Scholarlink

<p>The performance of magnesium-based composites fabricated through Friction Stir Processing (FSP) is highly dependent on the precise optimization of input process parameters. This study leverages advanced hybrid statistical optimization techniques to enhance the tensile strength of magnesium-based metal matrix composites (MMMCs). Fly ash (FA) was incorporated into an AZ31B magnesium alloy substrate to develop the composite, with FSP conducted under varying tool rotation speeds (TRS: 850–1650&#xa0;rpm), tool traverse speeds (TS: 25–45&#xa0;mm/min), and the number of FSP passes (NP: 2–4). To optimize these parameters and their influence on tensile strength, hybrid approaches such as Genetic Algorithm-Artificial Neural Network (GA-ANN) and Genetic Algorithm-Adaptive Neuro-Fuzzy Inference System (GA-ANFIS) were employed. Among the techniques, GA-ANN demonstrated superior accuracy of 98.50%, identifying optimized parameters of TRS 1512.8&#xa0;rpm, TS 39.1&#xa0;mm/min, and NP 4, achieving a maximum tensile strength of 330.62&#xa0;MPa. This work underscores the efficacy of hybrid algorithmic techniques in optimizing FSP parameters, paving the way for advancements in composite material performance.</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

Hybrid algorithmic techniques for optimizing tensile strength in magnesium-based composites developed via friction stir processing

  • 期刊论文

  • 发表日期：

    2025年1月20日

查看全文
  • Prem Sagar,
  • Sonia Rani,
  • Mukesh Kumar,
  • M. Ashokkumar

摘要

The performance of magnesium-based composites fabricated through Friction Stir Processing (FSP) is highly dependent on the precise optimization of input process parameters. This study leverages advanced hybrid statistical optimization techniques to enhance the tensile strength of magnesium-based metal matrix composites (MMMCs). Fly ash (FA) was incorporated into an AZ31B magnesium alloy substrate to develop the composite, with FSP conducted under varying tool rotation speeds (TRS: 850–1650 rpm), tool traverse speeds (TS: 25–45 mm/min), and the number of FSP passes (NP: 2–4). To optimize these parameters and their influence on tensile strength, hybrid approaches such as Genetic Algorithm-Artificial Neural Network (GA-ANN) and Genetic Algorithm-Adaptive Neuro-Fuzzy Inference System (GA-ANFIS) were employed. Among the techniques, GA-ANN demonstrated superior accuracy of 98.50%, identifying optimized parameters of TRS 1512.8 rpm, TS 39.1 mm/min, and NP 4, achieving a maximum tensile strength of 330.62 MPa. This work underscores the efficacy of hybrid algorithmic techniques in optimizing FSP parameters, paving the way for advancements in composite material performance.