Scholarlink

This paper focuses on developing a predictive model for profile error in ultra-precision turning using a diamond tool on the aspherical surface of Al6061 material. A 30-experiment empirical model is established with three input parameters: spindle speed, feed rate, and depth of cut. The results from this model are collected to form an input dataset for an Artificial Neural Network (ANN) to build a predictive model for profile error. Identifying a network structure with high accuracy and reliability is crucial for determining a regression function that enhances optimization precision. The ANN structure 3–5-10–1 provides the best prediction results with R2 = 0.99, MAPE = 7.25%, MSE = 57.17, and RMSE = 3268. This study contributes valuable insights into predicting and optimizing profile error in ultra-precision turning of Al6061 material. Additionally, the proposed modeling and optimization approach can be extended to other materials and machining processes for diffractive surfaces.

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

Research on Modeling for Surface Profile Errors of Al6061 Aspherical in Ultra-precision Turning Based on Neural Network

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Hoang Nghia Duc,
  • Duong Xuan Bien,
  • Bui Kim Hoa,
  • Nguyen Kim Hung,
  • Do Manh Tung,
  • Ngo Viet Hung

摘要

This paper focuses on developing a predictive model for profile error in ultra-precision turning using a diamond tool on the aspherical surface of Al6061 material. A 30-experiment empirical model is established with three input parameters: spindle speed, feed rate, and depth of cut. The results from this model are collected to form an input dataset for an Artificial Neural Network (ANN) to build a predictive model for profile error. Identifying a network structure with high accuracy and reliability is crucial for determining a regression function that enhances optimization precision. The ANN structure 3–5-10–1 provides the best prediction results with R2 = 0.99, MAPE = 7.25%, MSE = 57.17, and RMSE = 3268. This study contributes valuable insights into predicting and optimizing profile error in ultra-precision turning of Al6061 material. Additionally, the proposed modeling and optimization approach can be extended to other materials and machining processes for diffractive surfaces.