Intrusive deconvolutional neural networks for enhancing PIC/FLIP solutions

TL;DR

This paper introduces a deep learning-based multi-fidelity solver that enhances low-fidelity PIC/FLIP fluid simulations, achieving high accuracy and up to 100 times faster computation, addressing limitations of existing ML approaches.

Contribution

A novel deep learning methodology that integrates with low-fidelity fluid solvers to significantly improve accuracy and speed, enabling real-time fluid flow predictions.

Findings

Achieves up to 100x reduction in computational time.

Enhances PIC/FLIP fluid simulations with deep learning.

Demonstrates effectiveness on a popular fluid simulator.

Abstract

Traditional fluid flow predictions require large computational resources. Despite recent progress in parallel and GPU computing, the ability to run fluid flow predictions in real-time is often infeasible. Recently developed machine learning approaches, which are trained on high-fidelity data, perform unsatisfactorily outside the training set and remove the ability of utilising legacy codes after training. We propose a novel methodology that uses a deep learning approach that can be used within a low-fidelity fluid flow solver to significantly increase the accuracy of the low-fidelity simulations. The resulting solver enables accurate while reducing computational times up to 100 times. The deep neural network is trained on a combination of low- and high-fidelity data, and the resulting solver is referred to as a multi-fidelity solver. The proposed methodology is demonstrated by means of enhancing a fluid flow simulator, known as PIC/FLIP, which is a popular fluid flow simulator in the field of computer generated imagery.