Scholarlink

<p>Sustainable machining of 17-4 PH steel is essential for minimizing environmental impact while ensuring product quality. This study presents a novel hybrid Artificial Neural Network–Genetic Algorithm (ANN-GA) framework designed to optimize CNC turning parameters, utilizing rice bran oil mixed with Al<sub>2</sub>O<sub>3</sub> nanoparticles as a sustainable coolant. To reduce experimental trials, Taguchi’s L<sub>9</sub> orthogonal array was used, focusing on controllable factors such as speed, feed, depth of cut, and coolant flow. The ANN-GA model demonstrated a 15% reduction in root mean square error (0.00255 compared to 0.003) and an 82% decrease in prediction errors compared to the baseline ANN, significantly improving Ra prediction accuracy. The feed rate and rice bran oil contributed 58.06% and 49.5% to Ra, respectively. Confirmation tests verified the optimal parameters (speed = 102&#xa0;m/min, feed = 0.1&#xa0;mm/rev, depth = 0.4&#xa0;mm, oil flow = 150&#xa0;ml/min), achieving a Ra measurement below 1.2&#xa0;μm, assuring excellent surface quality in all experiments. In comparison to traditional procedures, this strategy extended tool life by 25% and decreased material waste by 20% through fewer experimental trials. Sustainable manufacturing uses precise and eco-friendly solutions for machining difficult-to-cut materials that are provided by the combination of cutting-edge AI and sustainable cooling techniques.</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

Performance Evaluation of Machining Parameters in Turning Operations of 17-4 PH Steel Using Hybrid ANN-GA and Nano Cutting Fluids

  • 期刊论文

  • 发表日期：

    2025年12月23日

查看全文
  • Vivek John,
  • Vinny John,
  • Nitin Kumar,
  • Hemenkumar H Thakar,
  • Abhijit Bhowmik,
  • Ajay Kumar,
  • Kaushal Kumar,
  • Jeewan Singh

摘要

Sustainable machining of 17-4 PH steel is essential for minimizing environmental impact while ensuring product quality. This study presents a novel hybrid Artificial Neural Network–Genetic Algorithm (ANN-GA) framework designed to optimize CNC turning parameters, utilizing rice bran oil mixed with Al2O3 nanoparticles as a sustainable coolant. To reduce experimental trials, Taguchi’s L9 orthogonal array was used, focusing on controllable factors such as speed, feed, depth of cut, and coolant flow. The ANN-GA model demonstrated a 15% reduction in root mean square error (0.00255 compared to 0.003) and an 82% decrease in prediction errors compared to the baseline ANN, significantly improving Ra prediction accuracy. The feed rate and rice bran oil contributed 58.06% and 49.5% to Ra, respectively. Confirmation tests verified the optimal parameters (speed = 102 m/min, feed = 0.1 mm/rev, depth = 0.4 mm, oil flow = 150 ml/min), achieving a Ra measurement below 1.2 μm, assuring excellent surface quality in all experiments. In comparison to traditional procedures, this strategy extended tool life by 25% and decreased material waste by 20% through fewer experimental trials. Sustainable manufacturing uses precise and eco-friendly solutions for machining difficult-to-cut materials that are provided by the combination of cutting-edge AI and sustainable cooling techniques.