Scholarlink

<p>Wire Arc Additive Manufacturing (WAAM) is emerging as a cost-effective and material-efficient deposition technique; however, optimizing process parameters for dissimilar metal deposition remains a significant challenge. This study examines the impact of Gas Metal Arc Welding (GMAW) parameters, specifically current and deposition speed, on bead geometry and hardness during the deposition of Inconel 617 (IN 617) on a stainless steel 304L (SS 304L) substrate. An L9 orthogonal design was employed to conduct bead-on-plate depositions, followed by detailed macrostructural and microstructural analyses. Machine learning models (linear regression and random forest regression) were developed to predict bead width, bead height, and hardness, and Bayesian optimization was applied to identify the optimal parameter combination. Bead width increased with higher current, while bead height decreased with increasing deposition speed. Microstructural characterization revealed the presence of cellular, equiaxed, and columnar dendritic morphologies, along with unmixed zones at the interface. FESEM-EDS confirmed the segregation of alloying elements and the formation of Cr and Mo-rich carbides, as well as delta ferrite in the interfacial region. Bayesian optimization identified 200&#xa0;A current and 180&#xa0;mm/min deposition speed as optimal parameters, producing maximum bead width (13.7&#xa0;mm), bead height (7.27&#xa0;mm), and hardness (179.2&#xa0;HV). Overall, the integration of machine learning prediction with process optimization provides an effective strategy for improving deposition quality and mechanical performance in dissimilar WAAM of nickel-based superalloys.</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

Optimization of Gas Metal Arc Welding-Based Wire Arc Additive Manufacturing Parameters for Inconel 617 over SS304L: Experimental, Microstructural, and Machine Learning Insights

  • 期刊论文

  • 发表日期：

    2026年5月7日

查看全文
  • Manoj Kumar Perumal,
  • Niraj Kumar,
  • Prakash Kumar,
  • Santosh Kr. Mishra,
  • Sanjeev Kumar,
  • Manish Giri

摘要

Wire Arc Additive Manufacturing (WAAM) is emerging as a cost-effective and material-efficient deposition technique; however, optimizing process parameters for dissimilar metal deposition remains a significant challenge. This study examines the impact of Gas Metal Arc Welding (GMAW) parameters, specifically current and deposition speed, on bead geometry and hardness during the deposition of Inconel 617 (IN 617) on a stainless steel 304L (SS 304L) substrate. An L9 orthogonal design was employed to conduct bead-on-plate depositions, followed by detailed macrostructural and microstructural analyses. Machine learning models (linear regression and random forest regression) were developed to predict bead width, bead height, and hardness, and Bayesian optimization was applied to identify the optimal parameter combination. Bead width increased with higher current, while bead height decreased with increasing deposition speed. Microstructural characterization revealed the presence of cellular, equiaxed, and columnar dendritic morphologies, along with unmixed zones at the interface. FESEM-EDS confirmed the segregation of alloying elements and the formation of Cr and Mo-rich carbides, as well as delta ferrite in the interfacial region. Bayesian optimization identified 200 A current and 180 mm/min deposition speed as optimal parameters, producing maximum bead width (13.7 mm), bead height (7.27 mm), and hardness (179.2 HV). Overall, the integration of machine learning prediction with process optimization provides an effective strategy for improving deposition quality and mechanical performance in dissimilar WAAM of nickel-based superalloys.