Solving Time-dependent reliability-based design optimization by adaptive differential evolution algorithm and time-dependent polynomial chaos expansions (ADE-T-PCE)

被引：5

作者：

Ye, Xuerong ^{[1
]}

Chen, Hao ^{[1
]}

Kuang, Qiankun ^{[1
]}

Wang, Yue ^{[1
]}

Niu, Hao ^{[1
]}

Li, Wenwen ^{[2
]}

Yuan, Ruiming ^{[2
]}

Zhai, Guofu ^{[1
]}

机构：

[1] Harbin Inst Technol, Dept Elect Engn & Automat, Harbin, Peoples R China

[2] State Grid Jibei Mkt Serv Ctr, Metrol Ctr, Beijing, Peoples R China

来源：

MICROELECTRONICS RELIABILITY | 2020年 / 114卷 / 114期

基金：

中国国家自然科学基金;

关键词：

Pareto principle - Polynomials - Optimal systems - Reliability analysis - Time domain analysis - Least squares approximations - Evolutionary algorithms - Multiobjective optimization - Principal component analysis;

D O I：

10.1016/j.microrel.2020.113815

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

It remains a great many of challenge to explore time-dependent reliability-based design and optimization problems, owing to the high computational cost dependent reliability assessment and analysis, the difficulties to life-cycle reliability modelling. To address these issues, ADE-T-PCE, a methodology incorporating adaptive differential evolution algorithm and an enhanced instantaneous time-dependent polynomial chaos expansion is proposed. The polynomial chaos expression (PCE) method was improved based on time-domain extension and principal component selection partial least squares, the life-cycle reliability model is Consequently, dynamic niche Pareto optimal solution selection strategy, particle variations and optimal solution screening strategy, number and strategy of variation for the differential evolution algorithm were proposed to meet demands for multi-object time-dependent reliability design optimization. The effectiveness proposed method in this study was verified through an electromagnetic relay in hybrid vehicle.

引用

页数：6