Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres

The study presents a comparative approach between Response Surface Methodology (RSM) and hybridized Genetic Algorithm of Artificial Neural Network (GA-ANN) in predicting the water absorption, compressive strength, flexural strength, split tensile strength and slump for steel fibre reinforced concret...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Temitope F. Awolusi, Oluwaseyi L. Oke, Olufunke O. Akinkurolere, Olumoyewa D. Atoyebi
Formato:	article
Lenguaje:	EN
Publicado:	Taylor & Francis Group 2019
Materias:	response surface methodology hybrid genetic algorithm artificial neural network concrete flexural strength steel fibre reinforced concrete civil engineering Engineering (General). Civil engineering (General) TA1-2040
Acceso en línea:	https://doaj.org/article/81a52b9c4d5d4ba2adfbb0c18330554c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:81a52b9c4d5d4ba2adfbb0c18330554c
record_format	dspace
spelling	oai:doaj.org-article:81a52b9c4d5d4ba2adfbb0c18330554c2021-11-04T15:51:56ZComparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres2331-191610.1080/23311916.2019.1649852https://doaj.org/article/81a52b9c4d5d4ba2adfbb0c18330554c2019-01-01T00:00:00Zhttp://dx.doi.org/10.1080/23311916.2019.1649852https://doaj.org/toc/2331-1916The study presents a comparative approach between Response Surface Methodology (RSM) and hybridized Genetic Algorithm of Artificial Neural Network (GA-ANN) in predicting the water absorption, compressive strength, flexural strength, split tensile strength and slump for steel fibre reinforced concrete. The effects of process variables such as aspect ratio, water–cement ratio and cement content were investigated using the central composite design of response surface methodology. This same experimental design was used in training the hybrid-training approach of artificial neural network. The predicting ability of both methodologies was compared using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Model Predictive Error (MPE) and Absolute Average Deviation (AAD). The response surface methodology model was found more accurate in being able to predict compared to the hybridized genetic algorithm of the artificial neural network.Temitope F. AwolusiOluwaseyi L. OkeOlufunke O. AkinkurolereOlumoyewa D. AtoyebiTaylor & Francis Grouparticleresponse surface methodologyhybridgenetic algorithm artificial neural networkconcreteflexural strengthsteel fibre reinforced concretecivil engineeringEngineering (General). Civil engineering (General)TA1-2040ENCogent Engineering, Vol 6, Iss 1 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	response surface methodology hybrid genetic algorithm artificial neural network concrete flexural strength steel fibre reinforced concrete civil engineering Engineering (General). Civil engineering (General) TA1-2040
spellingShingle	response surface methodology hybrid genetic algorithm artificial neural network concrete flexural strength steel fibre reinforced concrete civil engineering Engineering (General). Civil engineering (General) TA1-2040 Temitope F. Awolusi Oluwaseyi L. Oke Olufunke O. Akinkurolere Olumoyewa D. Atoyebi Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
description	The study presents a comparative approach between Response Surface Methodology (RSM) and hybridized Genetic Algorithm of Artificial Neural Network (GA-ANN) in predicting the water absorption, compressive strength, flexural strength, split tensile strength and slump for steel fibre reinforced concrete. The effects of process variables such as aspect ratio, water–cement ratio and cement content were investigated using the central composite design of response surface methodology. This same experimental design was used in training the hybrid-training approach of artificial neural network. The predicting ability of both methodologies was compared using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Model Predictive Error (MPE) and Absolute Average Deviation (AAD). The response surface methodology model was found more accurate in being able to predict compared to the hybridized genetic algorithm of the artificial neural network.
format	article
author	Temitope F. Awolusi Oluwaseyi L. Oke Olufunke O. Akinkurolere Olumoyewa D. Atoyebi
author_facet	Temitope F. Awolusi Oluwaseyi L. Oke Olufunke O. Akinkurolere Olumoyewa D. Atoyebi
author_sort	Temitope F. Awolusi
title	Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
title_short	Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
title_full	Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
title_fullStr	Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
title_full_unstemmed	Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
title_sort	comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres
publisher	Taylor & Francis Group
publishDate	2019
url	https://doaj.org/article/81a52b9c4d5d4ba2adfbb0c18330554c
work_keys_str_mv	AT temitopefawolusi comparisonofresponsesurfacemethodologyandhybridtrainingapproachofartificialneuralnetworkinmodellingthepropertiesofconcretecontainingsteelfibreextractedfromwastetyres AT oluwaseyiloke comparisonofresponsesurfacemethodologyandhybridtrainingapproachofartificialneuralnetworkinmodellingthepropertiesofconcretecontainingsteelfibreextractedfromwastetyres AT olufunkeoakinkurolere comparisonofresponsesurfacemethodologyandhybridtrainingapproachofartificialneuralnetworkinmodellingthepropertiesofconcretecontainingsteelfibreextractedfromwastetyres AT olumoyewadatoyebi comparisonofresponsesurfacemethodologyandhybridtrainingapproachofartificialneuralnetworkinmodellingthepropertiesofconcretecontainingsteelfibreextractedfromwastetyres
_version_	1718444661541961728

Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres

Ejemplares similares