Simulation of hyperelastic materials in real-time using Deep Learning

Abstract

The finite element method (FEM) is among the most commonly used numerical methods for solving engineering problems. Due to its computational cost, various ideas have been introduced to reduce computation times, such as domain decomposition, parallel computing, adaptive meshing, and model order reduction. In this paper we present U-Mesh: a data-driven method based on a U-Net architecture that approximates the non-linear relation between a contact force and the displacement field computed by a FEM algorithm. We show that deep learning, one of the latest machine learning methods based on artificial neural networks, can enhance computational mechanics through its ability to encode highly non-linear models in a compact form. Our method is applied to two benchmark examples: a cantilever beam and an L-shape subject to moving punctual loads. A comparison between our method and proper orthogonal decomposition (POD) is done through the paper. The results show that U-Mesh can perform very fast simulations on various geometries, mesh resolutions and number of input forces with very small errors.

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• DeepWarp: DNN-based Nonlinear Deformation
• Towards Fast Biomechanical Modeling of Soft Tissue Using Neural Networks

Cited by in corpus (18)

• Probabilistic Deep Learning for Real-Time Large Deformation Simulations
• 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
• Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning
• Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics
• A Review on Organ Deformation Modeling Approaches for Reliable Surgical Navigation using Augmented Reality
• Leveraging Vision and Kinematics Data to Improve Realism of Biomechanic Soft-tissue Simulation for Robotic Surgery
• Data-driven methods for computational mechanics: A fair comparison between neural networks based and model-free approaches
• A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
• DeepFEA: Deep Learning for Prediction of Transient Finite Element Analysis Solutions
• A direct Jacobian total Lagrangian explicit dynamics finite element algorithm for real-time simulation of hyperelastic materials
• Stochastic Modeling of Inhomogeneities in the Aortic Wall and Uncertainty Quantification using a Bayesian Encoder-Decoder Surrogate
• Conditional Graph Neural Network for Predicting Soft Tissue Deformation and Forces
• A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
• PerSival: Neural-network-based visualisation for pervasive continuum-mechanical simulations in musculoskeletal biomechanics
• Data-driven registration and modeling of brain deformation for image-guided neurosurgery
• Prostate motion modelling using biomechanically-trained deep neural networks on unstructured nodes