Figure - available from: Shock and Vibration
This content is subject to copyright. Terms and conditions apply.
(a) External characteristics of cavitation and normal working conditions. (b) External characteristics of damage impeller and normal working conditions. (c) External characteristics of damage machine seal and normal working conditions.
Source publication
To effectively predict the faults of centrifugal pumps, the idea of machine learning k-nearest neighbor algorithm (KNN) was introduced into the traditional Mahalanobis distance fault discrimination, and an improved centrifugal pump fault prediction model of KNN based on the Mahalanobis distance is proposed. In this method, the Mahalanobis distance...
Similar publications
The numerical value of k in a k-fold cross-validation training technique of machine learning predictive models is an essential element that impacts the model's performance. A right choice of k results in better accuracy, while a poorly chosen value for k might affect the model's performance. In literature, the most commonly used values of k are fiv...
Citations
... The following assumptions are used when constructing PU models describing static (steady) modes: the transported liquid is considered incompressible; the temperature of the liquid and, therefore, the density are unchanged; the velocity head is neglected due to its small value compared to the potential head; and pressure losses at local supports are neglected. A description of the characteristics of the pump unit in the presence of malfunctions and non-stationary phenomena is given in [27,28]. ...
The scientific novelty of the proposed article lies in the development of the theory of analysis of the operation modes of group pump units operating on a long pipeline network with back pressure. This was achieved by creating electric equivalent circuits of group pump units based on the method of electrohydraulic analogy. Such equivalent circuits take into account pumps’ connection circuits, the configuration of the pipeline network, and the method of regulating technological parameters. A method for determining the characteristics of pump units with series and parallel connection is proposed. The dependences of the power consumed by the pump units on the change in the frequency of rotation of the adjustable pump are obtained for various parameters of the hydraulic network. This makes it possible to determine the limits of energy-efficient regulation of pump discharge. Analytical expressions for determining the lower limit of the pump rotation frequency for various circuits of turbo mechanism connection and various numbers of pumps operating simultaneously on a pipeline network with back pressure are proposed. The necessary range of adjustment of the pump rotation frequency with different circuits for turbo mechanism connection and different numbers of hydraulic machines operating at the same time is determined. The analysis of the obtained modes of pump units is performed and the possibility of expanding the controlled properties of the group electric drive systems of turbomachines when changing the direction of the rotation frequency and reversing the liquid in the event of an emergency situation is shown.
... According to Tiwari [1], due to the pressure below the vapor pressure suction, cavitation is reported to be the typical fault that most frequently develops in pumps, as described in several studies [1,[36][37][38][39][40][41][42][43]. Apart from cavitation, another recurring problem in pumps is damage to the casing and impeller, which can be caused due to the pulsation of pressure that is associated with internal recirculation. ...
A system’s operational life cycle now includes an integrated health management and diagnostic strategy due to improvements in the current technology. It is evident that the life cycle may be used to identify abnormalities, analyze failures, and forecast future conditions based on current data. Data models can be trained using machine learning and statistical ideas, employing condition data and on-site feedback. Once data models are trained, the data-processing logic can be integrated into onboard controllers, allowing for real-time health evaluation and analysis. Interestingly, the oil and gas industries may encounter numerous obstacles and hurdles as a result of the integration, highlighting the need for creative solutions to the perplexing problem. The potential benefits in terms of challenges involving feature extraction and data classification, machine learning has received significant research attention recently. The application and utility in pump system health management should be investigated to explore the extend it can be used to increase overall system resilience or identify potential financial advantages for maintenance, repair, and overhaul activities. This is seen as an evolving research area, with a variety of application domains. This article present a critical analysis of machine learning’s most current advances in the field of artificial intelligence-based system health management, specifically in terms of pump applications in the oil and gas industries. To further understand its potential, various algorithms and related theories are examined. Based on the examined studies, machine learning shows potential for prognostics and defect diagnosis. There are, few drawbacks that is seen to be preventing its widespread adoption which prompt for further improvement. The article discussed possible solutions to the identified drawbacks and future opportunities presented. This study further elaborates on the commonly available commercial machine learning (ML) tools used for pump fault prognostics and diagnostics with an emphasis on the type of data utilized. Findings from the literature review shows that the neural network (NN) is the most prevalent algorithm employed in studies, followed by the Bayesian network (BN), support vector machine (SVM), and hybrid models. While the need for selecting appropriate training algorithms is seen to be significant. Interestingly, no specific method or algorithm exists for a given problem instead the solution relies on the type of data and the algorithm’s or method’s aptitude for resolving the provided errors. Among the various research studies on pump fault diagnosis and prognosis, the most frequently discussed problem is a bearing fault, with a percentage of 46%, followed by cavitation. The studies rank seal damage as the third most prevalent flaw. Leakage and obstruction are the least studied defects in research. The main data types used in machine learning techniques for diagnosing pump faults are vibration and flow, which might not be sufficient to identify the condition of pumps and their characteristics. The various datasets have been derived from expert opinion, real-world observations, laboratory tests, and computer simulations. Field data have frequently been used to create experimental datasets and simulated data. In comparison to the algorithmic approach, the data approach has not received significant research attention.
... Many data-driven models have been developed, such as SVMs [3], ANN [4], PCA [5], and other artificial intelligence models. Liu [7]. Matheus et al. that are more representative of the minority fault data in the limited data, to reduce the burden on the model and increase the recognition effect of the model; (2) how to deal with the problem that the information contained in a minority of fault samples easily gets submerged in the majority of normal information, which easily leads to a high recognition error rate of the classifier for fault samples with a small amount of data. ...
The ratio between normal data and fault data generated by electric submersible pumps (ESPs) in production is prone to imbalance, and the information carried by the fault data generally as a minority sample is easily overwritten by the normal data as a majority sample, which seriously interferes with the fault identification effect. For the problem that data imbalance under different working conditions of ESPs causes the failure data to not be effectively identified, a fault identification method of ESPs based on unsupervised feature extraction integrated with migration learning was proposed. Firstly, new features were extracted from the data using multiple unsupervised methods to enhance the representational power of the data. Secondly, multiple samples of the source domain were obtained by multiple random sampling of the training set to fully train minority samples. Thirdly, the variation between the source domain and target domain was reduced by combining weighted balanced distribution adaptation (W-BDA). Finally, several basic learners were constructed and combined to integrate a stronger classifier to accomplish the ESP fault identification tasks. Compared with other fault identification methods, our method not only effectively enhances the performance of fault data features and improves the identification of a few fault data, but also copes with fault identification under different working conditions.
... Liu et al. proposed a chicken swarm optimization SVM model for fault diagnosis [6]. Chen et al. proposed an improved KNN fault detection method based on the Marxian distance for pump faults [7]. Matheus et al. proposed a randomforest-based approach for ESP data analysis for achieving multifault classification [8]. ...
The purpose of this study was to investigate how to detect abnormalities in electric submersible pumps (ESPs) in advance and how to classify the faults by monitoring the production data before pumps break down. Additionally, a new method based on the denoising autoencoder (DAE) and support vector machine (SVM) is proposed. Firstly, the ESP production data were processed and fault-related features were screened using the random forest (RF) algorithm. Secondly, input data were randomly damaged by the addition of noise, a DAE network structure was constructed, and the optimal learning rate, noise reduction coefficient, and other parameters were set. Thirdly, the real-time status of the production data of ESP was monitored with reconstruction errors to detect the point when an abnormality occurs signifying a pending fault. Finally, SVM was used to distinguish the type of fault. Compared with existing fault diagnosis methods, our method not only has the advantages of easy extraction of effective data features, higher accuracy, and strong generalization ability but can also detect an abnormal state indicating a coming fault and identify its type, hence enabling the preparation of an appropriate advance solution.
... (3) is paper combines the introduction of momentum factor and gray wolf algorithm optimization parameters, which avoids the randomness of the initial parameter selection of wavelet neural networks and effectively improves the accuracy and stability of network fault diagnosis results. (4) e IGWO-WNN fault diagnosis model proposed in this paper has superior generalization, which can not only achieve good results in network faults but also be suitable for diagnosing mechanical faults based on thermal imaging [22,23], vibration signal [24,25], and acoustic signals [26,27]. ...
To address the problem of diagnostic accuracy and stability degradation caused by random selection of the initial parameters for the wavelet neural network (WNN) fault diagnosis model, this paper proposes a network troubleshooting model based on the improved gray wolf algorithm (IGWO) and the wavelet neural network. First, the convergence factor and policy for the weight update are redesigned in the IGWO algorithm. This study uses a nonlinear convergence factor to balance the global and local search capabilities of the algorithm and dynamically adjusts the weights according to the adaptability of the head wolf α to strengthen its leadership position. Thereafter, the initial weights and biases of the WNN are optimized using the IGWO algorithm. During the backpropagation of the WNN error, momentum factors are introduced to prevent the model from falling into local optimization. Experimental results show that the IGWO algorithm is far better than GWO in terms of convergence speed and convergence accuracy. Furthermore, the average diagnostic accuracy of the IGWO-WNN model on the KDD-CUP99 dataset reaches 99.22%, which is 1.15% higher than that of the WNN model, and the stability of the diagnostic results is significantly improved.
... During the past three decades, diagnostic techniques for the detection of gearbox defects have been intensively researched, including those reported by Dalpiaz et al. [10], Ma et al. [11], Mohammed et al. [12], Saxena et al. [13], Wu et al. [14], and Li [15]. Rezaei et al. [16] detected multicrack locations and lengths from transmission-error ratios. ...
This study experimentally investigates vibration-based approaches for fault diagnosis of automotive gearboxes. The primary objective is to identify methods that can detect gear-tooth cracks, a common fault in gearboxes. Vibrational signals were supervised on a gearbox test rig under different operating conditions of gears with three symmetrical crack depths (1, 2, and 3 mm). The severity of the gear-tooth cracks was predicted from the vibrational signal dataset using an artificial feedforward multilayer neural network with backpropagation (NNBP). The vibration amplitudes were the greatest when the crack size in the high-speed shaft was 3 mm, and the root mean square of its vibration speed was below 3.5 mm/s. The vibration amplitudes of the gearbox increased with increasing depth of the tooth cracks under different operating conditions. The NNBP predicted the states of gear-tooth cracks with an average recognition rate of 80.41% under different conditions. In some cases, the fault degree was difficult to estimate via time-domain analysis as the vibration level increases were small and not easily noticed. Results also showed that when using the same statistical features, the time-domain analysis can better detect crack degree compared to the neural network technique.
The oil and gas sectors employ pumps extensively. The dependability and good operation of the pumps contribute significantly to the manufacturing line’s efficiency. Nevertheless, breakdowns can occur for a variety of causes, and a single failure can result in severe production delays and economic losses. Therefore, it is of the highest importance to anticipate future errors and swiftly address their root causes. Traditional pump maintenance and fault detection methods are ineffective in detecting possible defects. However, with the rapid rise of industry 4.0, the growing use of sensors, and the use of artificial intelligence techniques, smart plants may automate their operations to greatly enhance their efficiency and quality of output. Given that, Prognostics and Health Management (PHM) is essential for optimal machine performance. Meanwhile, Predictive Maintenance (PdM) is an emerging topic within maintenance methodologies with the objective of predicting failure prior to its occurrence in order to schedule maintenance only when it is necessary. These solutions have benefited pump maintenance decision-making by addressing complexity issues, reducing downtime, enhancing overall reliability, and reducing pump operating costs. This study examines the use of the classification learner to predict pump failure. The vibration sensor data for the pump were employed for prediction in the MATLAB software using the classification learner machine learning method. According to the dataset, the variable of interest is the machine status, which is categorized as normal, broken, and recovering. On the basis of the confusion matrix and the evaluation of the true positive rate (TPR), the false negative rate (FNR), the positive predicted values (PPV), and the false discovery value, the actual result was anticipated (FDR). The experimental result reveals that the accuracy of the training model was 91.94%, whereas the accuracy of the testing model was 74.4%.
Conventional signal processing methods such as Principle Component Analysis (PCA) focus on the decomposition of signals in the 2D time–frequency domain. Parallel factor analysis (PARAFAC) is a novel method used to decompose multi-dimensional arrays, which focuses on analyzing the relevant feature information by deleting the duplicated information among the multiple measurement points. In the paper, a novel hybrid intelligent algorithm for the fault diagnosis of a mechanical system was proposed to analyze the multiple vibration signals of the centrifugal pump system and multi-dimensional complex signals created by pressure and flow information. The continuous wavelet transform was applied to analyze the high-dimensional multi-channel signals to construct the 3D tensor, which makes use of the advantages of the parallel factor decomposition to extract feature information of the complex system. The method was validated by diagnosing the nonstationary failure modes under the faulty conditions with impeller blade damage, impeller perforation damage and impeller edge damage. The correspondence between different fault characteristics of a centrifugal pump in a time and frequency information matrix was established. The characteristic frequency ranges of the fault modes are effectively presented. The optimization method for a PARAFAC-BP neural network is proposed using a genetic algorithm (GA) to significantly improve the accuracy of the centrifugal pump fault diagnosis.
