Visualization of Induction Machine Fault Detection Using Self-Organizing Map and Support Vector Machine

Induction machines play an important role in today’s industries. How to monitoring, detection, classification, and diagnosis of induction machine faults have been the essential problems. Although there have been many methods proposed to deal with these problems, there is lack of visualization tool for understanding the problems more easily. In this paper, a visualization method is proposed to help users understand the mechanism of induction machine fault detection in a transparent way. Furthermore, user can also tell the status (normal or faulty) just directly from the visualization results. The visualization is implemented by hybridizing two neural networks: self-organizing map and support vector machine. Experimental results demonstrate the novelty and effectiveness of the proposed visualization method used for induction machine fault detection.

[1]  Tommy W. S. Chow,et al.  Support vector visualization and clustering using self-organizing map and vector one-class classification , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[2]  Hujun Yin,et al.  ViSOM - a novel method for multivariate data projection and structure visualization , 2002, IEEE Trans. Neural Networks.

[3]  Tommy W. S. Chow,et al.  Induction machine fault detection using SOM-based RBF neural networks , 2004, IEEE Transactions on Industrial Electronics.

[4]  Ye Zhongming,et al.  A review on induction motor online fault diagnosis , 2000, Proceedings IPEMC 2000. Third International Power Electronics and Motion Control Conference (IEEE Cat. No.00EX435).

[5]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[6]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems: theory and application , 1989 .

[7]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[8]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[9]  J. Edward Jackson,et al.  A User's Guide to Principal Components. , 1991 .

[10]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[11]  F. Filippetti,et al.  Neural networks aided on-line diagnostics of induction motor rotor faults , 1993, Conference Record of the 1993 IEEE Industry Applications Conference Twenty-Eighth IAS Annual Meeting.

[12]  Mo-Yuen Chow,et al.  Neural-network-based motor rolling bearing fault diagnosis , 2000, IEEE Trans. Ind. Electron..

[13]  Fiorenzo Filippetti,et al.  Recent developments of induction motor drives fault diagnosis using AI techniques , 2000, IEEE Trans. Ind. Electron..

[14]  Steffen Leonhardt,et al.  Methods of fault diagnosis , 1997 .

[15]  J. E. Jackson.  A User's Guide to Principal Components , 1991 .

[16]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[17]  Robert E. Uhrig,et al.  Monitoring and diagnosis of rolling element bearings using artificial neural networks , 1993, IEEE Trans. Ind. Electron..

[18]  Mo-Yuen Chow,et al.  A neural network approach to real-time condition monitoring of induction motors , 1991 .

[19]  Jeanny Hérault,et al.  Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets , 1997, IEEE Trans. Neural Networks.

[20]  John W. Sammon,et al.  A Nonlinear Mapping for Data Structure Analysis , 1969, IEEE Transactions on Computers.

[21]  Sun-Yuan Kung,et al.  Principal Component Neural Networks: Theory and Applications , 1996 .

[22]  Trevor F. Cox,et al.  Metric multidimensional scaling , 2000 .

[23]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[24]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.