Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics

Abstract

Deep learning surrogate models are being increasingly used in accelerating scientific simulations as a replacement for costly conventional numerical techniques. However, their use remains a significant challenge when dealing with real-world complex examples. In this work, we demonstrate three types of neural network architectures for efficient learning of highly non-linear deformations of solid bodies. The first two architectures are based on the recently proposed CNN U-NET and MAgNET (graph U-NET) frameworks which have shown promising performance for learning on mesh-based data. The third architecture is Perceiver IO, a very recent architecture that belongs to the family of attention-based neural networks--a class that has revolutionised diverse engineering fields and is still unexplored in computational mechanics. We study and compare the performance of all three networks on two benchmark examples, and show their capabilities to accurately predict the non-linear mechanical responses of soft bodies.

References in corpus (3)

• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Open-Full-Jaw: An open-access dataset and pipeline for finite element models of human jaw
• Neural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEs

Cited by in corpus (4)

• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Gaussian process regression + deep neural network autoencoder for probabilistic surrogate modeling in nonlinear mechanics of solids
• A short perspective on a posteriori error control and adaptive discretizations