Scholarlink

<p>To address the challenge of predicting the peak temperature and tensile strength of friction stir welded joints in 6061-T6 aluminum alloy, this paper presents a particle swarm optimization (PSO)-based support vector regression (SVR) optimization approach. A corresponding prediction model, namely PSO-SVR, is established for these two parameters. A comparative analysis is also conducted with other models including back propagation (BP), particle swarm optimization-back propagation (PSO-BP) and grid search-support vector regression (GS-SVR). Results demonstrate that the PSO-SVR model shows a remarkable superiority over BP, PSO-BP and GS-SVR models in handling both peak temperature and tensile strength data sets. Compared to the other models, PSO-SVR delivers higher precision accuracy. It is capable of accurately predicting the peak temperature and tensile strength of 6061-T6 aluminum alloy friction stir welded joints even when faced with limited data sets.</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

Prediction of Peak Temperature and Tensile Strength of 6061-T6 Aluminum Alloy Friction Stir Welded Joints Based on PSO-Optimized SVR

  • 期刊论文

  • 发表日期：

    2026年2月25日

查看全文
  • Shuo Yang,
  • Mengqi Cong,
  • Yang Zhang,
  • Xiaorui Zheng,
  • Hailin Chen,
  • Mingyu Wei

摘要

To address the challenge of predicting the peak temperature and tensile strength of friction stir welded joints in 6061-T6 aluminum alloy, this paper presents a particle swarm optimization (PSO)-based support vector regression (SVR) optimization approach. A corresponding prediction model, namely PSO-SVR, is established for these two parameters. A comparative analysis is also conducted with other models including back propagation (BP), particle swarm optimization-back propagation (PSO-BP) and grid search-support vector regression (GS-SVR). Results demonstrate that the PSO-SVR model shows a remarkable superiority over BP, PSO-BP and GS-SVR models in handling both peak temperature and tensile strength data sets. Compared to the other models, PSO-SVR delivers higher precision accuracy. It is capable of accurately predicting the peak temperature and tensile strength of 6061-T6 aluminum alloy friction stir welded joints even when faced with limited data sets.