Scholarlink

This work develops of hybrid Machine learning model for predicting the mechanical behavior of polymer/carbon nanotube composites, specifically focusing on elastic modulus and maximum tensile stress. The machine learning model leverages a comprehensive database compiled from various available sources. We opted for a hybrid Machine learning architecture and optimized its design through a parametric study. To evaluate the model's effectiveness, we employed several error metrics, including the widely used Coefficient of determination (R2), Root-Mean-Squared-Error (RMSE), and Mean-Absolute-Error (MAE). The results demonstrate that the developed hybrid Machine learning model exhibits good predictive performance, suggesting its capability for accurate prediction of elastic modulus and maximum tensile stress in polymer/CNT composites.

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

Hybrid Machine Learning Model for the Prediction of Maximum Tensile Stress and Elastic Modulus of Nanocomposites

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nang Xuan Ho,
  • Tien-Thinh Le,
  • Xuan-Son Nguyen,
  • Van-Hai Nguyen,
  • Huan Thanh Duong

摘要

This work develops of hybrid Machine learning model for predicting the mechanical behavior of polymer/carbon nanotube composites, specifically focusing on elastic modulus and maximum tensile stress. The machine learning model leverages a comprehensive database compiled from various available sources. We opted for a hybrid Machine learning architecture and optimized its design through a parametric study. To evaluate the model's effectiveness, we employed several error metrics, including the widely used Coefficient of determination (R2), Root-Mean-Squared-Error (RMSE), and Mean-Absolute-Error (MAE). The results demonstrate that the developed hybrid Machine learning model exhibits good predictive performance, suggesting its capability for accurate prediction of elastic modulus and maximum tensile stress in polymer/CNT composites.