Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Device residual life prediction method based on multi-hidden state fractional Brownian motion

A Brownian motion, hidden state technology, applied in electrical digital data processing, computer-aided design, design optimization/simulation, etc., can solve the problems of low accuracy of equipment life prediction, only considering the current observation value, etc., to improve life prediction. Accurate, model-flexible effects

Active Publication Date: 2018-11-16
SICHUAN UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method for predicting the remaining life of equipment based on multi-hidden state fractional Brownian motion. The problem of low precision

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Device residual life prediction method based on multi-hidden state fractional Brownian motion
  • Device residual life prediction method based on multi-hidden state fractional Brownian motion
  • Device residual life prediction method based on multi-hidden state fractional Brownian motion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041]The embodiment takes lithium-ion batteries as an example, and provides a method for predicting the remaining life of equipment based on multi-hidden state fractional Brownian motion. The specific steps are as follows:

[0042] Step 1: Select the nonlinear function according to the life degradation trend of the equipment, and determine the nonlinear fractional Brownian motion model of the nonlinear function, and regard the parameters in the nonlinear function as unobservable state variables, and the unobservable state variables are hidden state.

[0043] This step uses the empirical degradation function of the lithium battery as a nonlinear function in the nonlinear fractional Brownian motion model. The chosen nonlinear function is:

[0044] μ(τ;θ)=a·b·exp(bτ)+c·d·exp(dτ)

[0045] Among them, τ is a variable in the nonlinear function, and a, b, c and d are parameters in the nonlinear function;

[0046] The above nonlinear fractional Brownian motion model is:

[0047] ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of life prediction of electromechanical equipment, and discloses a device residual life prediction method based on multi-hidden state fractional Brownian motion, which solves the problem that only the current observation value is taken into account in the prior residual life prediction method based on fractional Brownian motion, the device life prediction precision is low. Firstly, a nonlinear function is selected according to the life degradation trend of the device, a nonlinear fractional Brownian motion model is determined, and the parameter in the nonlinear function is taken as a hidden state; the nonlinear fractional Brownian motion model is converted into the nonlinear Brownian motion model; then, curve fitting is carried out on the training data toobtain an initial value of the hidden state mean value; then iteration is carried out to update the mean value and variance of the hidden state to obtain a distribution function of the hidden state;then the posterior probability density distribution of a first impact time is deduced; Finally, the posterior probability density distribution of the first impact time is used for life prediction. Themethod is applicable to the prediction of residual effective service life of the electromechanical equipment.

Description

technical field [0001] The invention relates to the field of life prediction of electromechanical equipment, in particular to a method for predicting remaining life of equipment based on multi-hidden state fractional Brownian motion. Background technique [0002] With the rapid development of modern technology and industrial technology and the continuous improvement of functional requirements, a large number of electromechanical equipment has gradually shown a trend of complexity, integration and intelligence. These trends urgently require the improvement of health management capabilities and reliability of electromechanical equipment. Electromechanical equipment has inevitable performance degradation during operation. When the performance of the equipment degrades to the point that the equipment is not enough to complete its function, it will lead to equipment downtime or even failure, resulting in huge economic losses and even casualties. Accurately predicting the remaini...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/50
CPCG06F30/20G06F2119/04
Inventor 苗强张恒张新王剑宇莫贞凌刘慧宇曾小飞王俊峰
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products