A Selective Adversarial Adaptation Network for Remaining Useful Life Prediction of Machines Under Different Working Conditions

Abstract

Deep neural networks have been widely applied in machinery health prognostics due to their powerful feature learning capacity. However, in many existing remaining useful life (RUL) prediction methods, the data distribution shift between multiple working conditions is ignored. In fact, there are inevitably certain differences between different working conditions. How to transfer knowledge to different but related domains for machine RUL prediction is not considered well. Thus, this article proposes a novel domain adaptation method named selective adversarial adaptation network (SAAN) for machine RUL prediction. A selective feature interaction is utilized in SAAN to implement knowledge selection, and the selective weights can be updated according to different data distribution. A new feature generator, residual convolutional long short-term memory is utilized for sequential information extraction from time-series input. Finally, two experiment on engine and bearing are utilized to validate the performance of SAAN for RUL prediction. The comparison results demonstrate that SAAN can implement knowledge transferring for machine RUL prediction.