Remaining Useful Life Prediction of Bearings Using Reverse Attention Graph Convolution Network With Residual Convolution Transformer

Abstract

Bearings are key components in mechanical equipment, and remaining useful life (RUL) prediction of bearings is of great significance for stable production in industry. To predict RUL accurately, the time-frequency diagram and the long-term dependence of vibration signals have been widely researched. However, the linear frequency scale of time-frequency diagram is unfavorable to balance characteristic defect of low frequency and natural vibration of high frequency. Also, abrupt change vibration causes serious interference to long-term dependence. Therefore, based on theoretical analysis of bearings vibration, we introduce Mel-scale frequency cepstral coefficient (MFCC) three-channel image and propose reverse attention graph convolution network with residual convolution Transformer (RCT-RAGCN). MFCC three-channel image optimizes the frequency region by logarithmic Mel scale. Reverse attention improves aggregation method of long-term dependence, alleviates the interference of abrupt change, and approaches long-term dependency problems from signal difference perspective. In constructed graphs, reverse attention matrices are as edges, which is profit for aggregation of abrupt change by graph convolution network (GCN). In proposed encoder, residual convolution extracts features from MFCC three-channel image, and Transformer learns raw signals to prevent information loss caused in constructing MFCC. On the IEEE PHM 2012 dataset, results indicate that the proposed method outperforms five advanced models in terms of accuracy. The ablation studies verify the significant role of the proposed method.