A robust solution of a statistical inverse problem in multiscale computational mechanics using an artificial neural network

DOI10.1016/J.CMA.2020.113540zbMath1506.74488arXiv2011.11761OpenAlexW3103013643MaRDI QIDQ2020855

Florent Pled, Tian-Yu Zhang, Christophe Desceliers

Publication date: 26 April 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.11761

zbMATH Keywords

machine learninguncertainty quantificationprobabilistic modelingstatistical inverse problemrandom heterogeneous materialsrandom multiscale modeling

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Applications of statistics in engineering and industry; control charts (62P30) Probabilistic models, generic numerical methods in probability and statistics (65C20) Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Inverse problems in equilibrium solid mechanics (74G75) Homogenization in equilibrium problems of solid mechanics (74Q05) Neural nets and related approaches to inference from stochastic processes (62M45) Stochastic and other probabilistic methods applied to problems in solid mechanics (74S60)

Related Items (7)

Multiscale modeling of inelastic materials with thermodynamics-based artificial neural networks (TANN) ⋮ Computational stochastic homogenization of heterogeneous media from an elasticity random field having an uncertain spectral measure ⋮ Interfacing finite elements with deep neural operators for fast multiscale modeling of mechanics problems ⋮ Data-driven elasto-(visco)-plasticity involving hidden state variables ⋮ A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content ⋮ AI in computational mechanics and engineering sciences ⋮ A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites

Uses Software

• Neural Network Toolbox
• FEAPpv

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Uncertainty quantification. An accelerated course with advanced applications in computational engineering
• Identification of high-dimension polynomial chaos expansions with random coefficients for non-Gaussian tensor-valued random fields using partial and limited experimental data
• A computational inverse method for identification of non-Gaussian random fields using the Bayesian approach in very high dimension
• A stochastic-deterministic coupling method for continuum mechanics
• Random matrix theory for modeling uncertainties in computational mechanics
• Inversion of probabilistic structural models using measured transfer functions
• Stochastic spectral methods for efficient Bayesian solution of inverse problems
• Efficient Monte Carlo computation of Fisher information matrix using prior information
• Identification of Bayesian posteriors for coefficients of chaos expansions
• Dimensionality reduction and polynomial chaos acceleration of Bayesian inference in inverse problems
• Identification of chaos representations of elastic properties of random media using experimental vibration tests
• Polynomial chaos representation of spatio-temporal random fields from experimental measurements
• Approximations of effective coefficients in stochastic homogenization
• Maximum entropy, information without probability and complex fractals. Classical and quantum approach
• Multilayer feedforward networks are universal approximators
• Statistical and computational inverse problems.
• Non-Gaussian positive-definite matrix-valued random fields for elliptic stochastic partial differential operators
• On the construction and analysis of stochastic models: characterization and propagation of the errors associated with limited data
• Kernel Smoothing in Matlab
• Modeling of random anisotropic elastic media and impact on wave propagation
• Information Theory and Statistical Mechanics
• Approximation Theorems of Mathematical Statistics
• Maximum likelihood estimation of stochastic chaos representations from experimental data
• An efficient Bayesian inference approach to inverse problems based on an adaptive sparse grid collocation method
• Universal approximation bounds for superpositions of a sigmoidal function
• Probability Theory
• Computational Statistics
• Identification of Polynomial Chaos Representations in High Dimension from a Set of Realizations
• Multivariate Density Estimation
• Elements of Information Theory
• Monte Carlo Solution of Nonlinear Vibrations
• Approximation by superpositions of a sigmoidal function
• Random heterogeneous materials. Microstructure and macroscopic properties

This page was built for publication: A robust solution of a statistical inverse problem in multiscale computational mechanics using an artificial neural network