Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
arXiv:1705.09036
Abstract
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzmann flow simulations using deep neural networks. Lat-Net employs convolutional autoencoders and residual connections in a fully differentiable scheme to compress the state size of a simulation and learn the dynamics on this compressed form. The result is a computationally and memory efficient neural network that can be iterated and queried to reproduce a fluid simulation. We show that once Lat-Net is trained, it can generalize to large grid sizes and complex geometries while maintaining accuracy. We also show that Lat-Net is a general method for compressing other Lattice Boltzmann based simulations such as Electromagnetism.
References in corpus (4)
Cited by in corpus (12)
- Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
- Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
- Sub-grid scale model classification and blending through deep learning
- Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
- From Deep to Physics-Informed Learning of Turbulence: Diagnostics
- NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
- Lettuce: PyTorch-based Lattice Boltzmann Framework
- ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
- Frequency-compensated PINNs for Fluid-dynamic Design Problems
- Exploring helical dynamos with machine learning
- Connecting implicit and explicit large eddy simulations of two-dimensional turbulence through machine learning
- A Method for Tumor Treating Fields Fast Estimation