Residual Life Prediction of Bearings Based on SENet-TCN and Transfer Learning

Abstract

Accurate bearing remaining life prediction guarantees safety and continued profitability for the industry. Variable operating conditions of the bearing and difficulty in obtaining corresponding data labels in the industry result in low prediction accuracy of the model. To solve these problems, a bearing life prediction model based on an improved temporal convolutional network and transfer learning is proposed. First, the squeeze-and-excitation network is used to mine and recalibrate the deep features of source domain data. Second, the temporal convolutional network is used to calibrate the relationship between the features and lifetime, and the optimal source domain model is trained. Finally, the transfer learning training is conducted with the source domain model to obtain the transfer model, which can accurately predict the remaining life of the multi-operating condition signal. Comparative experiments were performed on IEEE PHM Challenge 2012 bearing life dataset. The results show that the proposed method can better mine the inherent degradation trend of bearings and effectively improve the prediction accuracy of the remaining useful life. Compared with the existing popular prediction methods, the prediction error was reduced by '20.8%' to '51.5%', which proves the effectiveness and feasibility of the proposed method.