Probabilistic deep learning for real-time large deformation simulations

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 lacking information about how certain can we be their predictions. In present work, propose a highly efficient deep-learning surrogate framework that is able to accurately predict response bodies undergoing large deformations in real-time. The model has convolutional neural network architecture, called U-Net, which trained with force–displacement data obtained finite element method. We deterministic probabilistic versions framework. utilizes Variational Bayes Inference approach capture all uncertainties well model. Based on several benchmark examples, show predictive capabilities discuss its possible limitations.