Scholarlink

<p>Additive manufacturing (AM) is a revolutionary industrial process, and its integration with artificial intelligence (AI) is becoming a key strategy for manufacturers aiming to gain a competitive advantage through sustainability initiatives. While some studies have explored machine learning in manufacturing optimization, there is a limited understanding of how AI supports sustainable practices in AM across various sectors and contexts. This study analysed peer-reviewed journals from the Scopus database published between 2019 and 2025, following systematic review methods. After screening and quality assessment, 34 relevant studies were selected and analysed using thematic content analysis. The findings reveal three key areas where AI improves sustainable AM: (1) energy management and prediction systems for optimizing energy use, (2) environmental impact assessment frameworks combining life cycle thinking with real-time decision-making, and (3) process optimization tools for improving material efficiency and supporting the circular economy. The study shows that machine learning algorithms, optimization techniques, and hybrid AI methods consistently deliver measurable sustainability benefits across various manufacturing applications. This research contributes to the field by integrating AI applications into sustainable AM, identifying implementation patterns and outcomes, and proposing a conceptual framework that aligns technological capabilities with sustainability goals to guide future research and practice.</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

AI as an enabler of sustainable additive manufacturing: environmental impact and circular design

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月4日

查看全文
  • Samuel Koranteng Fianko,
  • Isaac Kwesi Nooni,
  • Thywill Dzogbewu,
  • Edinam Agbemava,
  • Deon Johan de Beer

摘要

Additive manufacturing (AM) is a revolutionary industrial process, and its integration with artificial intelligence (AI) is becoming a key strategy for manufacturers aiming to gain a competitive advantage through sustainability initiatives. While some studies have explored machine learning in manufacturing optimization, there is a limited understanding of how AI supports sustainable practices in AM across various sectors and contexts. This study analysed peer-reviewed journals from the Scopus database published between 2019 and 2025, following systematic review methods. After screening and quality assessment, 34 relevant studies were selected and analysed using thematic content analysis. The findings reveal three key areas where AI improves sustainable AM: (1) energy management and prediction systems for optimizing energy use, (2) environmental impact assessment frameworks combining life cycle thinking with real-time decision-making, and (3) process optimization tools for improving material efficiency and supporting the circular economy. The study shows that machine learning algorithms, optimization techniques, and hybrid AI methods consistently deliver measurable sustainability benefits across various manufacturing applications. This research contributes to the field by integrating AI applications into sustainable AM, identifying implementation patterns and outcomes, and proposing a conceptual framework that aligns technological capabilities with sustainability goals to guide future research and practice.