An Application Of A Hybrid Wavelet-SVM Based Approach For Induction Motor Fault Detection

Intelligent Methods ◽

Induction motors have been widely used in the industries due to their simple and rugged construction. Failures of this electrical machinery may cause considerable losses. Therefore adapting an efficient method to diagnose a fault at a very early stage would prevent any further consequences of this deficiency. The major concern is related to the mechanical failures, normally caused by the inner component deficiencies. Application of intelligent methods have attracted interest in recent years. Support Vector Machine is a supervised learning method, based on statistical learning theory. This thesis presents three different SVM algorithms: SVM, KPCA-SVM and ROC-SVM, applicable for broken rotor bars detection. SVM proved to be reliable method for classification. While application of KPCA-SVM, shows nonlinear feature extraction can improve the performance of classifier with respect to reduce the number of overlapping samples. Furthermore, ROC-SVM has improved the accuracy by selecting a decision threshold for the classifier.

Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors

Expert Systems with Applications ◽

10.1016/j.eswa.2006.04.020 ◽

2007 ◽

Vol 33 (1) ◽

pp. 241-250 ◽

Cited By ~ 199

Author(s):

Achmad Widodo ◽

Bo-Suk Yang

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Support Vector Machines ◽

Induction Motors ◽

Support Vector ◽

Vector Machines ◽

Application of nonlinear feature extraction and least square support vector machines for fault diagnosis of chemical process

Journal of Computer Applications ◽

10.3724/sp.j.1087.2010.00236 ◽

2010 ◽

Vol 30 (1) ◽

pp. 236-239 ◽

Cited By ~ 1

Author(s):

Liang XU

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Support Vector Machines ◽

Chemical Process ◽

Least Square ◽

Support Vector ◽

Vector Machines ◽

Improving Sparsity in Kernelized Nonlinear Feature Extraction Algorithms by Polynomial Kernel Higher Order Neural Networks

Artificial Higher Order Neural Networks for Computer Science and Engineering ◽

10.4018/978-1-61520-711-4.ch009 ◽

2010 ◽

pp. 223-238 ◽

Cited By ~ 3

Author(s):

Zhao Lu ◽

Gangbing Song ◽

Leang-san Shieh

Keyword(s):

Neural Networks ◽

Feature Extraction ◽

Support Vector Regression ◽

Higher Order ◽

Polynomial Kernel ◽

Support Vector ◽

Higher Order Neural Networks ◽

Programming Support ◽

As a general framework to represent data, the kernel method can be used if the interactions between elements of the domain occur only through inner product. As a major stride towards the nonlinear feature extraction and dimension reduction, two important kernel-based feature extraction algorithms, kernel principal component analysis and kernel Fisher discriminant, have been proposed. They are both used to create a projection of multivariate data onto a space of lower dimensionality, while attempting to preserve as much of the structural nature of the data as possible. However, both methods suffer from the complete loss of sparsity and redundancy in the nonlinear feature representation. In an attempt to mitigate these drawbacks, this article focuses on the application of the newly developed polynomial kernel higher order neural networks in improving the sparsity and thereby obtaining a succinct representation for kernel-based nonlinear feature extraction algorithms. Particularly, the learning algorithm is based on linear programming support vector regression, which outperforms the conventional quadratic programming support vector regression in model sparsity and computational efficiency.

Target Recognition of SAR Images Based on Linear and Nonlinear Feature Extraction and Classification

Computational Intelligence and Neuroscience ◽

10.1155/2021/4322678 ◽

2021 ◽

Vol 2021 ◽

pp. 1-8

Author(s):

Haiyan Zhao

Keyword(s):

Feature Extraction ◽

Target Recognition ◽

Principal Component ◽

Kernel Functions ◽

Support Vector ◽

Sar Images ◽

Feature Vectors ◽

Linear And Nonlinear ◽

A synthetic aperture radar (SAR) target recognition method combining linear and nonlinear feature extraction and classifiers is proposed. The principal component analysis (PCA) and kernel PCA (KPCA) are used to extract feature vectors of the original SAR image, respectively, which are classical and reliable feature extraction algorithms. In addition, KPCA can effectively make up for the weak linear description ability of PCA. Afterwards, support vector machine (SVM) and kernel sparse representation-based classification (KSRC) are used to classify the KPCA and PCA feature vectors, respectively. Similar to the idea of feature extraction, KSRC mainly introduces kernel functions to improve the processing and classification capabilities of nonlinear data. Through the combination of linear and nonlinear features and classifiers, the internal data structure of SAR images and the correspondence between test and training samples can be better investigated. In the experiment, the performance of the proposed method is tested based on the MSTAR dataset. The results show the effectiveness and robustness of the proposed method.

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

Bearing degradation state recognition based on kernel PCA and wavelet kernel SVM

10.1177/0954406214563235 ◽

2014 ◽

Vol 229 (15) ◽

pp. 2827-2834 ◽

Cited By ~ 5

Author(s):

Shaojiang Dong ◽

Dihua Sun ◽

Baoping Tang ◽

Zhengyuan Gao ◽

Yingrui Wang ◽

...

Keyword(s):

Principal Component ◽

Kernel Principal Component Analysis ◽

Support Vector ◽

Feature Extraction Method ◽

State Identification ◽

Mode Decomposition ◽

Kernel Support Vector Machine ◽

Characteristic Features ◽

In order to effectively recognize the bearing’s running state, a new method based on kernel principal component analysis (KPCA) and the Morlet wavelet kernel support vector machine (MWSVM) was proposed. First, the gathered vibration signals were decomposed by the empirical mode decomposition (EMD) to obtain the corresponding intrinsic mode function (IMF). The EMD energy entropy that includes dominant fault information is defined as the characteristic features. However, the extracted features remained high-dimensional, and excessive redundant information still existed. Therefore, the nonlinear feature extraction method KPCA was introduced to extract the characteristic features and to reduce the dimension. The extracted characteristic features were inputted into the MWSVM to train and construct the running state identification model, and the bearing’s running state identification was thereby realized. Cases of test and actual were analyzed. The results validate the effectiveness of the proposed algorithm.

Proceedings of the Second International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering ◽

Structural Damage Identification based on Nonlinear Feature Extraction of a Support Vector Machine

10.4203/ccp.97.32 ◽

2011 ◽

Author(s):

S.F. Jiang ◽

Z.Q. Wu ◽

N. Yang

Keyword(s):

Support Vector Machine ◽

Feature Extraction ◽

Structural Damage ◽

Damage Identification ◽

Support Vector ◽

Structural Damage Identification ◽

Fuzzy-Based Statistical Feature Extraction for Detecting Broken Rotor Bars in Line-Fed and Inverter-Fed Induction Motors

Energies ◽

10.3390/en12122381 ◽

2019 ◽

Vol 12 (12) ◽

pp. 2381 ◽

Cited By ~ 4

Author(s):

Cleber Gustavo Dias ◽

Luiz Carlos da da Silva ◽

Ivan Eduardo Chabu

Keyword(s):

Feature Extraction ◽

Magnetic Flux ◽

Flux Density ◽

Induction Motors ◽

False Negative ◽

Magnetic Flux Density ◽

Support Vector ◽

Inference System ◽

Broken Rotor Bars ◽

Statistical Feature

This paper presents the use of a fuzzy-based statistical feature extraction from the air gap disturbances for diagnosing broken rotor bars in large induction motors fed by line or an inverter. The method is based on the analysis of the magnetic flux density variation in a Hall Effect Sensor, installed between two stator slots of the motor. The proposed method combines a fuzzy inference system and a support vector machine technique for time-domain assessment of the magnetic flux density, in order to detect a single fault or multiple broken bars in the rotor. In this approach, it is possible to detect not only the existence of failures, but also its severity. Moreover, it is not necessary to estimate the slip of the motor, usually required by other methods and the damaged rotor detection was also evaluated for oscillating load conditions. Thus, the present approach can overcome some drawbacks of the traditional MCSA method, particularly in operational cases where false positive and false negative indications are more frequently. The efficiency of this approach has been proven using some computational simulation results and experimental tests to detect fully broken rotor bars in a 7.5 kW squirrel cage induction machine fed by line and an inverter.