Life prediction method of accelerated life test based on grey RBF neural network

An accelerated life test and neural network technology, applied in the field of accelerated life test evaluation, can solve problems such as difficulty in establishing accelerated models and solving multivariate likelihood equations, large prediction errors, loss of empirical data, etc., so as to facilitate practical engineering applications and avoid Effects of systematic error and life prediction accuracy improvement

Inactive Publication Date: 2009-11-11
BEIHANG UNIV
View PDF0 Cites 50 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0025] The purpose of the present invention is to solve the practical problem that the life estimation method in the traditional accelerated life test has difficulty in establishing an accelerated model and solving the multiple likelihood equations, and solve the missing part of the empirical data in the existing life prediction method based on BP neural network , the problem of large prediction error, on the basis of absorbing the respective prediction advantages of gray system theory and radial basis function (RBF) neural network, using the principle of gray accumulation generating operation (AGO) to process neural network training data, forming a set based on A Method of Life Prediction in Constant Stress Accelerated Life Test Based on Gray RBF Neural Network

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
  • Life prediction method of accelerated life test based on grey RBF neural network
  • Life prediction method of accelerated life test based on grey RBF neural network
  • Life prediction method of accelerated life test based on grey RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] The method in this embodiment uses a Monte Carlo simulation method to verify its correctness. Assume that the lifetime of a product follows a two-parameter Weibull distribution:

[0082] F(t)=1-exp{(t / η) m}, t≥0

[0083] Among them, m is the shape parameter, because it is assumed that the failure mechanism of the product remains unchanged in the accelerated life test, so m does not change with the change of stress and is a constant. η is the characteristic life, this paper considers that the product is only affected by temperature and one kind of stress, and it satisfies the Arronis theorem:

[0084] η=A·exp(E / k·T)

[0085] Where A is a constant; E is activation energy, unit eV; k is Boltzmann's constant, k=8.6171×10 -5 eV / K; T is the thermodynamic temperature in K. Then, the simulation model is:

[0086] F(t)=1-exp{[t / A·exp(E / k·T)] m}, t≥0

[0087] The parameter values ​​are shown in Table 1:

[0088] Table 1: Simulation parameter values

[0089] par...

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 discloses a life prediction method of accelerated life test based on grey RBF neural network. An original curve of reliability and failure time is constructed by collecting test data; class ratio test is conducted on failure time data; a curve of reliability and accumulated failure time is constructed; three layers of RBF artificial neural network are established; RBF artificial neural network is trained; the well-trained neural network is used for prediction; and finally the prediction value of the dummy accumulated failure time obtained by prediction is reduced so as to obtain the life information of the products under normal stress. The method has no need of establishing physical accelerator model and resolving complex multivariate likelihood equation set, thereby avoiding the introduction of system error in the life prediction, solving the problem of needing a large number of training samples for artificial neural network modeling in accelerated life test, also being applied to small sample test data, and facilitating the application in actual engineering. Compared with the existing BP neural network prediction method, the life prediction precision is obviously improved.

Description

technical field [0001] The invention relates to a life prediction method in an accelerated life test, belonging to the technical field of accelerated life test evaluation. Background technique [0002] With the continuous improvement of product reliability level, life evaluation is facing a long-life and high-reliability product evaluation topic. If the evaluation is carried out according to the traditional life test technology, the time and cost will be unbearable, and the product will be eliminated due to backward performance before the life test is even completed. In addition, due to the rapid development of science and technology, the speed of product replacement is getting faster and faster. People urgently need to obtain product life information in a short period of time. Accelerated life test technology applies stress in a targeted manner according to the failure mechanism of the product. , will greatly improve the cost-effectiveness ratio of the reliability verifica...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01M19/00G06N3/02G06N3/10G01M99/00
Inventor 李树桢李晓阳姜同敏
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap