Scholarlink

<p>Laser Powder Bed Fusion (LPBF) enables the fabrication of complex soft magnetic components but often involves high energy input and trade-offs between magnetic and mechanical performance. This study presents an energy-aware optimization framework for LPBF processing of Fe–50wt%Ni soft magnetic alloys. Two L9 orthogonal experiments were conducted, and machine learning models were trained to predict magnetic permeability and ultimate tensile strength (UTS) from four key process parameters. The best condition, 3500 ppm oxygen, 300 smm/s scan speed, 250&#xa0;W laser power, and 0.09&#xa0;mm hatch distance, achieved relative permeabilities of 416.48, 400.58, 332.39, and 231.46 at 50, 200, 400, and 800&#xa0;Hz, respectively, and a UTS of 504.11&#xa0;MPa. A recommendation system integrating ensemble learning with NSGA-II was developed to minimize energy consumption while meeting user-specified property targets. A case study demonstrated a 47.2% reduction in energy use with about 5% loss in material performance. The key contribution lies in optimizing LPBF parameters based on specified property requirements while minimizing energy consumption rather than ideal trade-off balance, offering a practical strategy for sustainable additive manufacturing of soft magnetic alloys.</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

Energy Consumption and Property Optimization in Laser Powder Bed Fusion of Fe-50wt%Ni Permalloys

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月16日

查看全文
  • Chunhui Chung,
  • Chi-Chun Chen,
  • Tsung-Wei Chang,
  • Mi-Ching Tsai

摘要

Laser Powder Bed Fusion (LPBF) enables the fabrication of complex soft magnetic components but often involves high energy input and trade-offs between magnetic and mechanical performance. This study presents an energy-aware optimization framework for LPBF processing of Fe–50wt%Ni soft magnetic alloys. Two L9 orthogonal experiments were conducted, and machine learning models were trained to predict magnetic permeability and ultimate tensile strength (UTS) from four key process parameters. The best condition, 3500 ppm oxygen, 300 smm/s scan speed, 250 W laser power, and 0.09 mm hatch distance, achieved relative permeabilities of 416.48, 400.58, 332.39, and 231.46 at 50, 200, 400, and 800 Hz, respectively, and a UTS of 504.11 MPa. A recommendation system integrating ensemble learning with NSGA-II was developed to minimize energy consumption while meeting user-specified property targets. A case study demonstrated a 47.2% reduction in energy use with about 5% loss in material performance. The key contribution lies in optimizing LPBF parameters based on specified property requirements while minimizing energy consumption rather than ideal trade-off balance, offering a practical strategy for sustainable additive manufacturing of soft magnetic alloys.