset of such defects, e.g., fatigue cracks or surface spalling, involve the measurement of abnormal vibration signals transmitted through structural media due to the presence of the defect. Vibration sensors (e.g., accelerometers) may be used to measure these signals. Sensitive spectral analysis and astute signal processing of such sensor data is critical, chiefly because in practical machinery operational scenarios, there are an enormous number of vi- brations that interfere with one another and result in an observed signal that appears bewildering and uninformative. The main problem is therefore one of discovering the nee- dle (i.e., spectral content that provides useful and pertinent information about an incipient fault) in the haystack (i.e., the raw vibration signal). A number of sophisticated techniques
We present a generic methodology for machinery fault diagnosis through pattern recog- nition techniques. The proposed method has the advantage of dealing with complicated signatures, such as those present in the vibration signals of rolling element bearings with and without defects. The signature varies with the location and severity of bearing defects, load and speed of the shaft, and different bearing housing structures. More specifically, the proposed technique contains effective feature extraction, good learning ability, reli- able feature fusion, and a simple classification algorithm. Examples with experimental testing data were used to illustrate the idea and effectiveness of the proposed method. @DOI: 10.1115/1.1687391#
A physics-based approach for diagnostics and prognostics using integrated observers and life models is presented. Observers are filters based on physical models of machine- fault combinations and use measured machine signatures to identify and characterize the state of a machine. Observers are adaptively deployed as a machine wears and can be coupled with one another to handle interacting conditions and faults. The scheme is detailed using the fault of a cracked rotor shaft that interacts with gravity and imbalance. Observers for shaft cracking and imbalance are presented. The observers provide machine condition and fault strengths to life models used to determine remaining machine life. A life model based on the Forman crack growth law of linear elastic fracture mechanics is developed to determine the number of machine cycles remaining until catastrophic failure.
This paper presents a novel methodology for the diagnosis and prognosis of crucial gear faults, such as gear tooth fatigue cracking. Currently, an effective detection of tooth cracking can be achieved by using the autoregressive (AR) modeling approach, where the gear vibration signal is modeled by an AR model and gear tooth cracking is detected by identifying the sudden changes in the model's error signal. The model parameters can be estimated under the criteria of minimum power or maximum kurtosis of model errors. However, these model parameters possess no physical meaning about the monitored gear system. It is proposed that the AR model be replaced by a gear dynamics model (GDM) that contains physically meaningful parameters, such as mass, damping and stiffness. By identifying and tracking the changes in the parameters, it is possible to make diagnosis and prognosis of gear faults. For example, a reduction in mesh stiffness may indicate cracking of a gear tooth. Towards physical model-based prognosis, an adaptive (or optimization) strategy has been developed for approximating a gear signal using a simplified gear signal model. Preliminary results show that this strategy provides a feasible adaptive process for updating model parameters based on measured gear signal.
Complex dynamical systems such as aircraft, manufacturing systems, chillers, motor vehicles, submarines, etc. exhibit continuous and event-driven dynamics. These systems undergo several discrete operating modes from startup to shutdown. For example, a certain shipboard system may be operating at half load or full load or may be at start-up or shutdown. Of particular interest are extreme or "shock" operating conditions, which tend to severely impact fault diagnosis or the progression of a fault leading to a failure. Fault conditions are strongly dependent on the operating mode. Therefore, it is essential that in any diagnostic/prognostic architecture, the operating mode be identified as accurately as possible so that such functions as feature extraction, diagnostics, prognostics, etc. can be correlated with the predominant operating conditions. This paper introduces a mode identification methodology that incorporates both time- and event-driven information about the process. A fuzzy Petri net is used to represent the possible successive mode transitions and to detect events from processed sensor signals signifying a mode change. The operating mode is initialized and verified by analysis of the time-driven dynamics through a fuzzy logic classifier. An evidence combiner module is used to combine the results from both the fuzzy Petri net and the fuzzy logic classifier to determine the mode. Unlike most event-driven mode identifiers, this architecture will provide automatic mode initialization through the fuzzy logic classifier and robustness through the combining of evidence of the two algorithms. The mode identification methodology is applied to an AC Plant typically found as a component of a shipboard system.
A simple methodology for identification and quantification of nonlinear effects such as Coulomb friction and backlash is desired for use in condition based maintenance programs for both structural and machine based applications. Typically, structural applications are passive and undergo small vibratory motion when an external excitation is presented to the system. A spring-mass system was used as the structural example. Machine applications are typically active and motion is excited by internal actuation of large motion within the system. An industrial SCARA robot was used as the machine based example. The Hilbert transform was tested for detection and quantification of Coulomb friction in both systems.