Scholarlink

<p>High-strength Al-Si alloys are important lightweight materials, but their optimal design is hindered by scarce-imbalance data, and complex compositional-process-property relationships. Traditional trial-and-error experimentation fails to explore this multi-dimensional design space, where processing routes (PRs) and composition must be co-optimized to achieve superior strength. This study introduces a process-synergistic active learning (PSAL) framework leveraging a conditional Wasserstein autoencoder (c-WAE) to enable the data-efficient design. By encoding PRs as conditional variables, the PSAL framework reveals exceptional synergistic effects across diverse PRs, significantly outperforming single-process approaches. The process-aware latent representation facilitates the efficient exploration of potential compositions across multi-PRs simultaneously. Through iterative active learning cycles integrating machine learning predictions with experimental validations, ultimate tensile strength is greatly improved: 459.8 MPa for gravity casting with T6 heat treatment within three iterations and 220.5 MPa for gravity casting with hot extrusion in a single iteration. This framework handles sparse datasets effectively, capturing complex process-composition-property relationships and establishing a new paradigm for accelerated multi-objective material design.</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 process-synergistic active learning framework for high-strength Al-Si alloys design

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月14日

查看全文
  • Jianming Cai,
  • Mengxia Han,
  • Xirui Yan,
  • Yan Chen,
  • Daoxiu Li,
  • Kai Zhao,
  • Dongqing Zhang,
  • Kaiqi Hu,
  • Heng Han Sua,
  • Hieng Kiat Jun,
  • Kewei Xie,
  • Guiliang Liu,
  • Xiangfa Liu,
  • Sida Liu

摘要

High-strength Al-Si alloys are important lightweight materials, but their optimal design is hindered by scarce-imbalance data, and complex compositional-process-property relationships. Traditional trial-and-error experimentation fails to explore this multi-dimensional design space, where processing routes (PRs) and composition must be co-optimized to achieve superior strength. This study introduces a process-synergistic active learning (PSAL) framework leveraging a conditional Wasserstein autoencoder (c-WAE) to enable the data-efficient design. By encoding PRs as conditional variables, the PSAL framework reveals exceptional synergistic effects across diverse PRs, significantly outperforming single-process approaches. The process-aware latent representation facilitates the efficient exploration of potential compositions across multi-PRs simultaneously. Through iterative active learning cycles integrating machine learning predictions with experimental validations, ultimate tensile strength is greatly improved: 459.8 MPa for gravity casting with T6 heat treatment within three iterations and 220.5 MPa for gravity casting with hot extrusion in a single iteration. This framework handles sparse datasets effectively, capturing complex process-composition-property relationships and establishing a new paradigm for accelerated multi-objective material design.