Scholarlink

<p>The steelmaking industry is currently undergoing a significant transformation toward intelligent manufacturing, largely propelled by breakthroughs in artificial intelligence (AI). Based on a systematic review of peer-reviewed literature published between 2020 and 2026, including journal articles and conference papers, this synthesis consolidates insights from over 70 studies. Key trends reveal a progression from conventional machine learning approaches to more sophisticated deep learning models and physics-informed neural networks, with growing applications in process control, quality prediction, and energy efficiency. The review further critically assesses persistent challenges, including data imbalance, limited model interpretability, and barriers to real-world deployment, supported by a comparative analysis of studies conducted in China, Europe, South Korea, and Brazil. To conclude, the paper outlines future directions for AI-driven steelmaking, offering both theoretical and practical insights to support the advancement of intelligent and sustainable steel production.</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

Steelmaking in the age of artificial intelligence

  • 期刊论文

  • 发表日期：

    2026年5月23日

查看全文
  • Nanfu Zong,
  • Tao Jing,
  • Jean-Christophe Gebelin

摘要

The steelmaking industry is currently undergoing a significant transformation toward intelligent manufacturing, largely propelled by breakthroughs in artificial intelligence (AI). Based on a systematic review of peer-reviewed literature published between 2020 and 2026, including journal articles and conference papers, this synthesis consolidates insights from over 70 studies. Key trends reveal a progression from conventional machine learning approaches to more sophisticated deep learning models and physics-informed neural networks, with growing applications in process control, quality prediction, and energy efficiency. The review further critically assesses persistent challenges, including data imbalance, limited model interpretability, and barriers to real-world deployment, supported by a comparative analysis of studies conducted in China, Europe, South Korea, and Brazil. To conclude, the paper outlines future directions for AI-driven steelmaking, offering both theoretical and practical insights to support the advancement of intelligent and sustainable steel production.