Machine learning for metal additive manufacturing: predicting temperature and melt pool fluid dynamics using physics-informed neural networks [PDF]
Computational Mechanics, 2021 The recent explosion of machine learning (ML) and artificial intelligence (AI) shows great potential in the breakthrough of metal additive manufacturing (AM) process modeling, which is an indispensable step to derive the process-structure-property ...
Qiming Zhu, Zeliang Liu, Jinhui Yan
openalex +3 more sources
Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow [PDF]
The Physics of Fluids, 2022 In fluid physics, data-driven models to enhance or accelerate time to solution are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of
Varun Shankar +8 more
openalex +3 more sources
Advancing fluid dynamics simulations: A comprehensive approach to optimizing physics-informed neural networks [PDF]
The Physics of FluidsFlow modeling based on physics-informed neural networks (PINNs) is emerging as a potential artificial intelligence (AI) technique for solving fluid dynamics problems.
Wen Zhou, Shuichiro Miwa, Koji Okamoto
openalex +2 more sources
Machine Learning: Science and Technology, 2023 Finding the distribution of the velocities and pressures of a fluid by solving the Navier–Stokes equations is a principal task in the chemical, energy, and pharmaceutical industries, as well as in mechanical engineering and in design of pipeline systems.
Alexandr Sedykh +5 more
openalex +2 more sources
The neural particle method – An updated Lagrangian physics informed neural network for computational fluid dynamics [PDF]
Computer Methods in Applied Mechanics and Engineering, 2020 Henning Wessels +2 more
openalex +3 more sources
VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction [PDF]
arXiv.orgIn-Context Operator Networks (ICONs) have demonstrated the ability to learn operators across diverse partial differential equations using few-shot, in-context learning.
Yadi Cao +5 more
openalex +2 more sources
Theories of Relativistic Dissipative Fluid Dynamics [PDF]
Entropy, 2023 Relativistic dissipative fluid dynamics finds widespread applications in high-energy nuclear physics and astrophysics. However, formulating a causal and stable theory of relativistic dissipative fluid dynamics is far from trivial; efforts to accomplish ...
G. Rocha +4 more
semanticscholar +1 more source
Machine learning–accelerated computational fluid dynamics [PDF]
Proceedings of the National Academy of Sciences of the United States of America, 2021 Significance Accurate simulation of fluids is important for many science and engineering problems but is very computationally demanding. In contrast, machine-learning models can approximate physics very quickly but at the cost of accuracy.
Dmitrii Kochkov +5 more
semanticscholar +1 more source
NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields [PDF]
International Conference on Machine Learning, 2022 Deep learning has shown great potential for modeling the physical dynamics of complex particle systems such as fluids. Existing approaches, however, require the supervision of consecutive particle properties, including positions and velocities.
Shanyan Guan +3 more
semanticscholar +1 more source
Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics [PDF]
Neural Information Processing Systems, 2022 We present a novel method for guaranteeing linear momentum in learned physics simulations. Unlike existing methods, we enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional layers.
Lukas Prantl +3 more
semanticscholar +1 more source