Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics
This work addresses the problem of accelerating costly mechanical simulations for researchers and engineers, but it is incremental as it applies existing or recently proposed architectures to a new domain.
The paper tackled the challenge of using deep learning surrogate models for accelerating scientific simulations in mechanics, particularly for complex real-world examples, by demonstrating that three neural network architectures (CNN U-NET, MAgNET, and Perceiver IO) can accurately predict non-linear mechanical responses of soft bodies on benchmark examples.
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.