Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems

TL;DR

This paper introduces RA-PINN, a novel neural network framework that effectively models complex electrothermal multiphysics systems with strong nonlinear coupling, achieving high accuracy and robustness in steady-state simulations.

Contribution

The paper presents RA-PINN, a residual attention-based physics-informed neural network that captures localized coupling and steep gradients in multiphysics electrothermal simulations, outperforming existing methods.

Findings

RA-PINN achieves the lowest errors across benchmarks.

It maintains high accuracy in interface-dominated and variable-coefficient scenarios.

RA-PINN outperforms Pure-MLP, LSTM-PINN, and pLSTM-PINN in accuracy and robustness.

Abstract

Efficient thermal management and precise field prediction are critical for the design of advanced energy systems, including electrohydrodynamic transport, microfluidic energy harvesters, and electrically driven thermal regulators. However, the steady-state simulation of these electrothermal coupled multiphysics systems remains challenging for physics-informed neural computation due to strong nonlinear field coupling, temperature-dependent coefficient variability, and complex interface dynamics. This study proposes a Residual Attention Physics-Informed Neural Network (RA-PINN) framework for the unified solution of coupled velocity, pressure, electric-potential, and temperature fields. By integrating a unified five-field operator formulation with residual-connected feature propagation and attention-guided channel modulation, the proposed architecture effectively captures localized coupling structures and steep gradients. We evaluate RA-PINN across four representative energy-relevant benchmarks: constant-coefficient coupling, indirect pressure-gauge constraints, temperature-dependent transport, and oblique-interface consistency. Comparative analysis against Pure-MLP, LSTM-PINN, and pLSTM-PINN demonstrates that RA-PINN achieves superior accuracy, yielding the lowest MSE, RMSE, and relative $L_2$ errors across all scenarios. Notably, RA-PINN maintains high structural fidelity in interface-dominated and variable-coefficient settings where conventional PINN backbones often fail. These results establish RA-PINN as a robust and accurate computational framework for the high-fidelity modeling and optimization of complex electrothermal multiphysics in sustainable energy applications.