Parallel Physics-Informed Neural Networks with Bidirectional Balance

TL;DR

This paper introduces a parallel physics-informed neural network framework with bidirectional balance to effectively solve complex coupled PDEs in heat transfer problems, improving convergence and accuracy where traditional PINNs fail.

Contribution

It proposes a novel parallel PINNs architecture with bidirectional balancing modules to handle unbalanced variables and complex conditions in PDEs, enhancing stability and solvability.

Findings

Achieves stable convergence in complex coupled PDEs.

Significantly improves solution accuracy over classic PINNs.

Enables solving previously unsolvable PDE problems.

Abstract

As an emerging technology in deep learning, physics-informed neural networks (PINNs) have been widely used to solve various partial differential equations (PDEs) in engineering. However, PDEs based on practical considerations contain multiple physical quantities and complex initial boundary conditions, thus PINNs often returns incorrect results. Here we take heat transfer problem in multilayer fabrics as a typical example. It is coupled by multiple temperature fields with strong correlation, and the values of variables are extremely unbalanced among different dimensions. We clarify the potential difficulties of solving such problems by classic PINNs, and propose a parallel physics-informed neural networks with bidirectional balance. In detail, our parallel solving framework synchronously fits coupled equations through several multilayer perceptions. Moreover, we design two modules to balance forward process of data and back-propagation process of loss gradient. This bidirectional balance not only enables the whole network to converge stably, but also helps to fully learn various physical conditions in PDEs. We provide a series of ablation experiments to verify the effectiveness of the proposed methods. The results show that our approach makes the PINNs unsolvable problem solvable, and achieves excellent solving accuracy.