Physics-informed machine learning to reduce defects in additive manufacturing

Common defects in additive manufacturing such as cracking, lack of fusion, porosity, and balling affect the mechanical properties and serviceability of parts. We identify conditions for minimizing the defect formation in additively manufactured metallic parts by using physics-informed machine learning and experimental data.
For more information, please see our recent papers:
1) T. DebRoy, T. Mukherjee, H. L. Wei, J. W. Elmer, and J. O. Milewski. "Metallurgy, mechanistic models and machine learning in metal printing." Nature Reviews Materials 6, no. 1 (2021): 48-68.
2) Y. Du, T. Mukherjee, and T. DebRoy. "Physics-informed machine learning and mechanistic modeling of additive manufacturing to reduce defects." Applied Materials Today 24 (2021): 101123.
DebRoy Research Group