Scholarlink

<p>In recent years, meta-heuristic (MH) algorithms have emerged as powerful optimization tools, enabling efficient solutions to complex truss optimization tasks. In this study, a performance assessment of eight newly developed MH algorithms is presented for the optimal design of large-scale truss structures. The algorithms selected for testing include the Manta-ray Foraging Optimization&#xa0;(MRFO), Artificial Gorilla Troops Optimizer&#xa0;(GTO), Equilibrium Optimizer&#xa0;(EO), Henry Gas Solubility Optimizer (HGSO), Aquila Optimizer (AO), Heap-based Optimizer (HBO), Snake Optimizer&#xa0;(SO), and Artificial Hummingbird Algorithm&#xa0;(AHA). Collectively, the eight techniques cover recent advances in nature-inspired MH approaches and use diverse search mechanisms for their optimization procedure. To effectively compare the performance of the eight techniques, five large-scale truss benchmarks (including the 4666-bar truss tower) were employed as test beds. For statistical significance, the Friedman ranking test was used to quantitatively compare the performance of the eight techniques. The results of the comparison show HBO as the best-performing method by consistently providing the lightest truss designs with the least computational effort. Quantitatively, HBO produced structures that were (on average) 21% lighter than the other seven techniques. In contrast, both AO and HGSO suffered from poor results and slow convergence speeds. HGSO in particular emerged as the worst-performing method and was prone to falling into local optima. In light of this, recommendations for improving the optimization performance for the eight techniques were made within the article.</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

A performance comparison of eight meta-heuristic algorithms for the optimal design of large-scale truss structures

  • 期刊论文

  • 发表日期：

    2025年2月12日

查看全文
  • Rafiq Bodalal

摘要

In recent years, meta-heuristic (MH) algorithms have emerged as powerful optimization tools, enabling efficient solutions to complex truss optimization tasks. In this study, a performance assessment of eight newly developed MH algorithms is presented for the optimal design of large-scale truss structures. The algorithms selected for testing include the Manta-ray Foraging Optimization (MRFO), Artificial Gorilla Troops Optimizer (GTO), Equilibrium Optimizer (EO), Henry Gas Solubility Optimizer (HGSO), Aquila Optimizer (AO), Heap-based Optimizer (HBO), Snake Optimizer (SO), and Artificial Hummingbird Algorithm (AHA). Collectively, the eight techniques cover recent advances in nature-inspired MH approaches and use diverse search mechanisms for their optimization procedure. To effectively compare the performance of the eight techniques, five large-scale truss benchmarks (including the 4666-bar truss tower) were employed as test beds. For statistical significance, the Friedman ranking test was used to quantitatively compare the performance of the eight techniques. The results of the comparison show HBO as the best-performing method by consistently providing the lightest truss designs with the least computational effort. Quantitatively, HBO produced structures that were (on average) 21% lighter than the other seven techniques. In contrast, both AO and HGSO suffered from poor results and slow convergence speeds. HGSO in particular emerged as the worst-performing method and was prone to falling into local optima. In light of this, recommendations for improving the optimization performance for the eight techniques were made within the article.