An Adaptive Nonlinear Degradation Residual Life Prediction Method

Abstract

An adaptive nonlinear degradation remaining life prediction method, including: establishing a nonlinear degradation state space equation, and performing forward prediction based on equipment health indicators; obtaining the posteriori of the hidden variables in the nonlinear degradation state space equation according to the forward prediction results After estimation, an expectation-maximization algorithm is used to update the initial parameters and noise matrix in the nonlinear state space equation, and the updated parameters and a posteriori estimation results are substituted into the equation to obtain the overrun time. The difference between the overrun time and the current time The value is used as the predicted value of the remaining life; each time the newly collected equipment observation data is obtained, the above process is repeated, and the initial parameters and noise matrix in the equation are updated each time the new observation data is obtained, and the remaining life at the current moment is obtained Predictive value. The invention fully considers the individual difference, degradation randomness and measurement error in the non-linear degradation process of the equipment, and ensures a relatively high prediction accuracy of the remaining life.

Description

technical field [0001] The invention belongs to the field of equipment failure prediction and health management, in particular to an adaptive non-linear degradation remaining life prediction method. Background technique [0002] With the continuous deepening of industrialization and the development of information technology, equipment failure prediction and health management (Prognostics and health management) technology has become more and more prominent in its practicability and importance. Remaining life prediction is the core of equipment failure prediction and health management. Its prediction accuracy and algorithm robustness are of great significance to saving production costs and reducing safety accidents. Therefore, it has always been a research hotspot in the field of reliability engineering to carry out fault prediction and health management for important equipment, and then provide effective guidance for the safe production and operation and maintenance of enterp...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies in the prior art, the present invention provides an adaptive nonlinear degradation remaining life prediction method, which not only overcomes the prediction accuracy deviation and poor robustness caused by the traditional linearized remaining life prediction method problem, fully considering the factors such as individual differences, degradation randomness and measurement uncertainty in the nonlinear degradation process of the equipment, and explored a new Bayesian inference update paradigm based on nonlinear filtering technology, in order to improve equipment Nonlinear Degradation Remaining Life Prediction Accuracy Provides an Effective Tool

Images