A physics-informed GAN Framework based on Model-free Data-Driven Computational Mechanics

TL;DR

This paper introduces a novel physics-informed GAN framework that integrates data-driven computational mechanics with deep learning, enabling more accurate simulation and prediction of mechanical behaviors without relying on phenomenological models.

Contribution

It develops a new formalism combining physics-informed neural networks with GANs for model-free data-driven mechanics, enhancing simulation accuracy.

Findings

Effective integration of physics constraints into GANs.

Improved accuracy in mechanical behavior prediction.

Potential for broader application in computational mechanics.

Abstract

Model-free data-driven computational mechanics, first proposed by Kirchdoerfer and Ortiz, replace phenomenological models with numerical simulations based on sample data sets in strain-stress space. In this study, we integrate this paradigm within physics-informed generative adversarial networks (GANs). We enhance the conventional physics-informed neural network framework by implementing the principles of data-driven computational mechanics into GANs. Specifically, the generator is informed by physical constraints, while the discriminator utilizes the closest strain-stress data to discern the authenticity of the generator's output. This combined approach presents a new formalism to harness data-driven mechanics and deep learning to simulate and predict mechanical behaviors.