TY - JOUR
T1 - Machine learning in additive manufacturing
T2 - enhancing design, manufacturing and performance prediction intelligence
AU - Wang, Teng
AU - Li, Yanfeng
AU - Li, Taoyong
AU - Liu, Bei
AU - Li, Xiaowei
AU - Zhang, Xiangyu
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
PY - 2025
Y1 - 2025
N2 - Machine learning (ML) is reshaping additive manufacturing (AM) with its potent capability of data analysis, antonomous learning and intelligent decision-making. ML empowers designers by enhancing the capabilities of structural design, improving process optimization, and elevating product performance, thus further help to propose designs that can adapt to diversified manufacturing conditions and meet multi-functional requirements. We herein comprehensively review the cutting-edge advances of ML-based AM in various domains. ML technologies and methods used in multiple AM domains are summarized and the technical features are introduced. ML-based materials preparation, structure design, performance prediction and optimization of AM are comprehesively compared and discussed. Lastly the encountered challenges and the future developments are demonstrated. With an in-depth analysis, we hope this review can propel the applications of ML in the intelligence-led design of AM.
AB - Machine learning (ML) is reshaping additive manufacturing (AM) with its potent capability of data analysis, antonomous learning and intelligent decision-making. ML empowers designers by enhancing the capabilities of structural design, improving process optimization, and elevating product performance, thus further help to propose designs that can adapt to diversified manufacturing conditions and meet multi-functional requirements. We herein comprehensively review the cutting-edge advances of ML-based AM in various domains. ML technologies and methods used in multiple AM domains are summarized and the technical features are introduced. ML-based materials preparation, structure design, performance prediction and optimization of AM are comprehesively compared and discussed. Lastly the encountered challenges and the future developments are demonstrated. With an in-depth analysis, we hope this review can propel the applications of ML in the intelligence-led design of AM.
KW - Additive manufacturing
KW - Design optimization
KW - Machine learning
KW - Mechanical property prediction
UR - http://www.scopus.com/inward/record.url?scp=85217404430&partnerID=8YFLogxK
U2 - 10.1007/s10845-025-02568-7
DO - 10.1007/s10845-025-02568-7
M3 - Article
AN - SCOPUS:85217404430
SN - 0956-5515
JO - Journal of Intelligent Manufacturing
JF - Journal of Intelligent Manufacturing
ER -