A Mixed Wavelet-Learning Method of Predicting Macroscopic Effective Heat Transfer Conductivities of Braided Composite Materials

A Mixed Wavelet-Learning Method of Predicting Macroscopic Effective Heat Transfer Conductivities of Braided Composite Materials

Year:    2022

Author:    Hao Dong, Wenbo Kou, Junyan Han, Jiale Linghu, Minqiang Zou, Junzhi Cui

Communications in Computational Physics, Vol. 31 (2022), Iss. 2 : pp. 593–625

Abstract

In this paper, a novel mixed wavelet-learning method is developed for predicting macroscopic effective heat transfer conductivities of braided composite materials with heterogeneous thermal conductivity. This innovative methodology integrates respective superiorities of multi-scale modeling, wavelet transform and neural networks together. By the aid of asymptotic homogenization method (AHM), off-line multi-scale modeling is accomplished for establishing the material database with high-dimensional and highly-complex mappings. The multi-scale material database and the wavelet-learning strategy ease the on-line training of neural networks, and enable us to efficiently build relatively simple networks that have an essentially increasing capacity and resisting noise for approximating the high-complexity mappings. Moreover, it should be emphasized that the wavelet-learning strategy can not only extract essential data characteristics from the material database, but also achieve a tremendous reduction in input data of neural networks. The numerical experiments performed using multiple 3D braided composite models verify the excellent performance of the presented mixed approach. The numerical results demonstrate that the mixed wavelet-learning methodology is a robust method for computing the macroscopic effective heat transfer conductivities with distinct heterogeneity patterns. The presented method can enormously decrease the computational time, and can be further expanded into estimating macroscopic effective mechanical properties of braided composites.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/cicp.OA-2021-0110

Communications in Computational Physics, Vol. 31 (2022), Iss. 2 : pp. 593–625

Published online:    2022-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    33

Keywords:    Braided composite materials macroscopic effective heat transfer conductivities multi-scale modeling neural networks wavelet transform.

Author Details

Hao Dong

Wenbo Kou

Junyan Han

Jiale Linghu

Minqiang Zou

Junzhi Cui

  1. Continuous-discrete extended Kalman filter based parameter identification method for space robots in postcapture

    Zhang, Teng | Shi, Peng | Yang, Yang | Li, Wenlong | Yue, Xiaokui

    Nonlinear Dynamics, Vol. 112 (2024), Iss. 23 P.21205

    https://doi.org/10.1007/s11071-024-10079-y [Citations: 0]
  2. Integrated wavelet-learning method for macroscopic mechanical properties prediction of concrete composites with hierarchical random configurations

    Dong, Hao | Linghu, Jiale | Nie, Yufeng

    Composite Structures, Vol. 304 (2023), Iss. P.116357

    https://doi.org/10.1016/j.compstruct.2022.116357 [Citations: 4]
  3. Self-optimization wavelet-learning method for predicting nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations

    Linghu, Jiale | Dong, Hao | Gao, Weifeng | Nie, Yufeng

    Computer Physics Communications, Vol. 295 (2024), Iss. P.108969

    https://doi.org/10.1016/j.cpc.2023.108969 [Citations: 1]