Wavelet-based methods for the prognosis of mechanical and electrical failures in electric motors

被引:37
作者
Zanardelli, WG [1 ]
Strangas, EG
Khalil, HK
Miller, JM
机构
[1] Michigan State Univ, Dept Elect & Comp Engn, E Lansing, MI 48824 USA
[2] Ford Motor Co, Dearborn, MI 48121 USA
关键词
fault prognosis; wavelets; d.c; motors;
D O I
10.1016/j.ymssp.2003.10.002
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
The ability to give a prognosis for failure of a system is a valuable tool and can be applied to electric motors. In this paper, three wavelet-based methods have been developed that achieve this goal. Wavelet and filter bank theory, the nearest-neighbour rule, and linear discriminant functions are reviewed. A framework for the development of a fault detection and classification algorithm based on the coefficients calculated from the discrete wavelet transform and using clustering is described. An experimental set-up based on RT-Linux is described and results from testing are presented, verifying the analysis. (C) 2003 Elsevier Ltd. All rights reserved.
引用
收藏
页码:411 / 426
页数:16
相关论文
共 14 条
[1]  
[Anonymous], 2003, Statistical pattern recognition
[2]  
[Anonymous], 1974, Classification, Estimation and Pattern Recognition
[3]  
Burrus C.S., 1998, introduction to Wavelets and Wavelet Transforms-A Primer
[4]  
Chen D, 2002, MECH SYST SIGNAL PR, V16, P695, DOI [10.1006/mssp.2002.1488, 10.1006/ymssp.1488]
[5]   NEAREST NEIGHBOR PATTERN CLASSIFICATION [J].
COVER, TM ;
HART, PE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) :21-+
[6]  
FRIEDMAN JH, 1975, IEEE T COMPUT, V24, P1000, DOI 10.1109/T-C.1975.224110
[7]   Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network [J].
Liu, XQ ;
Zhang, HY ;
Liu, J ;
Yang, J .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2000, 47 (05) :1021-1030
[8]   Application of model-based fault detection to a brushless DC motor [J].
Moseler, O ;
Isermann, R .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2000, 47 (05) :1015-1020
[9]   Monitoring and diagnosis of induction motors electrical faults using a current Park's vector pattern learning approach [J].
Nejjari, H ;
Benbouzid, ME .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2000, 36 (03) :730-735
[10]   Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor [J].
Paya, BA ;
Esat, II ;
Badi, MNM .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 1997, 11 (05) :751-765