RONG Ming-xing. Wavelet Transform and Neural Networks in Fault Diagnosis of a Motor Rotor[J]. International Journal of Plant Engineering and Management, 2012, 17(2): 104-111

Wavelet Transform and Neural Networks in Fault Diagnosis of a Motor Rotor
RONG Ming-xing
Heilongjiang Institute of Science and Technology,Harbin 150027,P. R. China
In the motor fault diagnosis technique,vibration and stator current frequency components of detection are two main means.This article will discuss the signal detection method based on vibration fault.Because the motor vibration signal is a non-stationary random signal,fault signals often contain a lot of time-varying,burst properties of ingredients.The traditional Fourier signal analysis can not effectively extract the motor fault characteristics,but are also likely to be rich in failure information but a weak signal as noise.Therefore,we introduce wavelet packet transforms to extract the fault characteristics of the signal information.Obtained was the result as the neural network input signal,using the L-M neural network optimization method for training,and then used the BP network for fault recognition.This paper uses Matlab software to simulate and confirmed the method of motor fault diagnosis validity and accuracy.
Key words:    fault diagnosis    wavelet transform    neural networks    motor    vibration signal   
Received: 2012-05-16     Revised:
Corresponding author:
Author description:
PDF(787KB) Free

[1] Peng WJ,Luo X Z,Guo P C,Based on 2ndgeneration of hydropower units'wavelet signalpreprocessing. Chinese Journal of MechanicalEngineering,27(30):25-29,2007(InC hinese)
[2] Yang Y Q,Liu X,Ying J G,Characteristicsof power transformer vibration signal based onwavelet theory. High Voltage Technology,33(1):4-8,2007(In Chinese)
[3] Zhong B L,Huang R,Mechanical fault diag-uostics. Second Edition Beijing:MechanicalIndustry Press,2002 (In Chinese)
[4] Feng Z P,Li X J,Chu F L,Turbine based onstationary wavelet packet decomposition of non-stationary vibration signal Hilbert spectral a-nalysis. Chinese Journal of Mechanical Engi-neering,26(12):32-37,2006(In Chi-nese)
[5] Wang Z S,lutelligent, fault diagnosis and, fault tolerant control.Beijing:National Defense Industry Press,2005 (In Chinese)
[6] Liu M C,Wavelet analysis and its applications. Beijing:Tsinghua University Press, 2005 (In Chinese)
[7] Qi M,Chen L D,Feng T H,Thavelet packet in the rotary machinery fault diagnosis ribra-tion signal processing applications. Computing Technology and Automation, 24(2):14-17,2005 (In Chinese)
[8] Liao C J,Luo X L,Li X J,Thabelet packet transform in feature extraction of acoustic emis-siou signal application. Journal of Electronic Measurement and Instrument,22 (4 ):79-85,2008 (In Chinese)
[9] Qian H M,Ma J C,Shi L J,Sensor fault diag-nosis based on wavelet neural network naviga-tiou. Journal of Electronic Measurement and In-strument, 21(Supplement ):538-541,2007 (In Chinese)
[10] Wang P,Based on wavelet neural network in. fault diagnosis of the motor bearing. Shanxi:Taiyuan University of Technology,2005(InChinese)