Modeling method of accelerated degradation information fusion based on uncertain data envelopment analysis

Abstract

The invention discloses a modeling method of accelerated degradation information fusion based on uncertain data envelopment analysis. The method comprises the following steps of: 1, collecting all available degradation data obtained by the product ADT and perform data preprocessing; 2, performing accelerated degradation modeling to obtain a confident reliability distribution of a single data source; 3, evaluating the ADT data source and determine the evaluation index; 4, performing uncertain DEA modeling to determine the relative efficiency of each ADT data source; 5, assessing and predictingthe life and reliability of the product. Through the above steps, the multi-source ADT data can be fused to conduct comprehensive reliability evaluation of products, which can reduce the cognitive uncertainty and improve the reliability and life evaluation accuracy of products. In the field of current ADT reliability evaluation, the lack of overall product information recognition caused by small samples and the inadequate use of multi-source ADT data sources are solved.

Description

technical field [0001] The present invention proposes an accelerated degradation information fusion modeling method based on uncertain data envelope analysis, that is, an accelerated degradation information fusion modeling method based on the same stress type of uncertain DEA, which involves a The accelerated degradation data information fusion modeling method of network analysis belongs to the technical field of accelerated degradation test and is used to solve technical problems in the field of reliability and system engineering. Background technique [0002] With the increasing demand for long life and high reliability of products in modern industry, accelerated degradation tests (Accelerated degradation test, ADT) are widely carried out to assess the life and reliability of products before the products are officially put into production. ADT technology uses harsh test conditions to accelerate product performance degradation, and obtain relatively rich failure or degradat...

AI Technical Summary

Problems solved by technology

[0010] In the current ADT modeling method, the lack of cognition of overall product information due to small samples, and the problem that multi-source ADT data sources cannot be fully utilized, the present invention proposes an accelerated degradation method based on uncertain data envelopment analysis Data information fusion modeling method, that is, an accelerated degradation information fusion modeling method based on uncertain DEA of the same stress type, this method first performs accelerated degradation based on an uncertain process for each collected ADT data source of the same stress type Modeling to obtain the corresponding certainty and reliability distribution model; then, establish an ADT data source index evaluation system, use the uncertain DEA method to obtain the relative efficiency of each data source, obtain the corresponding weight of each data source, and use weighted fusion The method fuses multiple ADT data sources to give the certainty and reliability distribution of the product

Images