Scholarlink

<p>In modern manufacturing, machine learning (ML) plays a crucial role in predicting response measures, reducing machining trial costs and saving energy. This study investigates surface evolution and cutting forces (F<sub>avg</sub>) during the micro-milling of selective laser-melted (SLM) Ti6Al4V, focusing on spindle speed (SS), depth of cut (D<sub>OC</sub>), and feed rate (F<sub>Z</sub>). Analysis of variance&#xa0;(ANOVA) identified F<sub>Z</sub> as the most influential on surface roughness (Ra) of about 38.54% and D<sub>OC</sub> on F<sub>avg</sub> (42.16%). An artificial neural network (ANN) was trained to map the process-performance relationship, showing strong correlation with experimental results, thereby reducing material and resource costs. Additionally, a ML-based non-dominated sorting genetic algorithm (NSGA-II) was used for multi-objective optimization, achieving significant improvements in Ra and F<sub>avg</sub> by 335.61% and 592.61%, respectively, with optimal parameters of SS = 74,994 RPM, D<sub>OC</sub> = 19.94&#xa0;μm, and F<sub>Z</sub> = 1&#xa0;μm/tooth. Detailed analysis of F<sub>avg</sub> signals, tool wear, and surface evolution was conducted using scanning electron microscopy&#xa0;(SEM). The cumulative regression coefficient (R) for the ANN model is 0.99669, which demonstrates a strong correlation between the predicted values and the actual outcomes. The developed ML model will help the manufacturing industry by reducing the costs for materials, resources, and trial runs.</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

Analysing surface quality evolution and cutting forces in micro-milling of Ti6Al4V using experimental and machine learning approaches

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月6日

查看全文
  • Muhammad Rehan,
  • Muhammad Sana,
  • Muhammad Umar Farooq,
  • Wai Sze Yip,
  • Suet To

摘要

In modern manufacturing, machine learning (ML) plays a crucial role in predicting response measures, reducing machining trial costs and saving energy. This study investigates surface evolution and cutting forces (Favg) during the micro-milling of selective laser-melted (SLM) Ti6Al4V, focusing on spindle speed (SS), depth of cut (DOC), and feed rate (FZ). Analysis of variance (ANOVA) identified FZ as the most influential on surface roughness (Ra) of about 38.54% and DOC on Favg (42.16%). An artificial neural network (ANN) was trained to map the process-performance relationship, showing strong correlation with experimental results, thereby reducing material and resource costs. Additionally, a ML-based non-dominated sorting genetic algorithm (NSGA-II) was used for multi-objective optimization, achieving significant improvements in Ra and Favg by 335.61% and 592.61%, respectively, with optimal parameters of SS = 74,994 RPM, DOC = 19.94 μm, and FZ = 1 μm/tooth. Detailed analysis of Favg signals, tool wear, and surface evolution was conducted using scanning electron microscopy (SEM). The cumulative regression coefficient (R) for the ANN model is 0.99669, which demonstrates a strong correlation between the predicted values and the actual outcomes. The developed ML model will help the manufacturing industry by reducing the costs for materials, resources, and trial runs.