Degradation model consistency testing method catering to space shapes and error ranges

Abstract

The invention discloses a degradation model consistency testing method catering to space shapes and error ranges. The method includes the following steps that firstly, a product degradation model is selected; secondly, test data are analyzed and processed, wherein the test data are m data series {y[i](t), t=1,2,...,N, i=1,2,...,m} of performance parameters and time of m products under a constant-stress level; thirdly, a simulation test data series of the product degradation model is acquired under the stress level in the form of {x(t), t=1,2,...,N} according to the stress level of the test data and the degradation model; fourthly, error range consistency testing is carried out based on normal populations; fifthly, space shape similarity consistence testing is carried out based on grey correlation; sixthly, whether a degradation model caters to error range consistency testing based on the normal populations and space shape similarity consistency testing based on grey correlation or not is judged, if yes, the degradation model passes consistency testing, and otherwise the degradation model does not pass consistency testing. The degradation model consistency testing method overcomes the defect that only model error ranges are considered in existing methods and is easy and convenient to implement and wide in application range.

Description

technical field [0001] The invention proposes a method for checking the consistency of a degradation model oriented to space shape and error range, and belongs to the technical field of reliability of degradation modeling. Background technique [0002] With the improvement of product reliability and service life, a large number of non-failure products appear. The traditional reliability evaluation method model based on failure data has been difficult to meet the requirements of engineering evaluation. In order to solve such problems, degradation data is introduced into the field of reliability evaluation. , establishing a degradation model through degradation data has become an important way to solve the reliability evaluation problem of high reliability and long life products. [0003] However, the consistency test of the degradation model has become an urgent problem to be solved at present. The existing consistency test methods of the degradation model are mainly consider...

AI Technical Summary

Problems solved by technology

[0002] With the improvement of product reliability and service life, a large number of non-failure products appear. The traditional reliability evaluation method model based on failure data has been difficult to meet the requirements of engineering evaluation. In order to solve such problems, degradation data is introduced into the field of reliability evaluation. , establishing a degradation model through degradation data has become an important way to solve the reliability evaluation problem of high reliability and long life products

[0003] However, the consistency test of the degradation model has become an urgent problem to be solved at present. The existing consistency test methods of the degradation model are mainly considered from the perspective of the error range, and the consistency test method of the degradation model has not been considered from other factors. Even combining several factors together to improve the consistency test method of the degradation model, the existing methods effectively examine the error range of the degradation model, but fail to reflect the change process and law of the degradation model

Images