In response to the need for multiple complete bearing degradation datasets in traditional deep learning networks to predict the impact on individual bearings, a novel deep learning-based rolling bearing remaining life prediction method is proposed in the absence of fully degraded bearng data. This method involves processing the raw vibration data through Channel-wise Attention Encoder (CAE) from the Encoder-Channel Attention (ECA), extracting features related to mutual correlation and relevance, selecting the desired characteristics, and incorporating the selected features into the constructed Autoformer-based time prediction model to forecast the degradation trend of bearings' remaining time. The feature extraction method proposed in this approach outperforms CAE and multilayer perceptual-Attention Encoder in terms of feature extraction capabilities, resulting in reductions of 0.0059 and 0.0402 in mean square error, respectively. Additionally, the indirect prediction approach for the degradation trend of the target bearing demonstrates higher accuracy compared to Informer and Transformer models, with mean square error reductions of 0.3352 and 0.1174, respectively. This suggests that the combined deep learning model proposed in this paper for predicting rolling bearing life may be a more effective life prediction method deserving further research and application.
Keywords: Autoformer; deep learning; rolling bearings.