Scholarlink

<p>High-entropy alloys (HEAs) represent a state-of-the-art material system, exhibiting exceptional physical and chemical properties that hold great potential for engineering applications. Nevertheless, accurately identifying their complex phase structures remains a significant challenge. This study presents a novel integrated machine learning (ML) framework that combines data processing, feature optimization, and 12 predictive algorithms to enable rapid and precise classification of HEA phase structures. T Comprehensive qualitative and quantitative evaluations demonstrate that the SVM, GBT, and RF algorithms exhibit superior predictive performance. The voting ensemble strategy effectively integrates the strengths of individual methods, achieving the highest overall accuracy. Key features including <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\:{\updelta\:}\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\:{\upalpha\:}\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\:{{\upsigma\:}}_{{T}_{m}}\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\:{{\Delta\:}\text{H}}_{mix}\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(\:{{\Delta\:}\text{S}}_{mix}\)</EquationSource> </InlineEquation> consistently emerge as the most influential predictors across all models. This framework provides a powerful tool for predicting HEA properties, significantly accelerating the discovery and development of advanced materials.</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

A ML-Driven Framework for Phase Prediction in High-Entropy Alloys

  • 期刊论文

  • 发表日期：

    2025年11月3日

查看全文
  • Yingting Guo,
  • Yan Xu

摘要

High-entropy alloys (HEAs) represent a state-of-the-art material system, exhibiting exceptional physical and chemical properties that hold great potential for engineering applications. Nevertheless, accurately identifying their complex phase structures remains a significant challenge. This study presents a novel integrated machine learning (ML) framework that combines data processing, feature optimization, and 12 predictive algorithms to enable rapid and precise classification of HEA phase structures. T Comprehensive qualitative and quantitative evaluations demonstrate that the SVM, GBT, and RF algorithms exhibit superior predictive performance. The voting ensemble strategy effectively integrates the strengths of individual methods, achieving the highest overall accuracy. Key features including \(\:{\updelta\:}\) , \(\:{\upalpha\:}\) , \(\:{{\upsigma\:}}_{{T}_{m}}\) , \(\:{{\Delta\:}\text{H}}_{mix}\) and \(\:{{\Delta\:}\text{S}}_{mix}\) consistently emerge as the most influential predictors across all models. This framework provides a powerful tool for predicting HEA properties, significantly accelerating the discovery and development of advanced materials.