A novel Trunk Branch-net PINN for flow and heat transfer prediction in porous medium
This work addresses complex flow and heat transfer problems in porous media for engineering applications, but it appears incremental as it builds upon existing PINN methods with architectural modifications.
The authors tackled the challenge of predicting flow and heat transfer in porous media, which is complex and not handled by original PINNs, by developing a novel Trunk-Branch-net PINN architecture that demonstrated effectiveness in forward and inverse problems, with validation through transfer learning and superiority over traditional numerical methods.
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.