I-FENN with Temporal Convolutional Networks: expediting the load-history analysis of non-local gradient damage propagation

Abstract

In this paper, we demonstrate for the first time how the Integrated Finite Element Neural Network (I-FENN) framework, previously proposed by the authors, can efficiently simulate the entire loading history of non-local gradient damage propagation. To achieve this goal, we first adopt a Temporal Convolutional Network (TCN) as the neural network of choice to capture the history-dependent evolution of the non-local strain in a coarsely meshed domain. The quality of the network predictions governs the computational performance of I-FENN, and therefore we perform an extended investigation aimed at enhancing them. We explore a data-driven vs. physics-informed TCN setup to arrive at an optimum network training, evaluating the network based on a coherent set of relevant performance metrics. We address the crucial issue of training a physics-informed network with input data that span vastly different length scales by proposing a systematic way of input normalization and output un-normalization. We then integrate the trained TCN within the nonlinear iterative FEM solver and apply I-FENN to simulate the damage propagation analysis. I-FENN is always applied in mesh idealizations different from the one used for the TCN training, showcasing the framework's ability to be used at progressively refined mesh resolutions. We illustrate several cases that I-FENN completes the simulation using either a modified or a full Newton-Raphson scheme, and we showcase its computational savings compared to both the classical monolithic and staggered FEM solvers. We underline that we satisfy very strict convergence criteria for every increment across the entire simulation, providing clear evidence of the robustness and accuracy of I-FENN. All the code and data used in this work will be made publicly available upon publication of the article.

References in corpus (19)

• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Data-driven computational mechanics
• A survey on modern trainable activation functions
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• A machine learning based plasticity model using proper orthogonal decomposition
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Deep Learning in Deterministic Computational Mechanics
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• Data-driven fracture mechanics
• On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Automatic differentiation in ML: Where we are and where we should be going
• Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance

Cited by in corpus (1)

• Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials