Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks

Rosa, Ana Carolina; Elomari, Youssef; Calderon, Alejandro; Mateu, Carles; Haddad, Assed; Boer, Dieter

Pertenece a la colección PC:SerieArticles

TÍTULO:

Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks - imarina:9380945

Handle:

https://hdl.handle.net/20.500.11797/imarina9380945

Autor/es de la URV:	Boer, Dieter-Thomas / Elomari, Youssef
Autor según el artículo:	Rosa, Ana Carolina; Elomari, Youssef; Calderon, Alejandro; Mateu, Carles; Haddad, Assed; Boer, Dieter
Direcció de correo del autor:	youssef.elomari@urv.cat youssef.elomari@urv.cat dieter.boer@urv.cat
Identificador del autor:	0000-0002-5532-6409
Año de publicación de la revista:	2024
Tipo de publicación:	Journal Publications
Referencia de l'ítem segons les normes APA:	Rosa, Ana Carolina; Elomari, Youssef; Calderon, Alejandro; Mateu, Carles; Haddad, Assed; Boer, Dieter (2024). Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks. Applied Sciences-Basel, 14(17), 7598-. DOI: 10.3390/app14177598
Referencia al articulo segun fuente origial:	Applied Sciences-Basel. 14 (17): 7598-
Resumen:	The energy consumption of buildings presents a significant concern, which has led to a demand for materials with better thermal performance. Thermal conductivity (TC), among the most relevant thermal properties, is essential to address this demand. This study introduces a methodology integrating a Multilayer Perceptron (MLP) and a Generative Adversarial Network (GAN) to predict the TC of concrete based on its mass composition and density. Three scenarios using experimental data from published papers and synthetic data are compared and reveal the model's outstanding performance across training, validation, and test datasets. Notably, the MLP trained on the GAN-augmented dataset outperforms the one with the real dataset, demonstrating remarkable consistency between the model's predictions and the actual values. Achieving an RMSE of 0.0244 and an R2 of 0.9975, these outcomes can offer precise quantitative information and advance energy-efficient materials.
DOI del artículo:	10.3390/app14177598
Enlace a la fuente original:	https://www.mdpi.com/2076-3417/14/17/7598
Versión del articulo depositado:	info:eu-repo/semantics/publishedVersion
Acceso a la licencia de uso:	https://creativecommons.org/licenses/by/3.0/es/
Departamento:	Enginyeria Mecànica
URL Documento de licencia:	https://repositori.urv.cat/ca/proteccio-de-dades/
Áreas temáticas:	Química Process chemistry and technology Physics, applied Materials science, multidisciplinary Materials science (miscellaneous) Materials science (all) Materiais Instrumentation General materials science General engineering Fluid flow and transfer processes Engineering, multidisciplinary Engineering (miscellaneous) Engineering (all) Engenharias ii Engenharias i Computer science applications Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências agrárias i Ciência de alimentos Chemistry, multidisciplinary Biodiversidade Astronomia / física
Palabras clave:	Thermal conductivity Thermal conductivit Powder Performance Mlp Impac Gan Concrete Compressive strength Artificial neural networks
Entidad:	Universitat Rovira i Virgili
Fecha de alta del registro:	2024-09-28

Descripción:	The energy consumption of buildings presents a significant concern, which has led to a demand for materials with better thermal performance. Thermal conductivity (TC), among the most relevant thermal properties, is essential to address this demand. This study introduces a methodology integrating a Multilayer Perceptron (MLP) and a Generative Adversarial Network (GAN) to predict the TC of concrete based on its mass composition and density. Three scenarios using experimental data from published papers and synthetic data are compared and reveal the model's outstanding performance across training, validation, and test datasets. Notably, the MLP trained on the GAN-augmented dataset outperforms the one with the real dataset, demonstrating remarkable consistency between the model's predictions and the actual values. Achieving an RMSE of 0.0244 and an R2 of 0.9975, these outcomes can offer precise quantitative information and advance energy-efficient materials.
Tipo:	Journal Publications info:eu-repo/semantics/publishedVersion
Coautor:	Enginyeria Mecànica Universitat Rovira i Virgili
Títol:	Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks
Materia:	Chemistry, Multidisciplinary,Computer Science Applications,Engineering (Miscellaneous),Engineering, Multidisciplinary,Fluid Flow and Transfer Processes,Instrumentation,Materials Science (Miscellaneous),Materials Science, Multidisciplinary,Physics, Applied,Process Chemistry and Technology Thermal conductivity Thermal conductivit Powder Performance Mlp Impac Gan Concrete Compressive strength Artificial neural networks Química Process chemistry and technology Physics, applied Materials science, multidisciplinary Materials science (miscellaneous) Materials science (all) Materiais Instrumentation General materials science General engineering Fluid flow and transfer processes Engineering, multidisciplinary Engineering (miscellaneous) Engineering (all) Engenharias ii Engenharias i Computer science applications Ciências biológicas iii Ciências biológicas ii Ciências biológicas i Ciências agrárias i Ciência de alimentos Chemistry, multidisciplinary Biodiversidade Astronomia / física
Fecha:	2024
Autor:	Rosa, Ana Carolina Elomari, Youssef Calderon, Alejandro Mateu, Carles Haddad, Assed Boer, Dieter
Derechos:	info:eu-repo/semantics/openAccess

Busca tu registro en:

Archivos desponibles
Archivo	Descripción	Formato
DocumentPrincipal	DocumentPrincipal	application/pdf

Todos los objetos de esta colección

Información