The use of features selection and nearest neighbors rule for faults diagnostic in induction motors

This paper deals with the diagnosis of induction motors by pattern recognition methods. The objective is to use existing theories to improve the diagnosis procedures in electrical engineering. First of all, a single signature is determined to monitor several different operating modes. For this purpose, features are extracted from the combination of the stator currents and voltages. Then, the sequential backward algorithm is applied in order to select the most relevant features. The classification is performed by the k-nearest neighbors rule with reject options. The methodology is applied on a 5.5kW motor in normal conditions, then with stator and rotor faults. The experimental results prove the efficiency of pattern recognition methods in condition monitoring of electrical machines.

[1]  Hamid A. Toliyat,et al.  Transient analysis of cage induction machines under stator, rotor bar and end ring faults , 1995 .

[2]  Ivan Tomek,et al.  A Generalization of the k-NN Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Mineichi Kudo,et al.  Comparison of algorithms that select features for pattern classifiers , 2000, Pattern Recognit..

[4]  T.G. Habetler,et al.  Motor bearing damage detection using stator current monitoring , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[5]  C. K. Chow,et al.  On optimum recognition error and reject tradeoff , 1970, IEEE Trans. Inf. Theory.

[6]  W. T. Thomson,et al.  Current signature analysis to detect induction motor faults , 2001 .

[7]  Peter Vas,et al.  Electrical Machines and Drives: A Space-Vector Theory Approach , 1993 .

[8]  Mohamed Benbouzid,et al.  Induction motors' faults detection and localization using stator current advanced signal processing techniques , 1999 .

[9]  G. Dunteman.  Principal Components Analysis , 1989 .

[10]  C. H. Rojas,et al.  Study of an induction motor working under stator winding inter-turn short circuit condition , 2003, 4th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, 2003. SDEMPED 2003..

[11]  Guy Clerc,et al.  Rotor resistance estimation by non-linear observer for diagnostic and control systems , 2000 .

[12]  M. Dalva,et al.  A survey of faults on induction motors in offshore oil industry, petrochemical industry, gas terminals and oil refineries , 1994, Proceedings of IEEE Petroleum and Chemical Industry Technical Conference (PCIC '94).

[13]  Ben Pinkowski.  Principal component analysis of speech spectrogram images , 1997, Pattern Recognit..

[14]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .