Sparse Representation and SVM Diagnosis Method Inter-Turn Short-Circuit Fault in PMSM

Permanent magnet synchronous motors (PMSM) has the advantages of simple structure, small size, high efficiency, and high power factor, and a key dynamic source and is widely used in industry, equipment and electric vehicle. Aiming at its inter-turn short-circuit fault, this paper proposes a fault diagnosis method based on sparse representation and support vector machine (SVM). Firstly, the sparse representation is used to extract the first and second largest sparse coefficients of both current signal and vibration signals, and then they are composed into four-dimensional feature vectors. Secondly, the feature vectors are input into the support vector machine for fault diagnosis, which is suitable for small sample. Experiments on a permanent magnet synchronous motor with artificially set inter-turn short-circuit fault and a normal one showed that the method is feasible and accurate.

Download Full-text

FAULT DIAGNOSIS BASED ON LMD-SVD AND INFORMATION-GEOMETRIC SUPPORT VECTOR MACHINE FOR HYDRAULIC PUMPS

Transactions of the Canadian Society for Mechanical Engineering ◽

10.1139/tcsme-2015-0044 ◽

2015 ◽

Vol 39 (3) ◽

pp. 569-580 ◽

Cited By ~ 3

Author(s):

Ye Tian ◽

Chen Lu ◽

Zhipeng Wang ◽

Zili Wang

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Small Sample ◽

Support Vector ◽

Svm Classifier ◽

Health States ◽

Diagnosis Method ◽

Stationary Vibration ◽

Local Mean ◽

Value Decomposition

This study proposes a fault diagnosis method for hydraulic pumps based on local mean decomposition (LMD), singular value decomposition (SVD), and information-geometric support vector machine (IG-SVM). First, the nonlinear and non-stationary vibration signals are decomposed using LMD into several product functions (PFs). Then, the PFs are processed by SVD to obtain more stable and compact feature vectors. Finally, the health states are identified by an IG-SVM classifier, which is less-dependent on the selected kernel function and parameters than SVM. In addition, the comparisons between LMD, EMD, and WPD demonstrate the superiority of LMD in feature extraction. Compared with SVM and BP neural network, IG-SVM shows higher classification accuracy and computational efficiency in dealing with small-sample fault diagnosis. From the experimental results, it was concluded that the proposed method can effectively realize fault diagnosis for hydraulic pumps under small-sample conditions.

Download Full-text

Fault Diagnosis Method of Mine Motor Based on Support Vector Machine

Recent Patents on Engineering ◽

10.2174/1872212113666191121122720 ◽

2019 ◽

Vol 13 ◽

Author(s):

Yan Zhang ◽

Ren Sheng

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Optimization Method ◽

Support Vector ◽

Optimal Parameters ◽

Instantaneous Power ◽

Practical Usefulness ◽

Sample Data ◽

Diagnosis Method ◽

Fault Characteristic

Background: In order to improve the efficiency of fault treatment of mining motor, the method of model construction is used to construct the type of kernel function based on the principle of vector machine classification and the optimization method of parameters. Methodology: One-to-many algorithm is used to establish two kinds of support vector machine models for fault diagnosis of motor rotor of crusher. One of them is to obtain the optimal parameters C and g based on the input samples of the instantaneous power fault characteristic data of some motor rotors which have not been processed by rough sets. Patents on machine learning have also shows their practical usefulness in the selction of the feature for fault detection. Results: The results show that the instantaneous power fault feature extracted from the rotor of the crusher motor is obtained by the cross validation method of grid search k-weights (where k is 3) and the final data of the applied Gauss radial basis penalty parameter C and the nuclear parameter g are obtained. Conclusion: The model established by the optimal parameters is used to classify and diagnose the sample of instantaneous power fault characteristic measurement of motor rotor. Therefore, the classification accuracy of the sample data processed by rough set is higher.

Download Full-text

Analog Circuit Fault Diagnosis Based on Support Vector Machine Classifier and Fuzzy Feature Selection

Electronics ◽

10.3390/electronics10121496 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1496

Author(s):

Hao Liang ◽

Yiman Zhu ◽

Dongyang Zhang ◽

Le Chang ◽

Yuming Lu ◽

...

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Mutual Information ◽

Analog Circuit ◽

Fault Classification ◽

Support Vector ◽

Svm Classifier ◽

Fault Parameters ◽

Diagnosis Method ◽

Circuit Fault Diagnosis

In analog circuit, the component parameters have tolerances and the fault component parameters present a wide distribution, which brings obstacle to classification diagnosis. To tackle this problem, this article proposes a soft fault diagnosis method combining the improved barnacles mating optimizer(BMO) algorithm with the support vector machine (SVM) classifier, which can achieve the minimum redundancy and maximum relevance for feature dimension reduction with fuzzy mutual information. To be concrete, first, the improved barnacles mating optimizer algorithm is used to optimize the parameters for learning and classification. We adopt six test functions that are on three data sets from the University of California, Irvine (UCI) machine learning repository to test the performance of SVM classifier with five different optimization algorithms. The results show that the SVM classifier combined with the improved barnacles mating optimizer algorithm is characterized with high accuracy in classification. Second, fuzzy mutual information, enhanced minimum redundancy, and maximum relevance principle are applied to reduce the dimension of the feature vector. Finally, a circuit experiment is carried out to verify that the proposed method can achieve fault classification effectively when the fault parameters are both fixed and distributed. The accuracy of the proposed fault diagnosis method is 92.9% when the fault parameters are distributed, which is 1.8% higher than other classifiers on average. When the fault parameters are fixed, the accuracy rate is 99.07%, which is 0.7% higher than other classifiers on average.

Download Full-text

Fault Diagnosis Method of Low Noise Amplifier Based on Support Vector Machine and Hidden Markov Model

Journal of Electronic Testing ◽

10.1007/s10836-021-05938-0 ◽

2021 ◽

Author(s):

Lu Sun ◽

Yang Li ◽

Han Du ◽

Peipei Liang ◽

Fushun Nian

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Markov Model ◽

Hidden Markov Model ◽

Hidden Markov ◽

Low Noise ◽

Low Noise Amplifier ◽

Support Vector ◽

Diagnosis Method ◽

Noise Amplifier

Download Full-text

Sparse representation theory for support vector machine kernel function selection and its application in high-speed bearing fault diagnosis

ISA Transactions ◽

10.1016/j.isatra.2021.01.060 ◽

2021 ◽

Author(s):

Baojian Wang ◽

Xiaoli Zhang ◽

Suo Xing ◽

Chuang Sun ◽

Xuefeng Chen

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Representation Theory ◽

Sparse Representation ◽

Kernel Function ◽

High Speed ◽

Support Vector ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Function Selection

Download Full-text

A transformer fault diagnosis method based on sub-clustering reduction and multiclass multi-kernel support vector machine

2017 IEEE Conference on Energy Internet and Energy System Integration (EI2) ◽

10.1109/ei2.2017.8245354 ◽

2017 ◽

Cited By ~ 1

Author(s):

Jieshan Li ◽

Yonghu Zhu ◽

Yibin Xu ◽

Chuangxin Guo

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Support Vector ◽

Kernel Support Vector Machine ◽

Diagnosis Method ◽

Transformer Fault

Download Full-text

Research on Gyro Fault Diagnosis Method Based on Wavelet Packet Decomposition and Multi-class Least Squares Support Vector Machine

Recent Trends in Intelligent Computing, Communication and Devices - Advances in Intelligent Systems and Computing ◽

10.1007/978-981-13-9406-5_94 ◽

2019 ◽

pp. 789-797

Author(s):

Qiang Liu ◽

Jinjin Cheng ◽

Wenhao Guo

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Least Squares ◽

Wavelet Packet ◽

Support Vector ◽

Wavelet Packet Decomposition ◽

Diagnosis Method

Download Full-text

A Novel Fault Diagnosis Method for Power Transformer Based on Dissolved Gas Analysis Using Hypersphere Multiclass Support Vector Machine and Improved D–S Evidence Theory

Energies ◽

10.3390/en12204017 ◽

2019 ◽

Vol 12 (20) ◽

pp. 4017 ◽

Cited By ~ 7

Author(s):

Haikun Shang ◽

Junyan Xu ◽

Zitao Zheng ◽

Bing Qi ◽

Liwei Zhang

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Evidence Theory ◽

Gas Analysis ◽

Power Transformers ◽

Support Vector ◽

Dissolved Gas ◽

Dissolved Gas Analysis ◽

Diagnosis Method ◽

Multiclass Support Vector Machine

Power transformers are important equipment in power systems and their reliability directly concerns the safety of power networks. Dissolved gas analysis (DGA) has shown great potential for detecting the incipient fault of oil-filled power transformers. In order to solve the misdiagnosis problems of traditional fault diagnosis approaches, a novel fault diagnosis method based on hypersphere multiclass support vector machine (HMSVM) and Dempster–Shafer (D–S) Evidence Theory (DET) is proposed. Firstly, proper gas dissolved in oil is selected as the fault characteristic of power transformers. Secondly, HMSVM is employed to diagnose transformer fault with selected characteristics. Then, particle swarm optimization (PSO) is utilized for parameter optimization. Finally, DET is introduced to fuse three different fault diagnosis methods together, including HMSVM, hybrid immune algorithm (HIA), and kernel extreme learning machine (KELM). To avoid the high conflict between different evidences, in this paper, a weight coefficient is introduced for the correction of fusion results. Results indicate that the fault diagnosis based on HMSVM has the highest probability to identify transformer faults among three artificial intelligent approaches. In addition, the improved D–S evidence theory (IDET) combines the advantages of each diagnosis method and promotes fault diagnosis accuracy.

Download Full-text