Scholarlink

<p>The present work explores the transformation of conventional Fused Filament Fabrication (FFF) 3D printers into smart, interconnected systems through the integration of Machine Learning (ML) and Industry 4.0 technologies. The flexibility of Additive Manufacturing (AM) in producing complex, customized components is highlighted, while the significant role of optimized process parameters such as extrusion temperature and printing speed on product quality is addressed. Challenges such as inadequate layer adhesion and environmental effects on the printing process are highlighted, emphasizing the need for a multidisciplinary approach to optimizing printing parameters. A comprehensive framework for improving 3D printers using advanced technologies is presented, including ML, deep learning (DL), and cyber-physical systems. The use of the Raspberry Pi platform has been shown in the Digit.AM case study to retrofit existing printers, enabling real-time data collection and analysis for continuous improvement of printing processes. This transformation not only improves operational efficiency and product quality but also aligns with sustainable manufacturing practices by reducing material waste and supporting predictive maintenance. Together, the framework and case study illustrate a shift toward more autonomous, efficient, and sustainable manufacturing facilities, reflecting the principles of Industry 4.0 and demonstrating the potential for broader application in smart manufacturing environments. </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

Toward advance/digitalized FFF: real-time multimodal synchronized data acquisition and ML/DL-driven process optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月6日

查看全文
  • Mohammad Hossein Nikooharf,
  • Mohammadali Shirinbayan,
  • Nooshin Ghodsian,
  • Pedram Aminharati,
  • Nadia Bahlouli,
  • Joseph Fitoussi,
  • Khaled Benfriha

摘要

The present work explores the transformation of conventional Fused Filament Fabrication (FFF) 3D printers into smart, interconnected systems through the integration of Machine Learning (ML) and Industry 4.0 technologies. The flexibility of Additive Manufacturing (AM) in producing complex, customized components is highlighted, while the significant role of optimized process parameters such as extrusion temperature and printing speed on product quality is addressed. Challenges such as inadequate layer adhesion and environmental effects on the printing process are highlighted, emphasizing the need for a multidisciplinary approach to optimizing printing parameters. A comprehensive framework for improving 3D printers using advanced technologies is presented, including ML, deep learning (DL), and cyber-physical systems. The use of the Raspberry Pi platform has been shown in the Digit.AM case study to retrofit existing printers, enabling real-time data collection and analysis for continuous improvement of printing processes. This transformation not only improves operational efficiency and product quality but also aligns with sustainable manufacturing practices by reducing material waste and supporting predictive maintenance. Together, the framework and case study illustrate a shift toward more autonomous, efficient, and sustainable manufacturing facilities, reflecting the principles of Industry 4.0 and demonstrating the potential for broader application in smart manufacturing environments.