Physics-constrained local convexity data-driven modeling of anisotropic nonlinear elastic solids

Abstract

As characterization and modeling of complex materials by phenomenological models remains challenging, data-driven computing that performs physical simulations directly from material data has attracted considerable attention. Data-driven computing is a general computational mechanics framework that consists of a physical solver and a material solver, based on which data-driven solutions are obtained through minimization procedures. This work develops a new material solver built upon the local convexity-preserving reconstruction scheme by He and Chen (2020) A physics-constrained data-driven approach based on locally convex reconstruction for noisy database. Computer Methods in Applied Mechanics and Engineering 363, 112791 to model anisotropic nonlinear elastic solids. In this approach, a two-level local data search algorithm for material anisotropy is introduced into the material solver in online data-driven computing. A material anisotropic state characterizing the underlying material orientation is used for the manifold learning projection in the material solver. The performance of the proposed data-driven framework with noiseless and noisy material data is validated by solving two benchmark problems with synthetic material data. The data-driven solutions are compared with the constitutive model-based reference solutions to demonstrate the effectiveness of the proposed methods.

A Feature-Encoded Physics-Informed Parameter Identification Neural Network for Musculoskeletal Systems

“…To integrate data and physical models by using ML approaches, data-driven computing that enforces constraints of conservation laws in the learning algorithms of a material database has been developed in the field of computational mechanics [ 21 – 23 ]. This paradigm has been applied to other engineering problems, such as nonlinear material modeling [ 22 , 24 , 25 ] and, fracture mechanics [ 26 ], among others. Furthermore, deep manifold embedding techniques have been introduced in data-driven computing for extracting low-dimensional feature space [ 27 , 28 ].…”

Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials

“…In recent years, machine learning (ML) based data-driven approaches have demonstrated successful applications in various engineering problems, such as solving partial differential equations [9,10,11,12], system or parameter identification [13,9,14,15,16,12,17], data-driven computational mechanics [18,19,20,21,22,2,23,24], reduced-order modeling [25,26,27,28,29,30,31], material design [32,33], etc. ML models, such as deep neural networks (DNNs), have emerged as a promising alternative for constitutive modeling due to their strong flexibility and capability in extracting complex features and patterns from data [34].…”

Deep autoencoders for physics-constrained data-driven nonlinear materials modeling

“…In this data-driven approach, the search of material data at each integration point from the material dataset is determined via a distance-minimization function and is called the distance-minimizing data-driven (DMDD) computing. This data-driven computing paradigm has been extended to dynamics [20], problems with geometrical nonlinearity [21,1], inelasticity [22], anisotropy [23], material identification and constitutive manifold construction [24,25,26,27]. A variational framework for data-driven computing was proposed in [28,29] to allow versatile in the employment of special approximation functions and numerical methods.…”