Abstract: Driven by the development of big data,fault diagnosis method based on deep learning has gradually become a research hotspot in the field of fault diagnosis in recent years.However,in the real industrial field,deep learning fault diagnosis still has two limitations:1)Early fault features are weak and fault information extraction is insufficient.2)The distribution of fault data collected under variable conditions is inconsistent.The two points lead to the problems of low fault recognition rate and poor domain adaptability in deep learning fault diagnosis.In order to solve the problems above,a fault diagnosis method based on channel splitting CLAHE and adaptive threshold residual network(FEResNet) under variable operating conditions is proposed,which starts from the two perspectives of enhancing important features and deleting redundant features.Firstly,Morlet wavelet transform is employed for excavating discriminative time-frequency information hidden in vibration signals under variable operation conditions.Then,CLAHE with channel splitting is designed to improve the contrast and clarity of the time-frequency diagram to enhance fault information.Finally,the time-frequency diagram after feature enhancement is input to the designed adaptive thres-hold residual network to remove redundant features.Experimental results on CWRU dataset show that the prediction accuracy of the proposed method under the same working condition is up to 100%,the average prediction accuracy under different working conditions is up to 99.03%,and the domain adaptability is strong.

Key words: Fault diagnosis, Wavelet transform, CLAHE, Residual network, Feature enhancement