Remaining Useful Life Prediction Across Conditions Based on a Health Indicator-Weighted Subdomain Alignment Network

In recent years, domain adaptation (DA) has been extensively applied to predicting the remaining useful life (RUL) of bearings across conditions. Although traditional DA-based methods have achieved accurate predictions, most methods fail to extract multi-scale degradation information, focus only on global-scale DA, and ignore the importance of temporal weights. These limitations hinder further improvements in prediction accuracy. This paper proposes a novel model, called the health indicator-weighted subdomain alignment network (HIWSAN), which first learns feature representations at multiple scales, then constructs health indicators as temporal weights, and finally performs subdomain-level alignment. Two case studies based on the XJTU-SY and PRONOSTIA datasets were conducted, covering ablation, comparison, and generalization experiments to evaluate the proposed HIWSAN. Experimental results show that HIWSAN achieves an average MAE of 0.0989 and an average RMSE of 0.1189 across two datasets, representing reductions of 21.07% and 25.13%, respectively, compared to existing state-of-the-art methods.