Stochastic integrated machine learning based multiscale approach for the prediction of the thermal conductivity in carbon nanotube reinforced polymeric composites

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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Composites science and technology Ročník 224; s. 109425
Hlavní autori: Liu, Bokai, Vu-Bac, Nam, Zhuang, Xiaoying, Fu, Xiaolong, Rabczuk, Timon
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Barking Elsevier Ltd 16.06.2022
Elsevier BV
Predmet:
Carbon
Carbon nanotube reinforced polymeric composites (CNT-PCs)
Carbon nanotubes
Composite materials
Computational complexity
Computing costs
Cost analysis
Heat conductivity
Heat transfer
Machine learning
Multi-scale stochastic modeling
Multiscale analysis
Nanotubes
Particle swarm optimization
Regression analysis
Stochastic models
Support vector machines
Thermal conductivity
Thermal management
Thermal properties
Thermal properties
Carbon nanotube reinforced polymeric composites (CNT-PCs)
Multi-scale stochastic modeling
Computational complexity
Machine learning
ISSN:0266-3538, 1879-1050
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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. [Display omitted]
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0266-3538
1879-1050
DOI:10.1016/j.compscitech.2022.109425