| Scope |
This symposium will provide an excellent platform to exchange the latest knowledge in additive manufacturing (AM) modeling, simulation, and machine learning. Despite extensive progress in AM field, there are still many challenges in predictive theoretical and computational approaches that hinder the advance of AM technologies. The symposium is interested in receiving contributions in the following non-exclusive areas: In particular, the following topics, but not limited to, are of interest:
1. Modeling of microstructure evolution, phase transformation, and defect formation in AM parts
2. Modeling of residual stress, distortion, plasticity/damage, creep, and fatigue in AM parts
3. Machine learning (ML), artificial intelligence (AI), and data science (DS)’s applications to AM
4. Calibration and validation data sets relevant to models
5. AM process monitoring and defect quantification
6. Efficient computational methods using reduced-order models or fast emulators for process control
7. Multiscale/multiphysics modeling strategies, including any or all of the scales associated with the spatial, temporal, and/or material domains |