aiqbench analysis
This research advances AI in manufacturing by integrating physics-based constraints into deep learning models, enabling accurate prediction of 3D print quality even with sparse experimental data. The study demonstrates that hybrid approaches combining simulation outputs and physical laws significantly improve model reliability over purely data-driven methods.
Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication
arXiv:2608.17246v1 Announce Type: new Abstract: This article 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 (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results 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. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.
Abstract:This article 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 (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results 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. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.
Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE); Computation (stat.CO)
arXiv:2608.17246 [cs.LG]
(or arXiv:2608.17246v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.17246 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1007/s11837-020-04438-4 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 260 words
