Residual life prediction algorithm based on optimal degradation characteristic quantity

Abstract

The invention discloses a residual life prediction algorithm based on optimal degradation characteristic quantity. The residual life prediction algorithm comprises the steps of extracting the optimal degradation characteristic quantity of equipment and establishing a Weiner process residual life prediction model with a random effect. Compared with the prior art, the residual life prediction algorithm solves the problem of choosing degradation characteristic quantity in a man-made subjective mode and overcomes the bad effect that a single degradation characteristic quantity cannot completely represent equipment states. According to the residual life prediction algorithm, the merits and demerits of a genetic programming algorithm and the Weiner process model with the random effect are combined, and an optimal first prediction time can be chosen; thus, the residual life prediction algorithm based on the optimal degradation characteristic quantity can be established. From simulation results, the prediction accuracy of the algorithm is certainly improved.

Description

technical field [0001] The invention relates to a remaining life prediction algorithm combined with a genetic programming algorithm and a random Weiner process, in particular to a remaining life prediction algorithm based on optimal degradation characteristic quantities. Background technique [0002] The existing remaining life prediction technology obtains degradation data by monitoring key characteristic parameters in the process of equipment performance degradation, and then uses the degradation data to predict the remaining life of equipment and determine equipment maintenance strategies. However, the current remaining life research work basically selects the degradation characteristic quantity subjectively. In order to effectively solve this problem, in recent years, L.X. Liao proposed a method of using genetic programming to construct the optimal degraded feature, and using the paris equation to simulate the bearing expansion process, but this method does not consider ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the current problem of subjectively selecting degradation feature quantities, and the selected degradation feature quantities are all single degradation indicators, a single degradation index contains limited information on equipment degradation, and cannot fully reflect the full-life operating characteristics of equipment. Therefore, the present invention considers using The genetic programming algorithm extracts the optimal degradation feature quantity in the degradation process of the equipment, and uses the optimal degradation feature quantity that synthesizes multiple degradation feature quantities to comprehensively describe the operating state and degradation trend of the equipment. Specifically, the present invention will use the time domain The dimensionless index in , determines the time when the early failure of the equipment occurs, that is, the first prediction time FPT, uses the data after the early failure of the equipment to construct the optimal degradation feature quantity, and introduces the first prediction time into the genetic programming algorithm, which can greatly improve the Reduce the amount of data, and it is easy to construct the optimal degraded feature quantity

Images