Scholarlink

<p>Sustainability in machining is a critical aspect of modern manufacturing, aimed at reducing the environmental impact of production processes while ensuring economic and social benefits. This study investigates the machinability of Ti6Al4V alloy for optimal machining power requirement and optimization of minimum quantity lubrication (MQL) machining using advanced machine learning techniques. The primary objective is to minimize the machining power, a critical factor in manufacturing high-strength alloys. Two machine learning-based regression models—namely support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS)—are employed to predict machining power based on input parameters such as cutting speed (<i>v</i>), feed rate (<i>f</i>), and depth of cut (<i>d</i>). The predictive capability of the models was to assess their predictive accuracy and generalization capability. The process is optimized using a popular teaching–learning-based optimization (TLBO) algorithm to obtain the best combination of process parameters to minimize the machining power. The algorithm yielded a minimum machining power of 334.24&#xa0;W for 71.16&#xa0;m/min cutting speed, 0.056&#xa0;mm/rev feed, and 0.2&#xa0;mm depth of cut. The evolutionary optimization framework successfully identifies optimal parameter settings, substantially improving energy efficiency and machining performance. Further, microstructural studies of chips and confirmation tests were conducted to validate the optimum process parameters.</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

Intelligent Machine Learning Strategies for Minimizing Machining Power in Minimum Quantity Lubrication Machining of Ti6Al4V Alloy

  • 期刊论文

  • 发表日期：

    2025年3月20日

查看全文
  • Dhrubajit Sarma,
  • Rupshree Ozah,
  • Jyotisman Borah,
  • Muthumari Chandrasekaran,
  • Ashok Kumar Sahoo

摘要

Sustainability in machining is a critical aspect of modern manufacturing, aimed at reducing the environmental impact of production processes while ensuring economic and social benefits. This study investigates the machinability of Ti6Al4V alloy for optimal machining power requirement and optimization of minimum quantity lubrication (MQL) machining using advanced machine learning techniques. The primary objective is to minimize the machining power, a critical factor in manufacturing high-strength alloys. Two machine learning-based regression models—namely support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS)—are employed to predict machining power based on input parameters such as cutting speed (v), feed rate (f), and depth of cut (d). The predictive capability of the models was to assess their predictive accuracy and generalization capability. The process is optimized using a popular teaching–learning-based optimization (TLBO) algorithm to obtain the best combination of process parameters to minimize the machining power. The algorithm yielded a minimum machining power of 334.24 W for 71.16 m/min cutting speed, 0.056 mm/rev feed, and 0.2 mm depth of cut. The evolutionary optimization framework successfully identifies optimal parameter settings, substantially improving energy efficiency and machining performance. Further, microstructural studies of chips and confirmation tests were conducted to validate the optimum process parameters.