FAULT-DETECTION AND DIAGNOSIS IN LOW-SPEED ROLLING ELEMENT BEARINGS .2. THE USE OF NEAREST NEIGHBOR CLASSIFICATION

被引:37
作者
MECHEFSKE, CK
MATHEW, J
机构
[1] Centre for Machine Condition Monitoring, Monash University, Melbourne, Vic.
关键词
D O I
10.1016/0888-3270(92)90033-F
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
An effective procedure for automatic fault diagnosis in low speed (≤100 RPM) rolling element bearings is described. The procedure involves the calculation of a statistical distance measure between vibration signals. The distance measure is then automatically used to distinguish between different fault conditions. A new trending index, based on the statistical distance measure, which may be used for fault detection, is also described. © 1992.
引用
收藏
页码:309 / 316
页数:8
相关论文
共 17 条
[11]  
Itakura, Minimum prediction residual principle applied to speech recognition, IEEE Transactions on Acoustics, Speech, and Signal Processing, 23 ASSP, pp. 67-72, (1975)
[12]  
Gersch, Yonemoto, Low, McEwan, Automatic classification of electroencephalograms: Kullback-Leibler nearest neighbour rules, Science, 205, pp. 193-195, (1979)
[13]  
Gersch, Botherton, Braun, Nearest neighbour time series analysis classification of faults in rotating machinery, Transactions of the ASME, 105, pp. 178-184, (1983)
[14]  
Braun, Mechanical Signature Analysis: Theory and Applications, (1986)
[15]  
Mechefske, Mathew, Parametric spectral estimation to detect and diagnose faults in low speed rolling element bearings: preliminary investigations, 2nd International Machine Monitoring and Diagonostics Conference, pp. 108-114, (1990)
[16]  
Mathew, Szczepanik, Kuhnell, Stecki, Incipient damage detection in low speed bearings using the demodulated resonance technique, The Institution of Engineers, Australia, International Tribology Conference, pp. 366-369, (1987)
[17]  
Luo, Mathew, Demodulation resonance analysis: a theoretical analysis, Proceedings of the Asia Vibration Conference, pp. 712-719, (1989)