arXiv subjects

Chao-An Lin

Publications and source records attributed to Chao-An Lin.

4 recordsLinked to original sources

arXiv2025

Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics

Physics Informed Neural Networks offer a mesh free framework for solving PDEs but are highly sensitive to loss weight selection. We propose two dimensional analysis based weighting schemes, one based on quantifiable terms, and another also incorporating unquantifiable terms for more balanced training. Benchmarks on heat conduction, convection diffusion, and lid driven cavity flows show that the second scheme consistently improves stability and accuracy over equal weighting. Notably, in high Peclet number convection diffusion, where traditional solvers fail, PINNs with our scheme achieve stable, accurate predictions, highlighting their robustness and generalizability in CFD problems.

cs.LG↗

arXiv2025

Multi-level datasets training method in Physics-Informed Neural Networks

Physics-Informed Neural Networks have emerged as a promising methodology for solving PDEs, gaining significant attention in computer science and various physics-related fields. Despite being demonstrated the ability to incorporate the physics of laws for versatile applications, PINNs still struggle with the challenging problems which are stiff to be solved and/or have high-frequency components in the solutions, resulting in accuracy and convergence issues. It may not only increase computational costs, but also lead to accuracy loss or solution divergence. In this study, an alternative approach is proposed to mitigate the above-mentioned problems. Inspired by the multi-grid method in CFD community, the underlying idea of the current approach is to efficiently remove different frequency errors via training with different levels of training samples, resulting in a simpler way to improve the training accuracy without spending time in fine-tuning of neural network structures, loss weights as well as hyperparameters. To demonstrate the efficacy of current approach, we first investigate canonical 1D ODE with high-frequency component and 2D convection-diffusion equation with V-cycle training strategy. Finally, the current method is employed for the classical benchmark problem of steady Lid-driven cavity flows at different Reynolds numbers, to investigate the applicability and efficacy for the problem involved multiple modes of high and low frequency. By virtue of various training sequence modes, improvement through predictions lead to 30% to 60% accuracy improvement. We also investigate the synergies between current method and transfer learning techniques for more challenging problems (i.e., higher Re). From the present results, it also revealed that the current framework can produce good predictions even for the case of Re=5000, demonstrating the ability to solve complex high-frequency PDEs.

cs.LG↗

arXiv2023

Acoustics-based Active Control of Unsteady Flow Dynamics using Reinforcement Learning Driven Synthetic Jets

Flow generated noise are caused shear flows and, hence, they can be used as feedback to control the flow. Existing flow control uses state variables like velocity, pressure, or vorticity, none use acoustic observables as the primary control signal. It is tough to model a classical control algorithm using sound level but data-driven approaches are not as do not have to explicitly model the physics. We present an acoustics-driven framework for active control of unsteady wake dynamics behind a circular cylinder, in which sound is used as the primary feedback signal for flow regulation. The approach integrates deep reinforcement learning (DRL) with synthetic jet actuation, using acoustic measurements acquired from a downstream hydrophone array to inform control decisions in real time. Unlike conventional flow control strategies that rely on velocity or pressure field sensing, the proposed method establishes a direct link between far-field acoustic emissions and near-field actuation. Within this formulation, the DRL agent learns control policies that exploit acoustic signatures of vortex shedding to modulate synthetic jet actuation on the cylinder surface. The resulting control suppresses coherent wake structures and mitigates flow-induced disturbances. Quantitative results show reductions of up to 9.5\% in radiated noise and 23.8\% in drag under the tested conditions, accompanied by a marked attenuation of wake oscillations, for a DFG 2D benchmark flow with Reynolds number 100. These findings demonstrate that acoustic sensing alone can provide sufficient information for effective closed-loop flow control and highlight its potential as a non-intrusive feedback modality for coupled aerodynamic and aeroacoustic optimization in bluff-body flows. The codes for the algorithm can be found here: https://github.com/Siddharth-Rout/FlowControlDRL.

physics.flu-dyn↗

arXiv2022

Airfoil Shape Optimization using Deep Q-Network

The feasibility of using reinforcement learning for airfoil shape optimization is explored. Deep Q-Network (DQN) is used over Markov's decision process to find the optimal shape by learning the best changes to the initial shape for achieving the required goal. The airfoil profile is generated using Bezier control points to reduce the number of control variables. The changes in the position of control points are restricted to the direction normal to the chordline so as to reduce the complexity of optimization. The process is designed as a search for an episode of change done to each control point of a profile. The DQN essentially learns the episode of best changes by updating the temporal difference of the Bellman Optimality Equation. The drag and lift coefficients are calculated from the distribution of pressure coefficient along the profile computed using XFoil potential flow solver. These coefficients are used to give a reward to every change during the learning process where the ultimate aim stands to maximize the cumulate reward of an episode.

cs.LG↗