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

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.

MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations

Mesh-based approaches are fundamental to solving physics-based simulations, however, they require significant computational efforts, especially for highly non-linear problems. Deep learning techniques accelerate physics-based simulations, however, they fail to perform efficiently as the size and complexity of the problem increases. Hence in this work, we propose MAgNET: Multi-channel Aggregation Network, a novel geometric deep learning framework for performing supervised learning on mesh-based graph data. MAgNET is based on the proposed MAg (Multichannel Aggregation) operation which generalises the concept of multi-channel local operations in convolutional neural networks to arbitrary non-grid inputs. MAg can efficiently perform non-linear regression mapping for graph-structured data. MAg layers are interleaved with the proposed novel graph pooling operations to constitute a graph U-Net architecture that is robust, handles arbitrary complex meshes and scales efficiently with the size of the problem. Although not limited to the type of discretisation, we showcase the predictive capabilities of MAgNET for several non-linear finite element simulations.

FEM-based Real-Time Simulations of Large Deformations with Probabilistic Deep Learning

For many engineering applications, such as real-time simulations or control, conventional solution techniques of the underlying nonlinear problems are usually computationally too expensive. In this work, we propose a highly efficient deep-learning surrogate framework that is able to predict the response of hyper-elastic bodies under load. The surrogate model takes the form of special convolutional neural network architecture, so-called U-Net, which is trained with force-displacement data obtained with the finite element method. We propose deterministic- and probabilistic versions of the framework and study it for three benchmark problems. In particular, we check the capabilities of the Maximum Likelihood and the Variational Bayes Inference formulations to assess the confidence intervals of solutions.

Distributed prediction of unsafe reconfiguration scenarios of modular-robotic Programmable Matter

We present a distributed framework for predicting whether a planned reconfiguration step of a modular robot will mechanically overload the structure, causing it to break or lose stability under its own weight. The algorithm is designed to be executed by the modular robot itself and is based on an distributed iterative solution of mechanical equilibrium equations derived from a simplified model of the robot. The model treats inter-modular connections as beams and utilizes a no-sliding unilateral contact law between the modules and the ground. We also provide a simplified algorithm for detecting instability of a rigid robot on flat ground under gravitational loading. The algorithm is verified in simulations using the Programmable Matter simulator VisibleSim, and in real-life experiments using the modular robotic system Blinky Blocks.