Probabilistic Deep Learning for Real-Time Large Deformation Simulations

Abstract

For many novel applications, such as patient-specific computer-aided surgery, conventional solution techniques of the underlying nonlinear problems are usually computationally too expensive and are lacking information about how certain can we be about their predictions. In the present work, we propose a highly efficient deep-learning surrogate framework that is able to accurately predict the response of bodies undergoing large deformations in real-time. The surrogate model has a convolutional neural network architecture, 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. The probabilistic framework utilizes the Variational Bayes Inference approach and is able to capture all the uncertainties present in the data as well as in the deep-learning model. Based on several benchmark examples, we show the predictive capabilities of the framework and discuss its possible limitations

References in corpus (3)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• TensorFlow Distributions
• A Survey of Uncertainty in Deep Neural Networks

Cited by in corpus (11)

• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Gaussian process regression + deep neural network autoencoder for probabilistic surrogate modeling in nonlinear mechanics of solids
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics
• Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues
• 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
• From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics
• Definition and evaluation of a finite element model of the human heel for diabetic foot ulcer prevention under shearing loads
• A short perspective on a posteriori error control and adaptive discretizations
• Improved Moore-Penrose continuation algorithm for the computation of problems with critical points