• This review summarizes AI applications in additive manufacturing. • It elaborates on AI’s data-driven strategies for optimizing AM processes. • Key challenges and future directions in AI-driven AM are presented. Additive manufacturing (AM) has brought revolutionary changes to revolutionized modern manufacturing through its high flexibility, capability to fabricate complex structures, and efficient material utilization. However, conventional AM still faces major challenges, including inefficient design workflows, unstable process control, high defect rates, and sustainability issues related to energy consumption and cost. These limitations restrict its broader industrial application. Recently, the rapid development of artificial intelligence (AI) has become increasingly important across the entire AM workflow, offering powerful tools to compensate for its current shortcomings. Accordingly, this review follows the temporal logic of AM, covering the pre-processing, in-processing, and post-processing stages, and focuses on three core processes in their chronological order: (i) part design and optimization, (ii) process modeling and parameter control, and (iii) defect detection and sustainability improvement. We systematically examine how AI empowers each of these processes, as well as the persistent challenges that remain. We further suggest that future research should emphasize the integration of domain knowledge with advanced AI techniques and the development of modular, real-time adaptive models. This review aims to consolidate the current research landscape, highlight the role of AI and big data in AM, and provide directions for future research and development in both academia and industry.
Chen et al. (Sun,) studied this question.