关键词: 实时, 剩余寿命, 预测, 长期平均费用率, 非完美, 预防性维护维修

Abstract: The accurate prediction of the Remaining Useful Life (RUL) is the key for the equipment's preventive maintanance decision.Based on present moment and history monitoring information,a real-time remaining useful life prediction model was established by using stochastic filtering theory under the imperfect preventive maintenance strategies.A maintenance strategy of imperfect preventive maintenance and replacement strategy by taking average remaining useful life as threshold was proposed,and an optimization model was established to choose the threshold of preventive maintenance as optimal variable and the minimum average maintenance cost as object function.Particle Swarm Optimization (PSO) algorithm was used to solve the model,which could obtain the best preventive maintenance and preventive replacement threshold,and make the long-run average cost rate lowest.The fatigue cracking which accorded with Weibull distribution was taken as the example to verify the feasibility of proposed methods.

Key words: real-time, remaining useful life, prediction, long-run average cost rate, imperfect, preventive maintenance