Physics-guided deep reinforcement learning for flow field denoising

TL;DR

This paper introduces a physics-guided deep reinforcement learning model that reconstructs flow fields from noisy data by integrating physical constraints and reinforcement learning, achieving accurate results without requiring target training data.

Contribution

The study presents a novel PGDRL model combining DRL with physical constraints for flow field reconstruction without target data, enhancing efficiency and interpretability.

Findings

Successfully reconstructs flow fields from noisy data

Reproduces flow statistics and spectral content accurately

Reduces experimental and computational costs

Abstract

A multi-agent deep reinforcement learning (DRL)-based model is presented in this study to reconstruct flow fields from noisy data. A combination of the reinforcement learning with pixel-wise rewards (PixelRL), physical constraints represented by the momentum equation and the pressure Poisson equation and the known boundary conditions is utilised to build a physics-guided deep reinforcement learning (PGDRL) model that can be trained without the target training data. In the PGDRL model, each agent corresponds to a point in the flow field and it learns an optimal strategy for choosing pre-defined actions. The proposed model is efficient considering the visualisation of the action map and the interpretation of the model performance. The performance of the model is tested by utilising synthetic direct numerical simulation (DNS)-based noisy data and experimental data obtained by particle image velocimetry (PIV). Qualitative and quantitative results show that the model can reconstruct the flow fields and reproduce the statistics and the spectral content with commendable accuracy. These results demonstrate that the combination of DRL-based models and the known physics of the flow fields can potentially help solve complex flow reconstruction problems, which can result in a remarkable reduction in the experimental and computational costs.