Data Driven Computing with Noisy Material Data Sets

Abstract

We formulate a Data Driven Computing paradigm, termed max-ent Data Driven Computing, that generalizes distance-minimizing Data Driven Computing and is robust with respect to outliers. Robustness is achieved by means of clustering analysis. Specifically, we assign data points a variable relevance depending on distance to the solution and on maximum-entropy estimation. The resulting scheme consists of the minimization of a suitably-defined free energy over phase space subject to compatibility and equilibrium constraints. Distance-minimizing Data Driven schemes are recovered in the limit of zero temperature. We present selected numerical tests that establish the convergence properties of the max-ent Data Driven solvers and solutions.

References in corpus (1)

• Data-driven computational mechanics

Cited by in corpus (34)

• Model-Free Data-Driven Inelasticity
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• Data-driven fracture mechanics
• Model-Free Data-Driven Methods in Mechanics: Material Data Identification and Solvers
• FE${}^{\text{ANN}}$ $-$ An efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining
• A Physics-Constrained Data-Driven Approach Based on Locally Convex Reconstruction for Noisy Database
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• 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
• Model-data-driven constitutive responses: application to a multiscale computational framework
• A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
• Mixed-Integer Programming Formulation of a Data-Driven Solver in Computational Elasticity
• SINDy-BVP: Sparse Identification of Nonlinear Dynamics for Boundary Value Problems
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Data-Driven Rate-Dependent Fracture Mechanics
• Data-Driven Solvers for Strongly Nonlinear Material Response
• Model-Free Data-Driven Inference in Computational Mechanics
• Manifold embedding data-driven mechanics
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Simple Heuristic for Data-Driven Computational Elasticity with Material Data Involving Noise and Outliers: A Local Robust Regression Approach
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• Data-driven methods for computational mechanics: A fair comparison between neural networks based and model-free approaches
• Data-driven numerical site response
• Mechanics Informatics: A paradigm for efficiently learning constitutive models
• Mesh d-refinement: a data-based computational framework to account for complex material response
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method: Extension to geometrical parameterizations
• Three-Dimensional Data-Driven Magnetostatic Field Computation using Real-World Measurement Data
• Interdependent evolution of robustness, force transmission and damage in a heterogeneous quasi-brittle granular material: from suppressed to cascading failure
• Data-driven Computing in Elasticity via Chebyshev Approximation
• Data Driven Finite Element Method: Theory and Applications
• Data-Driven Computing in Dynamics
• Solving strategies for data-driven one-dimensional elasticity exhibiting nonlinear strains
• A Framework for Data-Driven Computational Mechanics Based on Nonlinear Optimization