Remaining Useful Life Estimation Under Multiple Operating Conditions via Deep Subdomain Adaptation
Yifei Ding, Minping Jia, Yudong Cao
Abstract
Transfer learning (TL) and domain adaptation (DA) have aroused the interest of many researchers and are used in the prognostics and health management (PHM) of bearings. However, traditional DA methods tend to lose fine-grained information when aligning the domains globally. Moreover, most DA methods are not suitable for regression tasks, such as remaining useful life (RUL) prediction. This article proposes a deep subdomain adaptive regression network (DSARN), which can align the relevant subdomains in the source and target domains. This method has good cross-domain generalization ability and thus can be used for RUL prediction of bearings under multiple operating conditions. The proposed method takes the multichannel time-frequency representation (TFR) of bearings as the input and uses DSARN to extract the domain-invariant hidden representation and to establish a mapping to RUL. The effectiveness of the proposed method is verified by case studies on bearings. A comparison with other state-of-the-art deep learning (DL) and TL methods also proves the superiority of the proposed method.