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

TL;DR

BubbleNet is a semi-physics-informed deep learning framework that accurately predicts micro-bubble dynamics in confined flows, outperforming traditional numerical methods and leveraging physics constraints for improved simulation fidelity.

Contribution

The paper introduces BubbleNet, a novel semi-physics-informed neural network that incorporates partial physics constraints to enhance micro-bubble flow predictions.

Findings

BubbleNet predicts physics fields more accurately than traditional methods.

Physics-informed component acts as effective inner supervision.

Framework generalizes to other engineering applications.

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.