Incipient Fault Detection in Stator Windings of an Induction Motor Using Stockwell Transform and SVM
15 Jun 2020-IEEE Transactions on Instrumentation and Measurement (IEEE)-Vol. 69, Iss: 12, pp 9496-9504
TL;DR: Stockwell transform (ST) is used to analyze the stator current signals for diagnosis of various motor conditions such as healthy, stator winding interturn shorts, and phase to ground faults.
Abstract: In this article, Stockwell transform (ST) is used to analyze the stator current signals for diagnosis of various motor conditions such as healthy, stator winding interturn shorts, and phase to ground faults. ST decomposes the current signals into complex ST matrix whose magnitude has been utilized for the fault detection. The nature of the fault, that is, ground or interturn is identified using the zero sequence currents followed by postfault detection. Two separate frequency bands are defined to extract the features which are fed to two different support vector machine (SVM) models for faulty phase detection for both types of faults. Under both cases, a heuristic feature selection approach is utilized to find the optimal features for classification purposes. Average classification accuracy of 96% has been achieved for both types of faults.
Citations
More filters
TL;DR: In this paper, the stator interturn short-circuit (ITSC) faults of an inverter-fed induction motor can be detected with good confidence by monitoring the online common-mode (CM) impedance of an IM through an inductive coupling technique at a specific frequency of interest (FOI).
Abstract: By monitoring the online common-mode (CM) impedance of an inverter-fed induction motor (IM) through an inductive coupling technique at a specific frequency of interest (FOI), the stator interturn short-circuit (ITSC) faults of the IM can be detected with good confidence. The inductive coupling technique is adopted because it monitors the CM impedance of the IM without a physical electrical connection, which eliminates electrical safety hazards and facilitates ease of implementation. Using a 1/2-hp squirrel-cage IM as a test case, it has been demonstrated that the proposed method is sensitive to the stator ITSC faults but invariant to motor load and speed variations, as well as bearing and rotor faults, making it highly reliable and robust for stator ITSC fault detection.
18 citations
TL;DR: In this article , the authors proposed an interturn fault diagnostic technique for synchronous reluctance machines based on the Luenberger state observer and current's second-order harmonic, which can evaluate the severity of the fault in early stages and under various operating conditions.
Abstract: Interturn short-circuit faults are one of the most (if not the most) harmful electrical machine failures, that if not detected and mitigated at a very incipient stage of development may involve serious consequences, both in terms of repair costs and safety. This article proposes a novel interturn fault diagnostic technique for synchronous reluctance machines based on the Luenberger state observer and current's second-order harmonic. The superiority of the proposed approach over the conventional model-based techniques is the ability to evaluate the severity of the fault as well as the efficiency in detecting faults in early stages and under various operating conditions. The effectiveness of the proposed method is demonstrated and validated through several experimental tests.
14 citations
TL;DR: Wang et al. as mentioned in this paper proposed a transformer fault diagnosis method based on Multi-class AdaBoost Algorithms in response to low fault diagnosis accuracy, where the AdaBoost algorithm is combined with Support Vector Machines (SVM), and the SVM is enhanced through the Adaboost algorithm, and the transformer fault data is deeply explored.
Abstract: Traditional shallow machine learning algorithms cannot effectively explore the relationship between the fault data of oil-immersed transformers, resulting in low fault diagnosis accuracy. This paper proposes a transformer fault diagnosis method based on Multi-class AdaBoost Algorithms in response to this problem. First, the AdaBoost algorithm is combined with Support Vector Machines (SVM), The SVM is enhanced through the AdaBoost algorithm, and the transformer fault data is deeply explored. Then the dynamic weight is introduced into the Particle Swarm Optimization (PSO); through the real-time update of the particle inertia weight, the search accuracy and optimization speed of the particle swarm optimization algorithm is improved, and the improved particle swarm optimization algorithm (IPSO) is used to optimize the parameters of the SVM. Finally, by analyzing the relationship between the dissolved gas in the transformer oil and the fault type, the uncoded ratio method forms a new gas group cooperation. The improved ratio method is constructed as the input feature vector. Simulations based on 117 sets of IECTC10 standard data and 419 sets of transformer fault data collected in China show that the diagnosis method proposed in this paper has strong search ability and fast convergence speed and has a significant improvement in diagnostic accuracy compared with traditional methods.
14 citations
TL;DR: A rolling bearing fault diagnosis method suitable for different working conditions based on simulating the real industrial scene and the experimental results show that the average fault diagnosis accuracy can reach 96.58%.
Abstract: The diagnosis of rolling bearing faults has become an increasingly popular research topic in recent years. However, many studies have been conducted based on sufficient training data. In the real industrial scene, there are some problems in bearing fault diagnosis, including the imbalanced ratio of normal and failure data and the amount of unlabeled data being far more than the amount of marked data. This paper presents a rolling bearing fault diagnosis method suitable for different working conditions based on simulating the real industrial scene. Firstly, the dataset is divided into the source and target domains, and the signals are transformed into pictures by continuous wavelet transform. Secondly, Wasserstein Generative Adversarial Nets-Gradient Penalty (WGAN-GP) is used to generate false sample images; then, the source domain and target domain data are input into the migration learning network with Resnet50 as the backbone for processing to extract similar features. Multi-Kernel Maximum mean discrepancies (MK-MMD) are used to reduce the edge distribution difference between the data of the source domain and the target domain. Based on Case Western Reserve University′s dataset, the feasibility of the proposed method is verified by experiments. The experimental results show that the average fault diagnosis accuracy can reach 96.58%.
9 citations
TL;DR: Wang et al. as discussed by the authors exploited the multivariate manifold structure by hypergraph, and proposed a hypergraph regularized semi-supervised support vector machine (HGSVM) algorithm.
Abstract: At present, graph regularized semi-supervised methods achieve excellent performance in various fields. However, the manifold regularization term of most methods only considers the pairwise relationship between data, thus it cannot accurately represent the multivariate and complex structure of data. In this paper, we exploit the multivariate manifold structure by hypergraph, and propose a hypergraph regularized semi-supervised support vector machine (HGSVM) algorithm. To accelerate the training process of HGSVM, we further develop a fast algorithm based boundary sample selection algorithm, termed fast-HGSVM. Moreover, two SMOTE-variant techniques and the one-vs-rest strategy are introduced in fast-HGSVM, and two multi-category semi-supervised algorithms called fast-ASHGSVM and fast-KSHGSVM are proposed. Experiments on two moons and UCI datasets validate the effectiveness of the proposed algorithms.
7 citations
References
More filters
TL;DR: The fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors are introduced.
Abstract: This paper is intended as a tutorial overview of induction motors signature analysis as a medium for fault detection. The purpose is to introduce in a concise manner the fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors. The paper is focused on the so-called motor current signature analysis which utilizes the results of spectral analysis of the stator current. The paper is purposefully written without "state-of-the-art" terminology for the benefit of practising engineers in facilities today who may not be familiar with signal processing.
1,396 citations
"Incipient Fault Detection in Stator..." refers methods in this paper
...High-resolution spectral analysis-based techniques such as multiple signal classification (MUSIC) and root-MUSIC have also been used for stator fault diagnosis [10]....
[...]
TL;DR: This paper attempts to present a comprehensive review of AI algorithms in rotating machinery fault diagnosis, from both the views of theory background and industrial applications.
Abstract: Fault diagnosis of rotating machinery plays a significant role for the reliability and safety of modern industrial systems. As an emerging field in industrial applications and an effective solution for fault recognition, artificial intelligence (AI) techniques have been receiving increasing attention from academia and industry. However, great challenges are met by the AI methods under the different real operating conditions. This paper attempts to present a comprehensive review of AI algorithms in rotating machinery fault diagnosis, from both the views of theory background and industrial applications. A brief introduction of different AI algorithms is presented first, including the following methods: k-nearest neighbour, naive Bayes, support vector machine, artificial neural network and deep learning. Then, a broad literature survey of these AI algorithms in industrial applications is given. Finally, the advantages, limitations, practical implications of different AI algorithms, as well as some new research trends, are discussed.
1,287 citations
"Incipient Fault Detection in Stator..." refers background in this paper
...The widespread use of machine learning (ML) techniques for stator fault diagnosis has been reported in various articles [18], [19]....
[...]
TL;DR: In this article, a comprehensive review of various stator faults, their causes, detection parameters/techniques, and latest trends in the condition monitoring technology is presented. And a broad perspective on the status of stator fault monitoring to researchers and application engineers using induction motors is provided.
Abstract: Condition monitoring of induction motors is a fast emerging technology for online detection of incipient faults. It avoids unexpected failure of a critical system. Approximately 30-40% of faults of induction motors are stator faults. This work presents a comprehensive review of various stator faults, their causes, detection parameters/techniques, and latest trends in the condition monitoring technology. It is aimed at providing a broad perspective on the status of stator fault monitoring to researchers and application engineers using induction motors. A list of 183 research publications on the subject is appended for quick reference.
541 citations
"Incipient Fault Detection in Stator..." refers background in this paper
...[4], they are generally caused due to a combination of vibrations caused by electromechanical forces, frequent motor start-ups and stops, high dv/dt voltage surges, mechanical stresses, thermal overload, and contamination....
[...]
TL;DR: An in-depth literature review of testing and monitoring methods that diagnose the condition of the turn-to-turn insulation of low-voltage machines, which is a rapidly expanding area for both research and product development efforts.
Abstract: A breakdown of the electrical insulation system causes catastrophic failure of the electrical machine and brings large process downtime losses. To determine the conditions of the stator insulation system of motor drive systems, various testing and monitoring methods have been developed. This paper presents an in-depth literature review of testing and monitoring methods, categorizing them into online and offline methods, each of which is further grouped into specific areas according to their physical nature. The main focus of this paper is on testing and monitoring techniques that diagnose the condition of the turn-to-turn insulation of low-voltage machines, which is a rapidly expanding area for both research and product development efforts. In order to give a compact overview, the results are summarized in two tables. In addition to monitoring methods on turn-to-turn insulation, some of the most common methods to assess the stator's phase-to-ground and phase-to-phase insulation conditions are included in the tables as well.
438 citations
"Incipient Fault Detection in Stator..." refers methods in this paper
...Several techniques based on the current signals are reported in [3], where the analysis is performed with negative sequence components, spectral analysis, high-resolution spectral analysis, Park/Concordia methods, high-frequency signal injection method, time-frequency analysis, and so on....
[...]
12 Sep 1994
TL;DR: A survey of the reliability of squirrel cage motors on board drilling, production, and other platforms offshore, together with cage motors in the petrochemical industry, gas terminals, and refineries onshore is presented in this article.
Abstract: This report presents a survey of the reliability of squirrel cage motors on board drilling, production, and other platforms offshore, together with cage motors in the petrochemical industry, gas terminals, and refineries onshore. Most of the activity in this connection is related to The North Sea that offers a tough environment for motors. The collected data have been treated statistically, and the faults sorted according to supply and motor data, driving conditions, electrical protection, maintenance, and so on, and further analyzes failure-initiators, contributors, and underlying causes. Comparisons between this survey and a survey from the IEEE Motor Reliability Working Group [8] have been done. The report also pays some attention to methods for monitoring of machinery and detecting of faults. >
355 citations
"Incipient Fault Detection in Stator..." refers background in this paper
...Such faults share about 30%–40% of the total motor faults [1], [2]....
[...]