Data-driven computational mechanics have been used in the field of multiscale analysis where the constitutive modeling of composites is obtained by learning the material database obtained experimentally or numerically, using artificial neural network (ANN). In this paper, we present a data-driven multiscale analysis by combining the cluster-based non-uniform transformation field analysis (CNTFA), a reduced order model for the numerical homogenization of composites with periodically arranged microstructure, with ANN. Here, the CNTFA which was developed by the authors is efficient reduced order model for multiscale analysis of different nonlinear composites. Feed-forward neural network, a neural network is designed and trained for calculating the material stiffness and reproducing the microscale field quantities. The stiffness of homogenized material is approximately calculated using the gradient of ANN and strain concentration tensor. The proposed method can be effectively used in reproduction of field information (e.g. strain and stress) at the microscale as well as the analysis of structures at the macroscale. This property is distinguished with other cluster based methods such as SCA, VCA, FCA, in which the field information is reproduced at cluster level, not microscale level. An example calculation of three-point bending beam shows that the proposed method is very effective for the multiscale analysis of nonlinear composite structures.
| Published in | Science Frontiers (Volume 6, Issue 4) |
| DOI | 10.11648/j.sf.20250604.11 |
| Page(s) | 122-132 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
ANN, Data-driven Computational Mechanics, Cluster-based Non-uniform Transformation Field Analysis, Reproduction
| [1] | Ramberg W, Osgood WR. Description of stress-strain curve by three parameters. NACA TN No. 902(1943). |
| [2] | Chen SH, Pande GN. Rheological model and finite element analysis of jointed rock masses reinforced by passive fully-grouted bolts. Int J Rock Mech Min Sci & Geomech Abstr 1994; 31(3): 273-7. |
| [3] | Pietruszczak S, Pande GN. Constitutive relations for partially saturated soils containing gas inclusions. J Geotech Eng ASCE 1996; January: 50-9. |
| [4] | Melro AR, Camanho PP, Pires FMA, Pinho ST. Micromechanical analysis of polymer composites reinforced by unidirectional fibres: Part I - constitutive modeling. Int J Solids Struct 2013; 50(11-12): 1897-905. |
| [5] | Alotta O. Barrera A. C. F. Cocks, Di Paola M. On the behavior of a three-dimensional fractional viscoelastic constitutive model. Meccanica 2017; 52(9): 2127-2142. |
| [6] | Ghaboussi J, Garrett Jr J, Wu X. Knowledge-based modeling of material behavior with neural networks. J Engin Mech 1991; 117(1); 132-153. |
| [7] | Ghaboussi J, Pecknold D. A, Zhang M, Haj-Ali R. M. Autoprogressive training of neural network constitutive models. Int J Numer Meth Eng 1998; 42(1): 105-126. |
| [8] | Hashash Y, Jung S, Ghaboussi J. Numerical implementation of a neural network based material model in finite element analysis. Int J Numer Meth Eng 2004; 59(7): 989-1005. |
| [9] | Jung S, Ghaboussi J. Neural network constitutive model for rate-dependent materials. Comput & Struct 2006; 84(15-16): 955-963. |
| [10] | Dvorak GJ. Transformation field analysis of inelastic composite materials. Roy Soc Lond A: Math Phys Eng Sci 1900; 1992(437): 311-27. |
| [11] | Michel JC, Suquet P. Computational analysis of nonlinear composite structures using the nonuniform transformation field analysis. Comput Methods Appl Mech Eng 2004; 193(48): 5477-502. |
| [12] | Felix Fritzen, Oliver Kunc. Two-stage data-driven homogenization for nonlinear solids using a reduced order model. European Journal of Mechanics / A Solids. |
| [13] | Liu Z, Bessa M, Liu W. Self-consistent clustering analysis: an efficient multi-scale scheme for inelastic heterogeneous materials. Comput Meth Appl Mech Eng 2016; 306-319. |
| [14] | Tang S, Zhang L, Liu WK. From virtual clustering analysis to self-consistent clustering analysis: a mathematical study. Comput Mech 2018; 1-18. |
| [15] | Cheng G, Li X, Nie Y, Li H. FEM-Cluster based reduction method for efficient numerical prediction of effective properties of heterogeneous material in nonlinear range. Comput Meth Appl Mech Eng 2019; 348: 157-184. |
| [16] | Jun-Hyok Ri, Hyon-Sik Hong, Sung-Gyu Ri. Cluster Based Nonuniform Transformation Field Analysis: An Efficient Homogenization for Inelastic Heterogeneous Materials. Int J Numer Meth Engng. 2021; 00: 1-37. |
| [17] | Jun-Hyok Ri, Un-Il Ri, Hyon-Sik Hong. Multiscale analysis of elastic-viscoplastic composite using a cluster-based reduced order model. Compos Struct. |
| [18] | Un-Il Ri, Jun-Hyok Ri, Hyon-Sik Hong. Multiscale computational homogenization for woven composites using the cluster-based nonuniform transformation field analysis. Arch Appl Mech. 2023; 93: 1797-1808. |
| [19] | Li H, Kafka O. L, Gao J, Yu C, Nie Y, Zhang L, Tajdari M, Tang S, Guo X, Li G. Clustering discretization methods for generation of material performance databases in machine learning and design optimization. Comput Mech. 2019; 64(2): 281-305. |
| [20] | Wing KL, George K, Shaoqiang T, Julien Y. A computational mechanics special issue on: data‑driven modeling and simulation-theory, methods, and applications. Comput Mech. 2019; 64: 275-277. |
| [21] | Xin L. How machine learning can help the design and analysis of composite materials and structures? Compos Mat. 2021 (conference paper). arXiv: 2010.09438v1. |
| [22] | Yang H, Guo X, Tang S, Liu WK. Derivation of heterogeneous material laws via data-driven principal component expansions. Comput Mech. 2019; 64(2): 365-379. |
| [23] | Xu K, Darve E. Physics constrained learning for data-driven inverse modeling from sparse observations. arXiv preprint arXiv: 2002.10521, 2020. |
| [24] | Jiaying G, Modesar S, Gino D, Matthias M, Guowei Z, Danielle Z, Xuming S, Wing KL. Predictive multiscale modeling for Unidirectional Carbon Fiber Reinforced Polymers. Compos Sci Tech. 2020; 186: 107922. |
| [25] | Modesar S, Jiaying G, Zeliang L, Liu WK. A Data-Driven Multiscale Theory for Modeling Damage and Fracture of Composite Materials. Part of the lecture Lote in Computational Science and Engineering book series (LNCSE, Volume 129). |
APA Style
Ri, U., Ri, J., Hong, H., Kim, Y., Ri, J. (2025). A Data-driven Multiscale Analysis by Combination of Cluster-based Non-uniform Transformation Field Analysis and Artificial Neural Network. Science Frontiers, 6(4), 122-132. https://doi.org/10.11648/j.sf.20250604.11
ACS Style
Ri, U.; Ri, J.; Hong, H.; Kim, Y.; Ri, J. A Data-driven Multiscale Analysis by Combination of Cluster-based Non-uniform Transformation Field Analysis and Artificial Neural Network. Sci. Front. 2025, 6(4), 122-132. doi: 10.11648/j.sf.20250604.11
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.sf.20250604.11,
author = {Un-Il Ri and Jun-Hyok Ri and Hyon-Sik Hong and Yong-Chol Kim and Jin-Chol Ri},
title = {A Data-driven Multiscale Analysis by Combination of Cluster-based Non-uniform Transformation Field Analysis and Artificial Neural Network
},
journal = {Science Frontiers},
volume = {6},
number = {4},
pages = {122-132},
doi = {10.11648/j.sf.20250604.11},
url = {https://doi.org/10.11648/j.sf.20250604.11},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sf.20250604.11},
abstract = {Data-driven computational mechanics have been used in the field of multiscale analysis where the constitutive modeling of composites is obtained by learning the material database obtained experimentally or numerically, using artificial neural network (ANN). In this paper, we present a data-driven multiscale analysis by combining the cluster-based non-uniform transformation field analysis (CNTFA), a reduced order model for the numerical homogenization of composites with periodically arranged microstructure, with ANN. Here, the CNTFA which was developed by the authors is efficient reduced order model for multiscale analysis of different nonlinear composites. Feed-forward neural network, a neural network is designed and trained for calculating the material stiffness and reproducing the microscale field quantities. The stiffness of homogenized material is approximately calculated using the gradient of ANN and strain concentration tensor. The proposed method can be effectively used in reproduction of field information (e.g. strain and stress) at the microscale as well as the analysis of structures at the macroscale. This property is distinguished with other cluster based methods such as SCA, VCA, FCA, in which the field information is reproduced at cluster level, not microscale level. An example calculation of three-point bending beam shows that the proposed method is very effective for the multiscale analysis of nonlinear composite structures.
},
year = {2025}
}
TY - JOUR T1 - A Data-driven Multiscale Analysis by Combination of Cluster-based Non-uniform Transformation Field Analysis and Artificial Neural Network AU - Un-Il Ri AU - Jun-Hyok Ri AU - Hyon-Sik Hong AU - Yong-Chol Kim AU - Jin-Chol Ri Y1 - 2025/09/26 PY - 2025 N1 - https://doi.org/10.11648/j.sf.20250604.11 DO - 10.11648/j.sf.20250604.11 T2 - Science Frontiers JF - Science Frontiers JO - Science Frontiers SP - 122 EP - 132 PB - Science Publishing Group SN - 2994-7030 UR - https://doi.org/10.11648/j.sf.20250604.11 AB - Data-driven computational mechanics have been used in the field of multiscale analysis where the constitutive modeling of composites is obtained by learning the material database obtained experimentally or numerically, using artificial neural network (ANN). In this paper, we present a data-driven multiscale analysis by combining the cluster-based non-uniform transformation field analysis (CNTFA), a reduced order model for the numerical homogenization of composites with periodically arranged microstructure, with ANN. Here, the CNTFA which was developed by the authors is efficient reduced order model for multiscale analysis of different nonlinear composites. Feed-forward neural network, a neural network is designed and trained for calculating the material stiffness and reproducing the microscale field quantities. The stiffness of homogenized material is approximately calculated using the gradient of ANN and strain concentration tensor. The proposed method can be effectively used in reproduction of field information (e.g. strain and stress) at the microscale as well as the analysis of structures at the macroscale. This property is distinguished with other cluster based methods such as SCA, VCA, FCA, in which the field information is reproduced at cluster level, not microscale level. An example calculation of three-point bending beam shows that the proposed method is very effective for the multiscale analysis of nonlinear composite structures. VL - 6 IS - 4 ER -
Institute of Mechanics, State Academy of Sciences, Pyongyang, Democratic People's Republic of Korea
Department of Coal Mining Construction Engineering, Pyongsong University of Coal Mining, Pyongsong, Democratic People's Republic of Korea
Information