Graph Neural Network Surrogates for Contacting Deformable Bodies with Necessary and Sufficient Contact Detection

TL;DR

This paper introduces a graph neural network model for contact detection between deformable bodies, incorporating sufficient conditions and continuous collision detection, enabling rapid and accurate predictions in complex soft tissue mechanics scenarios.

Contribution

The work presents the first GNN architecture that uses sufficient contact conditions and continuous collision detection for deformable bodies, improving accuracy and generalization over existing methods.

Findings

Achieves up to a thousand-fold inference speedup.

Regularization with contact terms improves generalization.

Handles varying geometries and complex contact scenarios.

Abstract

Surrogate models for the rapid inference of nonlinear boundary value problems in mechanics are helpful in a broad range of engineering applications. However, effective surrogate modeling of applications involving the contact of deformable bodies, especially in the context of varying geometries, is still an open issue. In particular, existing methods are confined to rigid body contact or, at best, contact between rigid and soft objects with well-defined contact planes. Furthermore, they employ contact or collision detection filters that serve as a rapid test but use only the necessary and not sufficient conditions for detection. In this work, we present a graph neural network architecture that utilizes continuous collision detection and, for the first time, incorporates sufficient conditions designed for contact between soft deformable bodies. We test its performance on two benchmarks, including a problem in soft tissue mechanics of predicting the closed state of a bioprosthetic aortic valve. We find a regularizing effect on adding additional contact terms to the loss function, leading to better generalization of the network. These benefits hold for simple contact at similar planes and element normal angles, and complex contact at differing planes and element normal angles. We also demonstrate that the framework can handle varying reference geometries. However, such benefits come with high computational costs during training, resulting in a trade-off that may not always be favorable. We quantify the training cost and the resulting inference speedups on various hardware architectures. Importantly, our graph neural network implementation results in up to a thousand-fold speedup for our benchmark problems at inference.