$${\text {FE}}^r$$ method with surrogate localization model for hyperelastic composite materials

Abstract

This study presents a method for constructing a surrogate localization model for a periodic microstructure, or equivalently, a unit cell, to efficiently perform micro-macro coupled analyses of hyperelastic composite materials. The offline process in this approach is to make a response data matrix that stores the microscopic stress distributions in response to various patterns of macroscopic deformation gradients, which is followed by the proper orthogonal decomposition (POD) of the matrix to construct a reduced order model (ROM) of the microscopic analysis (localization) with properly extracted POD bases. Then, response surfaces of the POD coefficients are constructed so that the ROM can be continuous with respect to the input datum, namely, the macroscopic deformation gradient. The novel contributions of this study are the application of the L2 regularization to the interpolation approximations of the POD coefficients by use of radial basis functions (RBFs) to make the response surfaces continuous and the combined use of the cross-validation and the Bayesian optimization to search for the optimal set of parameters in both the RBFs and L2regularization formula. The resulting model can be an alternative to microscopic finite element (FE) analyses in the conventional $${\text {FE}}^2$$ FE 2 method and realizes $${\text {FE}}^r$$ FE r with $$1<r<<2$$ 1 < r < < 2 accordingly. Representative numerical examples of micro-macro coupled analysis with the $${\text {FE}}^r$$ FE r are presented to demonstrate the capability and promise of the surrogate localization model constructed with the proposed approach in comparison with the results with high-fidelity direct $${\text {FE}}^2$$ FE 2 .

Accelerated offline setup of homogenized microscopic model for multi‐scale analyses using neural network with knowledge transfer

“…To address this computational bottleneck, the reduced order modeling (ROM) and machine learning methods are two popular approaches, to efficiently determine the micro‐structural responses in a multi‐scale analysis 15 . Broadly speaking, the ROM method considers the parametric variations of the solution in a selected low‐dimensional subspace before model deployment (offline stage), through a pre‐computation process 16‐18 . The degrees of freedom (dof) can then be reduced, for example, by using the snapshot proper orthogonal decomposition (POD), 19‐21 or the reduced basis method 22‐24 .…”

“…15 Broadly speaking, the ROM method considers the parametric variations of the solution in a selected low-dimensional subspace before model deployment (offline stage), through a pre-computation process. [16][17][18] The degrees of freedom (dof) can then be reduced, for example, by using the snapshot proper orthogonal decomposition (POD), [19][20][21] or the reduced basis method. [22][23][24] The predictive capability of ROM methods, however, may be limited by the linear projection of subspace.…”