Details
Original language | English |
---|---|
Article number | 109425 |
Journal | Composites science and technology |
Volume | 224 |
Early online date | 18 Apr 2022 |
Publication status | Published - 16 Jun 2022 |
Abstract
We present a stochastic integrated machine learning based multiscale approach for the prediction of the macroscopic thermal conductivity in carbon nanotube reinforced polymeric composites (CNT-PCs). Seven types of machine learning models are exploited, namely Multivariate Adaptive Regression Splines (MARS), Support Vector Machine (SVM), Regression Tree (RT), Bagging Tree (Bag), Random Forest (RF), Gradient Boosting Machine (GBM) and Cubist. They are used as components of stochastic modeling constructing the relationship between all uncertain inputs variables and the output of interest, the macroscopic thermal conductivity of the composite. Particle Swarm Optimization (PSO) is used for hyper-parameter tuning to find the global optimal values leading to a significant reduction in the computational cost. We also analyze the advantages and disadvantages of various methods in terms of computational expense and model complexity. We believe that the presented stochastic integrated machine learning approach accounting for uncertainties is a valuable step towards computational design of new composites for application related to thermal management.
Keywords
- Carbon nanotube reinforced polymeric composites (CNT-PCs), Computational complexity, Machine learning, Multi-scale stochastic modeling, Thermal properties
ASJC Scopus subject areas
- Materials Science(all)
- Ceramics and Composites
- Engineering(all)
- General Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Composites science and technology, Vol. 224, 109425, 16.06.2022.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites
AU - Liu, Bokai
AU - Vu-Bac, Nam
AU - Zhuang, Xiaoying
AU - Fu, Xiaolong
AU - Rabczuk, Timon
N1 - Funding Information: We gratefully acknowledge the support of the China Scholarship Council (CSC) .
PY - 2022/6/16
Y1 - 2022/6/16
N2 - We present a stochastic integrated machine learning based multiscale approach for the prediction of the macroscopic thermal conductivity in carbon nanotube reinforced polymeric composites (CNT-PCs). Seven types of machine learning models are exploited, namely Multivariate Adaptive Regression Splines (MARS), Support Vector Machine (SVM), Regression Tree (RT), Bagging Tree (Bag), Random Forest (RF), Gradient Boosting Machine (GBM) and Cubist. They are used as components of stochastic modeling constructing the relationship between all uncertain inputs variables and the output of interest, the macroscopic thermal conductivity of the composite. Particle Swarm Optimization (PSO) is used for hyper-parameter tuning to find the global optimal values leading to a significant reduction in the computational cost. We also analyze the advantages and disadvantages of various methods in terms of computational expense and model complexity. We believe that the presented stochastic integrated machine learning approach accounting for uncertainties is a valuable step towards computational design of new composites for application related to thermal management.
AB - We present a stochastic integrated machine learning based multiscale approach for the prediction of the macroscopic thermal conductivity in carbon nanotube reinforced polymeric composites (CNT-PCs). Seven types of machine learning models are exploited, namely Multivariate Adaptive Regression Splines (MARS), Support Vector Machine (SVM), Regression Tree (RT), Bagging Tree (Bag), Random Forest (RF), Gradient Boosting Machine (GBM) and Cubist. They are used as components of stochastic modeling constructing the relationship between all uncertain inputs variables and the output of interest, the macroscopic thermal conductivity of the composite. Particle Swarm Optimization (PSO) is used for hyper-parameter tuning to find the global optimal values leading to a significant reduction in the computational cost. We also analyze the advantages and disadvantages of various methods in terms of computational expense and model complexity. We believe that the presented stochastic integrated machine learning approach accounting for uncertainties is a valuable step towards computational design of new composites for application related to thermal management.
KW - Carbon nanotube reinforced polymeric composites (CNT-PCs)
KW - Computational complexity
KW - Machine learning
KW - Multi-scale stochastic modeling
KW - Thermal properties
UR - http://www.scopus.com/inward/record.url?scp=85130118707&partnerID=8YFLogxK
U2 - 10.1016/j.compscitech.2022.109425
DO - 10.1016/j.compscitech.2022.109425
M3 - Article
AN - SCOPUS:85130118707
VL - 224
JO - Composites science and technology
JF - Composites science and technology
SN - 0266-3538
M1 - 109425
ER -