Scholarlink

<p>Metal-based Laser Additive Manufacturing (MLAM) has emerged as a transformative technology in industrial sectors due to its ability to fabricate complex, high-performance metal components directly from digital 3-D models. Despite its advantages, the process is prone to the formation of residual stresses, which can cause defects such as part distortion and cracking. Hence, accurately predicting and managing these stresses is essential to ensure the structural integrity and quality of the final product. To address these issues, this review explores a novel methodology that integrates in-situ field assistance and real-time process monitoring to improve melt pool behavior and guide grain nucleation, thereby enhancing build quality. Focusing on the key elements of closed-loop control systems in MLAM, the paper presents a comprehensive examination of in-situ sensing and control approaches. It covers various signal monitoring techniques, analyzes the root causes of typical defects, and introduces scientific control strategies tailored to mitigate them. The study also summarizes the current advancements and challenges in implementing sensing technologies and closed-loop control architectures. Furthermore, the review highlights the limitations of existing methods and outlines future directions for research in in-situ monitoring, intelligent process control, and the application of machine learning models. By doing so, it offers a strategic foundation for developing advanced, intelligent control systems for industrial-scale MLAM, providing a valuable resource for both researchers and practitioners in the field.</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 review on in-situ monitoring, process control and residual stress prediction using machine learning methods in metal-based laser additive manufacturing

  • 期刊论文

  • 发表日期：

    2026年2月3日

查看全文
  • Gaurav Kishor,
  • Yugal Kishor Sharma,
  • Krishna Kishore Mugada,
  • Raju Prasad Mahto

摘要

Metal-based Laser Additive Manufacturing (MLAM) has emerged as a transformative technology in industrial sectors due to its ability to fabricate complex, high-performance metal components directly from digital 3-D models. Despite its advantages, the process is prone to the formation of residual stresses, which can cause defects such as part distortion and cracking. Hence, accurately predicting and managing these stresses is essential to ensure the structural integrity and quality of the final product. To address these issues, this review explores a novel methodology that integrates in-situ field assistance and real-time process monitoring to improve melt pool behavior and guide grain nucleation, thereby enhancing build quality. Focusing on the key elements of closed-loop control systems in MLAM, the paper presents a comprehensive examination of in-situ sensing and control approaches. It covers various signal monitoring techniques, analyzes the root causes of typical defects, and introduces scientific control strategies tailored to mitigate them. The study also summarizes the current advancements and challenges in implementing sensing technologies and closed-loop control architectures. Furthermore, the review highlights the limitations of existing methods and outlines future directions for research in in-situ monitoring, intelligent process control, and the application of machine learning models. By doing so, it offers a strategic foundation for developing advanced, intelligent control systems for industrial-scale MLAM, providing a valuable resource for both researchers and practitioners in the field.