Method for predicting service lives in consideration of long-range correlation and uncertainty of components

Abstract

The invention discloses a method for predicting service lives in consideration of long-range correlation and uncertainty of components, and belongs to the field of prediction and prediction of residual service lives in health management. The method includes steps of reading state monitoring degradation data and initializing model parameters for specified drift structures (such as exponential functions, power functions and linear functions); estimating unknown parameters of models by the aid of maximum likelihood algorithms; carrying out approximation on obtained degradation processes on the basis of weak convergence criteria and computing probability density functions of residual service lives; judging fitting effects and the prediction ability of the models by the aid of AIC (akaike information criteria) and mean-square errors. Compared with existing methods, the method has the advantages of high universality and prediction precision.

Description

technical field [0001] The invention belongs to the field of remaining life prediction in prediction and health management, and in particular relates to a life prediction method considering long-range correlation and component uncertainty. Background technique [0002] For actual industrial systems, remaining life prediction is an important technology to effectively reduce maintenance costs. Based on condition monitoring data, the core of remaining life prediction technology is to estimate the probability density function of the time from the degradation process to the first reaching the predetermined failure threshold. High-precision remaining life prediction method is the theoretical basis in the field of predictive maintenance. [0003] At present, the remaining life prediction algorithms proposed by domestic and foreign scholars in the field of prediction and health management can be divided into two types based on direct monitoring data and based on indirect monitoring ...

AI Technical Summary

Problems solved by technology

However, Brownian motion is actually a Markov process, i.e. memory effects are completely ignored

Still taking the blast furnace temperature as an example, the complex heat conduction in the furnace greatly affects the temperature measurement, making the temperature degradation non-stationary and correlated

[0006] Obviously, the existing degradation modeling and remaining life prediction algorithms based on monitoring data cannot describe non-Markovian processes with memory effects

In addition, considering some practical factors, such as the influence of environment and operating conditions, there may be certain differences between each device

Images