Single Machine Remaining Life Prediction Method Fused with Life Data and Performance Degradation Data

Abstract

The present invention discloses a stand-alone residual life prediction method for integrating life data and performance degradation data, and relates to the field of product residual life prediction. The method comprises the following steps: (S1) initializing the drift parameter mu and the diffusion parameter sigma; (S2) updating the drift parameter mu and the diffusion parameter sigma; (S3) carrying out Gibbs sampling numerical simulation to solve the parameter estimation value; and (S4) carrying out residual life prediction based on the degradation process. The purpose of the present invention is providing a method, and when a component performance degradation process can be taken as a linear drift Wiener process, the method can be used for integrating life data and performance degradation data, estimating distribution parameters of the component residual life, and further estimating the product residual life, so that the problem of residual life prediction of the complex product with high reliability, long life and small sample is solved, and real-time updating of parameters is realized.

Description

technical field [0001] The invention belongs to the field of product remaining life prediction, and in particular relates to a real-time update remaining life prediction method that integrates no-failure timing censored life data, minimal failure life data and performance degradation data. Background technique [0002] Generally, the remaining life of a product (Residual Life, RL) refers to the time length between the current moment and the failure of the product. For products in the use stage, from the perspective of reliability management, it is often necessary to pay attention to how long the product can continue to run without failing at the current moment. Based on the results of the remaining life prediction, combined with the product maintenance support plan, the decision-making on product monitoring, maintenance and replacement can be optimized to avoid the problems of "excessive maintenance" / "insufficient maintenance" or "redundant replacement" / "under-replacement". ...

AI Technical Summary

Problems solved by technology

[0063] At present, most remaining life prediction methods that integrate multi-source information are based on failure life data, but most of the current satellite platform stand-alone life data are censored life data without failure timing, and a very small part of life data is failure life data.

Images