About this Abstract |
Meeting |
2021 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2021)
|
Symposium
|
Special Session
|
Presentation Title |
Physics-informed and Hybrid Machine Learning in Additive Manufacturing |
Author(s) |
Berkcan Kapusuzoglu, Sankaran Mahadevan |
On-Site Speaker (Planned) |
Berkcan Kapusuzoglu |
Abstract Scope |
This work investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep learning models for predicting the bond quality and porosity of fused filament fabrication parts. A physics-based sintering model is developed to predict the neck diameter and porosity of FFF parts. Three types of strategies and their combinations are explored to incorporate physics information into a deep neural network (DNN), thus ensuring consistency with physical laws: (1) incorporate physics constraints within the loss function of the DNN, (2) use physics model outputs as additional inputs to the DNN model, and (3) pre-train a DNN model with physics model input-output and then update it with experimental data. These strategies help to enforce a physically consistent relationship between bond quality and tensile strength, thus making porosity predictions physically meaningful. The results show how the combination these strategies produces accurate results even with limited experimental data. |
Proceedings Inclusion? |
Definite: Post-meeting proceedings |