Scholarlink

Surface roughness (Ra) significantly impacts the quality and performance of machined components, particularly in aluminum alloys. This work investigates how machine learning (ML) can predict Ra. A user-friendly Graphical User Interface (GUI) was developed that takes into account cutting conditions, like cutting speed (Vc), feed rate (f), depth of cut (ap), and mechanical properties (tensile strength, hardness, etc.). Data was harvested from published research to construct a database including diverse aluminum alloy grades (5XXX–7XXX). Several ML algorithms were employed to analyze the data and generate predictive models. Based on user input, the GUI displays predicted Ra and estimated material removal rate (MR). Statistical metrics (RMSE, MAE, and R2) confirm the model's accuracy. Additionally, the GUI highlights the relative importance of each input variable, providing valuable insights into the milling process. For industries using aluminum alloys, this research offers practical value through a GUI that empowers manufacturers to (1) achieve desired Ra consistently and (2) gain a deeper understanding of the relationships between cutting conditions, mechanical properties, and surface finish.

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

GUI-Based Prediction of Surface Roughness in Multi-Grade Aluminum Alloy Milling Considerations of Mechanical Properties

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Van-Hai Nguyen,
  • Tien-Thinh Le,
  • Anh-Tu Nguyen,
  • Ngoc-Kien Nguyen,
  • Nhu-Tung Nguyen

摘要

Surface roughness (Ra) significantly impacts the quality and performance of machined components, particularly in aluminum alloys. This work investigates how machine learning (ML) can predict Ra. A user-friendly Graphical User Interface (GUI) was developed that takes into account cutting conditions, like cutting speed (Vc), feed rate (f), depth of cut (ap), and mechanical properties (tensile strength, hardness, etc.). Data was harvested from published research to construct a database including diverse aluminum alloy grades (5XXX–7XXX). Several ML algorithms were employed to analyze the data and generate predictive models. Based on user input, the GUI displays predicted Ra and estimated material removal rate (MR). Statistical metrics (RMSE, MAE, and R2) confirm the model's accuracy. Additionally, the GUI highlights the relative importance of each input variable, providing valuable insights into the milling process. For industries using aluminum alloys, this research offers practical value through a GUI that empowers manufacturers to (1) achieve desired Ra consistently and (2) gain a deeper understanding of the relationships between cutting conditions, mechanical properties, and surface finish.