Intelligent additive manufacturing: from multi-physics modeling to AI-driven prediction and diagnostics

Here I will present our work in developing intelligent additive manufacturing, where digitalization is a key enabler. We start from multi-scale multi-physics modeling to understand the fundamental mechanisms, spanning from powder and melt pool dynamics, to microstructure and mechanical properties, i.e., process-structure-property relationships. To enhance the computational efficiency, we have developed physics-informed AI models using physics-based simulation results as the training data and physical laws as the constraints. As most sensor data only contains limited and indirect information, we leverage physics-based simulation and AI models to extract more in-depth and instructive information, achieving comprehensive diagnostics to identify defects.

Dr. Wentao Yan is an associate professor in the Department of Mechanical Engineering, National University of Singapore (NUS). Before joining NUS in 2018, Dr. Yan was a postdoctoral fellow at Northwestern University in the USA. He received his Ph.D. degree jointly at Tsinghua University, Beijing and Northwestern University, USA. He got his Bachelor degree from the Department of Mechanical Engineering, Tsinghua University, Beijing in 2012. Supported by multi-million grants, his research group with 20+ students focus on multi-scale multi-physics modeling, experimental investigation and data analysis of additive manufacturing. Over 30 of his former postdocs and PhD students have got faculty positions. He has published >160 papers on flagship journals, such as Nature Communications, Acta Materialia, JMPS and CMAME, which have received over 10,000 citations. His team was the biggest winner in the 2022 and 2025 NIST AM-Bench Simulation Challenges. He has won multiple best paper awards in various journals. He currently serves as the Senior Editor for Additive Manufacturing Journal and an editorial board member for IJMTM and Materials & Design.