Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture

TL;DR

This paper develops a physics-informed neural network to simulate the thermochemical curing process of composite materials, incorporating complex physics, interface discontinuities, and parameter variations for real-time predictions.

Contribution

It introduces a novel PINN architecture with disconnected subnetworks and a sequential training algorithm to handle coupled heat transfer and cure kinetics, including interface discontinuities and parameter inputs.

Findings

The PINN accurately models the curing process across various scenarios.

Including problem parameters enables real-time surrogate modeling.

Transfer learning reduces training time for similar problem settings.

Abstract

We present a Physics-Informed Neural Network (PINN) to simulate the thermochemical evolution of a composite material on a tool undergoing cure in an autoclave. In particular, we solve the governing coupled system of differential equations -- including conductive heat transfer and resin cure kinetics -- by optimizing the parameters of a deep neural network (DNN) using a physics-based loss function. To account for the vastly different behaviour of thermal conduction and resin cure, we design a PINN consisting of two disconnected subnetworks, and develop a sequential training algorithm that mitigates instability present in traditional training methods. Further, we incorporate explicit discontinuities into the DNN at the composite-tool interface and enforce known physical behaviour directly in the loss function to improve the solution near the interface. We train the PINN with a technique that automatically adapts the weights on the loss terms corresponding to PDE, boundary, interface, and initial conditions. Finally, we demonstrate that one can include problem parameters as an input to the model -- resulting in a surrogate that provides real-time simulation for a range of problem settings -- and that one can use transfer learning to significantly reduce the training time for problem settings similar to that of an initial trained model. The performance of the proposed PINN is demonstrated in multiple scenarios with different material thicknesses and thermal boundary conditions.