BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning

Abstract

Micro-bubbles and bubbly flows are widely observed and applied in chemical engineering, medicine, involves deformation, rupture, and collision of bubbles, phase mixture, etc. We study bubble dynamics by setting up two numerical simulation cases: bubbly flow with a single bubble and multiple bubbles, both confined in the microchannel, with parameters corresponding to their medical backgrounds. Both the cases have their medical background applications. Multiphase flow simulation requires high computation accuracy due to possible component losses that may be caused by sparse meshing during the computation. Hence, data-driven methods can be adopted as an useful tool. Based on physics-informed neural networks (PINNs), we propose a novel deep learning framework BubbleNet, which entails three main parts: deep neural networks (DNN) with sub nets for predicting different physics fields; the semi-physics-informed part, with only the fluid continuum condition and the pressure Poisson equation $\mathcal{P}$ encoded within; the time discretized normalizer (TDN), an algorithm to normalize field data per time step before training. We apply the traditional DNN and our BubbleNet to train the coarsened simulation data and predict the physics fields of both the two bubbly flow cases. The BubbleNets are trained for both with and without $\mathcal{P}$, from which we conclude that the 'physics-informed' part can serve as inner supervision. Results indicate our framework can predict the physics fields more accurately, estimating the prediction absolute errors. Our deep learning predictions outperform traditional numerical methods computed with similar data density meshing. The proposed network can potentially be applied to many other engineering fields.

arXiv commentRefine the manuscript

References in corpus (20)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• DeepXDE: A deep learning library for solving differential equations
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• Fourier Neural Operator for Parametric Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Deep Learning in Alzheimer's disease: Diagnostic Classification and Prognostic Prediction using Neuroimaging Data
• PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs
• Physics-informed deep learning for incompressible laminar flows
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• DeePCG: constructing coarse-grained models via deep neural networks
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• Operator learning for predicting multiscale bubble growth dynamics
• Deep Model Predictive Control with Online Learning for Complex Physical Systems
• Microbubble formation and pinch-off scaling exponent in flow-focusing devices
• BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning
• Deep learning velocity signals allows to quantify turbulence intensity

Cited by in corpus (5)

• Comparison of Deep Learning and Deterministic Algorithms for Control Modeling
• BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning
• Controlling Chaos in Van Der Pol Dynamics Using Signal-Encoded Deep Learning
• Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training
• Controlling Biofilm Transport with Porous Metamaterials Designed with Bayesian Learning