Fine-tuning physics-informed neural networks for cavity flows using coordinate transformation

TL;DR

This paper introduces a coordinate transformation-based fine-tuning method for physics-informed neural networks to efficiently model cavity flows with various geometries, reducing training costs and improving convergence.

Contribution

It proposes a novel fine-tuning approach for PINNs using coordinate transformation, enabling effective transfer learning across different cavity geometries.

Findings

Fine-tuning improves training convergence over random initialization.

Pre-trained models with similar geometry enhance training efficiency.

Method applicable to real-world blood flow modeling in clinical settings.

Abstract

Physics-informed neural networks (PINNs) have attracted attention as an alternative approach to solve partial differential equations using a deep neural network (DNN). Their simplicity and capability allow them to solve inverse problems for many applications. Despite the versatility of PINNs, it remains challenging to reduce their training cost. Using a DNN pre-trained with an arbitrary dataset with transfer learning or fine-tuning is a potential solution. However, a pre-trained model using a different geometry and flow condition than the target may not produce suitable results. This paper proposes a fine-tuning approach for PINNs with coordinate transformation, modelling lid-driven cavity flows with various shapes. We formulate the inverse problem, where the reference data inside the domain and wall boundary conditions are given. A pre-trained PINN model with an arbitrary Reynolds number and shape is used to initialize a target DNN. To reconcile the reference shape with different targets, governing equations as a loss of the PINNs are given with coordinate transformation using a deformation gradient tensor. Numerical examples for various cavity flows with square, rectangular, shear deformed and inflated geometries demonstrate that the proposed fine-tuning approach improves the training convergence compared with a randomly-initialized model. A pre-trained model with a similar geometry to the target further increases training efficiency. These findings are useful for real-world applications such as modelling intra-aneurysmal blood flows in clinical use.