Rail transit hardware equipment residual life prediction method, equipment and storage medium

Abstract

The invention provides a rail transit hardware equipment residual life prediction method, equipment and a storage medium. The method comprises the following steps: generating particles of hardware equipment at an initial moment; determining a state equation at a prediction moment from a pre-constructed multi-stage state change equation; based on the state equation at the prediction moment, determining a particle weight at the prediction moment; predicting a state value at the prediction moment according to the particle weight at the prediction moment and the state equation at the prediction moment; and determining residual life of the hardware equipment according to the state value at the prediction moment. According to the invention, the residual life of the hardware equipment is determined by the state equation at the prediction moment, and the state equation at the prediction moment is determined from the pre-constructed multi-stage state change equation, so that prediction of the residual life of the hardware equipment has the capability of evaluating multi-stage state changes, the applicability of the state equation at the prediction moment to current working conditions of the hardware equipment is ensured, and the problem that accuracy of prediction of service life of the hardware equipment under changing working conditions is low is solved.

Description

technical field [0001] The present application relates to the technical field of rail transit, and in particular to a method, device and storage medium for predicting the remaining life of rail transit hardware equipment. Background technique [0002] Aiming at the problem of low prediction accuracy of the remaining life of the hardware equipment of the rail transit signaling system during service, the existing scheme uses a statistical model to predict the remaining life of the hardware equipment. [0003] The method based on the remaining life prediction of the statistical model can establish a degradation model according to the degradation track of the product, and obtain the probability distribution of the remaining life of the system. Among them, the particle filter algorithm is suitable for the prediction of nonlinear stochastic process with noise, and it is a method widely used in statistical model methods. However, this method usually uses a fixed state equation, wh...

AI Technical Summary

Problems solved by technology

However, this method usually uses a fixed state equation, which cannot well evaluate the life of equipment in different states throughout the life cycle, which in turn affects the accuracy of life prediction results.

Images