A fuzzy support vector machine based on environmental membership and its application to motor fault classification

To weaken the effects of the outliers or noise in classification, a fuzzy support vector machine (FSVM) based on environmental fuzzy membership is proposed. The environmental fuzzy membership considers not only the number of the similar samples nearby but also the distribution of the samples nearby. As more information of the samples is considered, the reliability and robustness of the FSVM is further enhanced, which can improve the classification performance, especially for overlapping samples. The classification performance of the proposed method is validated by numerical case studies, an experimental study for a breast cancer dataset, and an application to motor fault classification. Compared with the FSVM based on the k-nearest neighbor algorithm, the proposed method obtains more robust and accurate classification rates in all case studies.

[1]  Guohai Liu,et al.  Internal Model Control of Permanent Magnet Synchronous Motor Using Support Vector Machine Generalized Inverse , 2013, IEEE Transactions on Industrial Informatics.

[2]  Peter W. Tse,et al.  An enhanced Kurtogram method for fault diagnosis of rolling element bearings , 2013 .

[3]  Z. Lachiri,et al.  Broken rotor bar diagnosis in induction machines through stationary wavelet packet transform and multiclass wavelet SVM , 2013 .

[4]  Iqbal Gondal,et al.  Inchoate Fault Detection Framework: Adaptive Selection of Wavelet Nodes and Cumulant Orders , 2012, IEEE Transactions on Instrumentation and Measurement.

[5]  S. Seker,et al.  Continuous Wavelet Transform for Bearing Damage Detection in Electric Motors , 2006, MELECON 2006 - 2006 IEEE Mediterranean Electrotechnical Conference.

[6]  Chong Liu,et al.  Motor Broken-Bar Fault Diagnosis Based on Park Vector and Wavelet Neural Network , 2011 .

[7]  Okan Bingol,et al.  A virtual laboratory for neural network controlled DC motors based on a DC-DC buck converter , 2012 .

[8]  Subhasis Nandi,et al.  Detection of Eccentricity Faults in Induction Machines Based on Nameplate Parameters , 2011, IEEE Transactions on Industrial Electronics.

[9]  Seungchul Lee,et al.  Source Contribution Evaluation of Mechanical Vibration Signals via Enhanced Independent Component Analysis , 2012 .

[10]  Osman Bilgin,et al.  Neural Network Classification and Diagnosis of Broken Rotor Bar Faults by Means of Short Time Fourier Transform , 2009 .

[11]  Paul King,et al.  Time-Frequency Analysis of Single-Point Engine-Block Vibration Measurements for Multiple Excitation-Event Identification , 2009 .

[12]  Jose A. Antonino-Daviu,et al.  Instantaneous Frequency of the Left Sideband Harmonic During the Start-Up Transient: A New Method for Diagnosis of Broken Bars , 2009, IEEE Transactions on Industrial Electronics.

[13]  J. Kamruzzaman,et al.  An Adaptive Self-Configuration Scheme for Severity Invariant Machine Fault Diagnosis , 2013, IEEE Transactions on Reliability.

[14]  Sheng-De Wang,et al.  Fuzzy support vector machines , 2002, IEEE Trans. Neural Networks.

[15]  Xiao Wu,et al.  A New Fuzzy SVM based on the Posterior Probability Weighting Membership , 2012, J. Comput..

[16]  Arturo Garcia-Perez,et al.  Reconfigurable Monitoring System for Time-Frequency Analysis on Industrial Equipment Through STFT and DWT , 2013, IEEE Transactions on Industrial Informatics.

[17]  Hadi Sadoghi Yazdi,et al.  Relaxed constraints support vector machines for noisy data , 2011, Neural Computing and Applications.

[18]  O. Mangasarian,et al.  Robust linear programming discrimination of two linearly inseparable sets , 1992 .

[19]  M. Riera-Guasp,et al.  Toward Condition Monitoring of Damper Windings in Synchronous Motors via EMD Analysis , 2012, IEEE Transactions on Energy Conversion.

[20]  Reinhard Klette,et al.  Fuzzy support vector machine with a fuzzy nearest neighbor classifier for insect footprint classification , 2010, International Conference on Fuzzy Systems.

[21]  Mehmet Akar.  Detection of a static eccentricity fault in a closed loop driven induction motor by using the angular domain order tracking analysis method , 2013 .

[22]  Zhengjia He,et al.  Independent component analysis based source number estimation and its comparison for mechanical systems , 2012 .

[23]  Lie Xu,et al.  Improvement of the Hilbert Method via ESPRIT for Detecting Rotor Fault in Induction Motors at Low Slip , 2013, IEEE Transactions on Energy Conversion.

[24]  Swagatam Das,et al.  Multi-sensor data fusion using support vector machine for motor fault detection , 2012, Inf. Sci..

[25]  Osman Bilgin,et al.  Automatic detection and classification of rotor cage faults in squirrel cage induction motor , 2010, Neural Computing and Applications.

[26]  B Mahdi Ebrahimi,et al.  Feature Extraction for Short-Circuit Fault Detection in Permanent-Magnet Synchronous Motors Using Stator-Current Monitoring , 2010, IEEE Transactions on Power Electronics.

[27]  Zhang Xiang,et al.  Fuzzy Support Vector Machine Based on Affinity Among Samples , 2006 .

[28]  E. Afjei,et al.  Misalignment fault analysis and diagnosis in switched reluctance motor , 2011 .

[29]  Seungchul Lee,et al.  Investigations of denoising source separation technique and its application to source separation and identification of mechanical vibration signals , 2014 .

[30]  Wei Cheng,et al.  Enhance the Separation Performance of ICA via Clustering Evaluation and Its Applications , 2011 .

[31]  Yu Zhang,et al.  Image denoising using SVM classification in nonsubsampled contourlet transform domain , 2013, Inf. Sci..

[32]  Gérard-André Capolino,et al.  Advanced Diagnosis of Electrical Faults in Wound-Rotor Induction Machines , 2013, IEEE Transactions on Industrial Electronics.