Scholarlink

A hybrid strategy, integrating Binary-Coded Genetic Algorithm (BCGA) tuner and Artificial Neural Network (ANN), enhances the precision and generality of the predictive model. The BCGA tuner optimizes the ANN model’s parameters, resulting in an efficient and robust predictive tool. The research methodology involves collecting a comprehensive dataset with input parameters like discharge energy, tube thickness, number of punches, and spacer length, alongside output data representing thickness reduction and morphological conditions. The BCGA tuner refines the ANN model's architecture and weights, ensuring optimal performance. The trained ANN model's efficacy is evaluated using statistical metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R2). Comparative analysis with simulation data across six datasets indicates a minimal deviation (less than 5%), highlighting the model's accuracy and reliability. This accurate predictive model empowers manufacturers to optimize parameters, minimize waste, and reduce production costs, making it a valuable tool for widespread industrial implementation.

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

Development of a Hybrid BCGA Tuner for Artificial Neural Network in Assessing the Performance of Electromagnetic Forming and Perforation (EMFP) of Al6061–T6 Tube

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Avinash Chetry,
  • Arup Nandy

摘要

A hybrid strategy, integrating Binary-Coded Genetic Algorithm (BCGA) tuner and Artificial Neural Network (ANN), enhances the precision and generality of the predictive model. The BCGA tuner optimizes the ANN model’s parameters, resulting in an efficient and robust predictive tool. The research methodology involves collecting a comprehensive dataset with input parameters like discharge energy, tube thickness, number of punches, and spacer length, alongside output data representing thickness reduction and morphological conditions. The BCGA tuner refines the ANN model's architecture and weights, ensuring optimal performance. The trained ANN model's efficacy is evaluated using statistical metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R2). Comparative analysis with simulation data across six datasets indicates a minimal deviation (less than 5%), highlighting the model's accuracy and reliability. This accurate predictive model empowers manufacturers to optimize parameters, minimize waste, and reduce production costs, making it a valuable tool for widespread industrial implementation.