A novel Trunk Branch-net PINN for flow and heat transfer prediction in porous medium

TL;DR

This paper introduces a novel Trunk-Branch PINN architecture that effectively captures global and local features to solve complex flow and heat transfer problems in porous media, outperforming traditional methods especially in inverse problems.

Contribution

The paper proposes a new Trunk-Branch PINN architecture that enhances the ability to solve complex flow and heat transfer problems in porous media, including inverse and transfer learning tasks.

Findings

Demonstrates effectiveness on forward flow and heat transfer problems.

Validates transfer learning capability for resource reuse.

Shows superiority over traditional numerical methods in inverse problems.

Abstract

A novel Trunk-Branch (TB)-net physics-informed neural network (PINN) architecture is developed, which is a PINN-based method incorporating trunk and branch nets to capture both global and local features. The aim is to solve four main classes of problems: forward flow problem, forward heat transfer problem, inverse heat transfer problem, and transfer learning problem within the porous medium, which are notoriously complex that could not be handled by origin PINN. In the proposed TB-net PINN architecture, a Fully-connected Neural Network (FNN) is used as the trunk net, followed by separated FNNs as the branch nets with respect to outputs, and automatic differentiation is performed for partial derivatives of outputs with respect to inputs by considering various physical loss. The effectiveness and flexibility of the novel TB-net PINN architecture is demonstrated through a collection of forward problems, and transfer learning validates the feasibility of resource reuse. Combining with the superiority over traditional numerical methods in solving inverse problems, the proposed TB-net PINN shows its great potential for practical engineering applications.