Research Progress on Data Driven-based RUL Prediction Methods of Mechanical Equipment

With the development of the industry, the performance of large and complex systems is constantly increasing and the complexity is increasing. In the process of using mechanical equipment, there is often a phenomenon of downtime and the most of the reasons is that the related parts are faulty. As one of the foremost tasks of prognostic and health management (PHM) and condition based maintenance (CBM), the prediction of remaining useful life (RUL) for mechanical equipment is receiving more and more attention. By knowing the RUL of the equipment, it can play an important role in maintaining related equipment in advance. It is more effective than the traditional regular maintenance and post-repair maintenance, thus avoiding the occurrence of malfunctions and the reduction of property loss. This paper focuses on the AI-based RUL prediction methods and explains the strengths and weaknesses of each of these methods and summarizes the latest literature on various methods in the last few years. Finally, the present methods and future trends are discussed and hot spots for the future are given.