Mathematical and Computational Engineering Stream

Artificial Intelligence Driven Multiscale and Multiphysics Computational Framework for Materials and Process Design

Faculty: Prof. Prosenjit Das (ME) and Prof. Ratikanta Behera (CDS)

Advanced manufacturing technologies are increasingly being explored to develop next-generation lightweight metallic materials with superior mechanical and thermal performance. Among these, Laser Powder Bed Fusion (LPBF) has emerged as a powerful additive manufacturing technique capable of producing complex components with high precision and design flexibility. Aluminum-based High-Entropy Alloys (Al-HEAs) represent a promising class of materials combining low density, high strength, and excellent corrosion resistance, with broad potential across aerospace, automotive, and energy sectors.

Despite their promise, fabricating Al-HEAs through LPBF involves complex physical phenomena occurring
across multiple length and time scales, making process optimization through conventional experimental approaches alone both time-consuming and costly. This research addresses these challenges by developing an integrated computational and experimental framework that combines multiscale physics-based simulations with Machine Learning (ML) techniques. The computational models capture powder dynamics, heat transfer, solidification, and microstructure evolution during processing, while ML algorithms establish predictive relationships between processing conditions and resulting mechanical and functional properties of the material. Experimental data from microstructural characterization and mechanical testing continuously refine the ML models through a closed-loop active learning strategy, ensuring improved prediction accuracy and reliability.

This integrated framework demonstrates how ML can transform additive manufacturing by enabling rapid identification of optimal processing windows, reducing costly trial-and-error experimentation, and ultimately accelerating the development of high-performance lightweight alloys for aerospace, defense, and advanced engineering applications.

Candidates with a background in Applied Mathematics and Machine Learning, with strong interest in
Materials Science & Engineering, Mechanical Engineering, Design and Manufacturing, Physics, are
encouraged to apply.

References

  1. Liu, Q., Wu, H., Paul, M.J., He, P., Peng, Z., Gludovatz, B., Kruzic, J.J., Wang, C.H., and Li, X. Machine
    learning assisted laser powder bed fusion process optimization for AlSi10Mg: New microstructure description indices and fracture mechanisms. Acta Materialia, 201, 316–328, 2020.
    https://doi.org/10.1016/j.actamat.2020.10.010
  2. Ng, C.T., et al. Progress and opportunities for machine learning in materials and processes of
    additive manufacturing. Advanced Materials, 36, 2310006, 2024. https://doi.org/10.1002/adma. 202310006
  3. Chen, L.Q., and Zhao, Y. Understanding and design of metallic alloys guided by phase-field simulations. npj Computational Materials, 9, 94, 2023. https://doi.org/10.1038/s41524-023-01038-z
  4. Rahnama, A., et al. Additive manufacturing of alloys with programmable microstructure and properties. Nature Communications, 14, 6717, 2023. https://doi.org/10.1038/s41467-023-42326-y
  5. Soheilnia, F., et al. Integrating phase field modeling and machine learning to develop process-microstructure relationships in laser powder bed fusion of IN718. Metallography, Microstructure, and Analysis, 2024. https://doi.org/10.1007/s13632-024-01130-w