Scholarlink

Abstract <p>This article presents an optimization approach utilizing the Covariance Matrix Adaptation Evolution Strategy algorithm (CMA-ES) for the optimal design of truss structures with discrete variables under various loading conditions. The model uses CMA-ES to optimize design variables, specifically the cross-sectional areas of the truss bars. Evaluation data are generated by testing different cross-sectional configurations through structural analysis of the trusses, with the aim of minimizing the mass of the structure while respecting stress and displacement limits. CMA-ES is then employed to efficiently navigate the design space and identify the optimal configuration. This method was applied to three planar and spatial truss examples, with results compared to literature studies to validate the approach’s effectiveness and robustness. The optimization results highlight the exceptional performance of the CMA-ES algorithm in achieving optimal solutions and demonstrating efficient convergence behavior.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Covariance Matrix Adaptation Evolution Strategy for Optimizing Truss Structures with Discrete Variables

  • 期刊论文

  • 发表日期：

    2025年4月1日

查看全文
  • O. El Mrimar,
  • Z. El Haddad,
  • O. Bendaou,
  • B. Samoudi

摘要

Abstract

This article presents an optimization approach utilizing the Covariance Matrix Adaptation Evolution Strategy algorithm (CMA-ES) for the optimal design of truss structures with discrete variables under various loading conditions. The model uses CMA-ES to optimize design variables, specifically the cross-sectional areas of the truss bars. Evaluation data are generated by testing different cross-sectional configurations through structural analysis of the trusses, with the aim of minimizing the mass of the structure while respecting stress and displacement limits. CMA-ES is then employed to efficiently navigate the design space and identify the optimal configuration. This method was applied to three planar and spatial truss examples, with results compared to literature studies to validate the approach’s effectiveness and robustness. The optimization results highlight the exceptional performance of the CMA-ES algorithm in achieving optimal solutions and demonstrating efficient convergence behavior.