Remaining useful life prediction of rolling bearings based on TCN-LSTM

Rolling bearings are crucial components in mechanical systems, and accurately predicting their remaining service life holds significant practical importance. To tackle the shortcomings of conventional deep learning methods for predicting remaining useful life (RUL), which suffer from insufficient feature extraction and low prediction accuracy, especially regarding single short-term and single long-term dependent features. This paper introduces a residual remaining useful life prediction method for bearings, named TCN-LSTM-attention, which leverages CBAM attention alongside parallel Temporal Convolutional Network (TCN) and Long Short-Term Memory (LSTM) components. The method employs parallel TCN and LSTM network architectures for feature extraction, concurrently integrating the CBAM attention mechanism to weigh features across various dimensions. This approach not only captures a more comprehensive distribution of features but also amplifies the representation of critic al features, thereby significantly enhancing RUL prediction accuracy. Finally, to assess the efficacy of the proposed method, we conducted experiments using the PHM2012 rolling bearing datasets. The results demonstrate the method's robustness and generalization capabilities.