Scholarlink

<p>Wire Electrical Discharge Machining (WEDM) efficiency on aluminum alloys is highly dependent on the optimization of processing conditions to achieve high productivity and superior surface integrity. This research implements an integrated framework combining a Modified Taguchi Design of Experiments (DoE) with Artificial Intelligence (AI) to optimize the machining of Al6068 alloy. The study evaluates the influence of pulse-on time, pulse-off time, servo voltage, and servo feed rate on performance. Analysis of Variance (ANOVA) indicates that servo feed is the most significant factor, contributing 68.9% to the Material Removal Rate (MRR) and 52.5% to the Surface Roughness (Ra). The results demonstrate that maximum MRR (8.16&#xa0;mm<sup>3</sup>/min) and minimum Ra (1.21&#xa0;μm) can be achieved through targeted parameter sets, while a multi-objective configuration yielded balanced performance (MRR: 5.77&#xa0;mm<sup>3</sup>/min, Ra: 1.70&#xa0;μm). Scanning Electron Microscopy (SEM) and microhardness analysis confirmed that the optimized settings significantly enhanced surface morphology and minimized the thickness of the recast layer. To capture the nonlinear dynamics of the process, a Random Forest Regression (RFR) model was developed and validated, achieving an <i>R</i><sup>2</sup> of 0.999. The RFR model was coupled with a Genetic Algorithm (GA) to identify optimal parameters, which yielded MRR: 6.768&#xa0;mm<sup>3</sup>/min, Ra: 1.823&#xa0;μm. Though the output responses are higher than those from the modified Taguchi approach, this hybrid approach provides a robust methodology for precision machining of Al6068 alloys.</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

Multi-Objective Optimization of WEDM of AA6068 Alloy for Metal Forming Tooling Using an Integrated Modified Taguchi Approach

  • 期刊论文

  • 发表日期：

    2026年7月17日

查看全文
  • Ramatenki Chinna,
  • Boggarapu Nageswara Rao,
  • Tanya Buddi

摘要

Wire Electrical Discharge Machining (WEDM) efficiency on aluminum alloys is highly dependent on the optimization of processing conditions to achieve high productivity and superior surface integrity. This research implements an integrated framework combining a Modified Taguchi Design of Experiments (DoE) with Artificial Intelligence (AI) to optimize the machining of Al6068 alloy. The study evaluates the influence of pulse-on time, pulse-off time, servo voltage, and servo feed rate on performance. Analysis of Variance (ANOVA) indicates that servo feed is the most significant factor, contributing 68.9% to the Material Removal Rate (MRR) and 52.5% to the Surface Roughness (Ra). The results demonstrate that maximum MRR (8.16 mm3/min) and minimum Ra (1.21 μm) can be achieved through targeted parameter sets, while a multi-objective configuration yielded balanced performance (MRR: 5.77 mm3/min, Ra: 1.70 μm). Scanning Electron Microscopy (SEM) and microhardness analysis confirmed that the optimized settings significantly enhanced surface morphology and minimized the thickness of the recast layer. To capture the nonlinear dynamics of the process, a Random Forest Regression (RFR) model was developed and validated, achieving an R2 of 0.999. The RFR model was coupled with a Genetic Algorithm (GA) to identify optimal parameters, which yielded MRR: 6.768 mm3/min, Ra: 1.823 μm. Though the output responses are higher than those from the modified Taguchi approach, this hybrid approach provides a robust methodology for precision machining of Al6068 alloys.