A new method for rolling bearing compound fault diagnosis based on WT-PCA method

Abstract

As it is difficult to extract the combined faults from rolling bearings of aero-engine in strong noise, a fault diagnosis method based on wavelet transform (WT), principal component analysis (PCA) and self-correlation noise reduction is proposed to solve this problem. The proposed method is then compared with the target matrix composed of maximum component of kurtosis, the largest and the second largest kurtosis value. The result of comparative analysis reveals that the 2D target matrix proposed in this paper works better to extract the characteristic frequency of combined faults of rolling bearings in terms of accuracy and effectiveness.

Diagnosis of rotating machinery based on improved convolutional neural networks with gray-level transformation

“…Chen et al [18] applied the diagonal slice spectrum (DSS) to the final signal of ATVMF, the method enhanced the pulse characteristics related to the fault and can diagnose the weak fault of the bearing. A new fault diagnosis method based on the Wavelet Transform (WT), the Principal Component Analysis (PCA) and the autocorrelation noise reduction effectively is developed to extract the characteristic frequency of the rolling bearing combined faults [19]. A novel fault diagnosis approach based on the improved Manhattan distance in Symmetrized Dot Pattern (SDP) image is proposed.…”