Manifold embedding data-driven mechanics
arXiv:2112.09842 · doi:10.1016/j.jmps.2022.104927
Abstract
This article introduces a new data-driven approach that leverages a manifold embedding generated by the invertible neural network to improve the robustness, efficiency, and accuracy of the constitutive-law-free simulations with limited data. We achieve this by training a deep neural network to globally map data from the constitutive manifold onto a lower-dimensional Euclidean vector space. As such, we establish the relation between the norm of the mapped Euclidean vector space and the metric of the manifold and lead to a more physically consistent notion of distance for the material data. This treatment in return allows us to bypass the expensive combinatorial optimization, which may significantly speed up the model-free simulations when data are abundant and of high dimensions. Meanwhile, the learning of embedding also improves the robustness of the algorithm when the data is sparse or distributed unevenly in the parametric space. Numerical experiments are provided to demonstrate and measure the performance of the manifold embedding technique under different circumstances. Results obtained from the proposed method and those obtained via the classical energy norms are compared.
References in corpus (24)
- Adam: A Method for Stochastic Optimization
- Hyperparameters and Tuning Strategies for Random Forest
- Reconciling modern machine learning practice and the bias-variance trade-off
- Deep learning for universal linear embeddings of nonlinear dynamics
- NICE: Non-linear Independent Components Estimation
- Data-driven computational mechanics
- Model-Free Data-Driven Inelasticity
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- Data Driven Computing with Noisy Material Data Sets
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- Data-driven fracture mechanics
- Data driven problems in elasticity
- A Physics-Constrained Data-Driven Approach Based on Locally Convex Reconstruction for Noisy Database
- Model-free Data-Driven Computational Mechanics Enhanced by Tensor Voting
- Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
- Efficient Data Structures for Model-free Data-Driven Computational Mechanics
- Deep Learning Models for Global Coordinate Transformations that Linearize PDEs
- BourGAN: Generative Networks with Metric Embeddings
- An accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data
- Simple Heuristic for Data-Driven Computational Elasticity with Material Data Involving Noise and Outliers: A Local Robust Regression Approach
- Uncertainty quantification for complex systems with very high dimensional response using Grassmann manifold variations
- Deep Learning of Conjugate Mappings
- Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
- Manifold Denoising by Nonlinear Robust Principal Component Analysis