Machinery degradation trend prediction considering temporal distribution discrepancy between degradation stages

Catering to the rapidly growing of smart manufacturing, recent years have witnessed that a great number of degradation trend prediction techniques were developed with the desire to guarantee the reliability and safety of machinery. Most existing studies assume that the future degradation trends follow similar data distributions to the degradation features fed for modeling, which may be challenging to satisfy in realistic scenarios. To address this issue, distribution discrepancy aligning-oriented domain adaptation was proposed. However, the stage-specific properties of the degradation process are often ignored, which may not be conducive. to maintain consistency in the distribution within the degradation stage and to evaluate the temporal distribution discrepancy in the degradation process. Therefore, this study presents a performance degradation trend prediction methodology that incorporates considerations of the temporal distribution discrepancy between degradation stages to overcome these challenges. Specifically, an adaptive degradation stage characterization (AdaDSC) strategy is designed to partition the degradation feature sequence into multiple degradation stages, ensuring that their distributions are as diverse as possible. Building upon this, a distribution discrepancy evaluation gated recurrent unit (DDE-GRU) module is introduced. It aims to mitigate the effects of distribution gaps while capturing the temporal dependencies within the data. The feasibility and effectiveness of the proposed methodology are verified through experiments conducted on three publicly available run-to-failure datasets, as well as an engineering dataset collected from the main bearing of a wind turbine. These experiments demonstrate the potential and practicality of the proposed methodology in accurately predicting performance degradation trends.