Enhanced physics-informed neural networks for hyperelasticity

Abstract

Physics-informed neural networks have gained growing interest. Specifically, they are used to solve partial differential equations governing several physical phenomena. However, physics-informed neural network models suffer from several issues and can fail to provide accurate solutions in many scenarios. We discuss a few of these challenges and the techniques, such as the use of Fourier transform, that can be used to resolve these issues. This paper proposes and develops a physics-informed neural network model that combines the residuals of the strong form and the potential energy, yielding many loss terms contributing to the definition of the loss function to be minimized. Hence, we propose using the coefficient of variation weighting scheme to dynamically and adaptively assign the weight for each loss term in the loss function. The developed PINN model is standalone and meshfree. In other words, it can accurately capture the mechanical response without requiring any labeled data. Although the framework can be used for many solid mechanics problems, we focus on three-dimensional (3D) hyperelasticity, where we consider two hyperelastic models. Once the model is trained, the response can be obtained almost instantly at any point in the physical domain, given its spatial coordinates. We demonstrate the framework's performance by solving different problems with various boundary conditions.

References in corpus (5)

• Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Exploring the structure-property relations of thin-walled, 2D extruded lattices using neural networks
• Surrogate Neural Network Model for Sensitivity Analysis and Uncertainty Quantification of the Mechanical Behavior in the Optical Lens-Barrel Assembly
• A deep learning energy method for hyperelasticity and viscoelasticity

Cited by in corpus (10)

• Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads
• Mixed formulation of physics-informed neural networks for thermo-mechanically coupled systems and heterogeneous domains
• A deep learning energy-based method for classical elastoplasticity
• Deep energy method in topology optimization applications
• DCEM: A deep complementary energy method for solid mechanics
• Applications of Scientific Machine Learning for the Analysis of Functionally Graded Porous Beams
• A physics-informed neural network for modeling fracture without gradient damage: formulation, application, and assessment
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• Experimental Learning of a Hyperelastic Behavior with a Physics-Augmented Neural Network
• Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials