Title :
Fault diagnosis method study in roller bearing based on wavelet transform and stacked auto-encoder
Author :
Tan Junbo ; Lu Weining ; An Juneng ; Wan Xueqian
Author_Institution :
Center of Intell. Control & Telescience, Tsinghua Univ., Beijing, China
Abstract :
Considering the nonlinear and non-stationary characteristics of fault vibration signal in the roller bearing system, an intelligent fault diagnosis model based on wavelet transform and stacked auto-encoder is proposed. This paper firstly uses the combination of digital wavelet frame (DWF) and nonlinear soft threshold method to de-noise fault vibration signal. Then stacked auto-encoder is taken to extract the fault signal feature, which is regarded as the input of BP network classifier. The output results of BP network classifier represent fault categories. In addition, neural network ensemble method is also adopted to greatly improve the recognition rate of fault diagnosis.
Keywords :
backpropagation; fault diagnosis; feature extraction; neural nets; rolling bearings; signal classification; signal denoising; vibrational signal processing; wavelet transforms; BP network classifier; digital wavelet frame; fault categories; fault diagnosis recognition rate; fault signal feature extraction; fault vibration signal; fault vibration signal denoising; intelligent fault diagnosis model; neural network ensemble method; nonlinear characteristics; nonlinear soft threshold method; nonstationary characteristics; roller bearing; roller bearing system; stacked autoencoder; wavelet transform; Fault diagnosis; Feature extraction; Neural networks; Noise reduction; Vibrations; Wavelet transforms; deep learning; fault diagnosis; roller bearing; stacked auto-encoder; wavelet transform;
Conference_Titel :
Control and Decision Conference (CCDC), 2015 27th Chinese
Conference_Location :
Qingdao
Print_ISBN :
978-1-4799-7016-2
DOI :
10.1109/CCDC.2015.7162738
