Staff View: Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study

Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study

Ultra-high-performance geopolymer concrete (UHPGC) is a new category of traditional UHPC developed to meet the desire for ultra-high-strength and green building materials. In the current study, random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGB) are used to forec...

Full description

Saved in:

Bibliographic Details
Main Authors:	Abdellatief M., Hassan Y.M., Elnabwy M.T., Wong L.S., Chin R.J., Mo K.H.
Other Authors:	57855303900
Format:	Article
Published:	Elsevier Ltd 2025
Subjects:	Adaptive boosting Fly ash Forecasting Forestry Geopolymers High performance concrete Inorganic polymers Polypropylenes Potassium hydroxide Silica fume Sodium hydroxide Steel fibers Binder ratio Compressive strength prediction- extreme gradient boosting Geopolymer concrete Gradient boosting Machine learning models Random forests Strength prediction Support vector regressions Ultra high performance Ultra-high-performance geopolymer concrete Compressive strength
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-36392
record_format	dspace
spelling	my.uniten.dspace-363922025-03-03T15:42:12Z Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study Abdellatief M. Hassan Y.M. Elnabwy M.T. Wong L.S. Chin R.J. Mo K.H. 57855303900 57216270212 55848885000 55504782500 57189222458 55915884700 Adaptive boosting Fly ash Forecasting Forestry Geopolymers High performance concrete Inorganic polymers Polypropylenes Potassium hydroxide Silica fume Sodium hydroxide Steel fibers Binder ratio Compressive strength prediction- extreme gradient boosting Geopolymer concrete Gradient boosting Machine learning models Random forests Strength prediction Support vector regressions Ultra high performance Ultra-high-performance geopolymer concrete Compressive strength Ultra-high-performance geopolymer concrete (UHPGC) is a new category of traditional UHPC developed to meet the desire for ultra-high-strength and green building materials. In the current study, random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGB) are used to forecast the compressive strength (CS) of UHPGC. Firstly, the findings of the 113 CS tests available in the previous studies were extracted. Twelve feature variables, including GGBS, silica fume, fly ash, and rice husk ash contents as precursors, the Na2SiO3, NaOH, KOH, and extra water content, polypropylene fiber, steel fiber, liquid-to-binder (L/B) ratio, and curing temperature, were investigated. After analyzing the extracted data, it was found that there were more mixtures of steel fiber-based UHPGCs and synthetic fibers compared to mixtures without fibers. This may reduce the accuracy and comprehensiveness of the predictive models used. To address this issue, several experiments were designed, performed, and tested. Overall, the dataset of 128 CS results was used to develop the machine learning (ML) models. The findings validate the effectiveness of the RF, SVR, and XGB models in accurately predicting the strength of the UHPGC, as constructed by their excellent predictive accuracy (R2 > 0.84). The XGB model performance is superior to the RF and SVR models. The feature importance analysis determined that the steel fiber content and L/B ratio were the top two elements that might profoundly impact the CS. Additionally, NaOH and silica fume also have a positive correlation with CS. Conversely, the extra water and percentage of GGBS exhibit a low correlation with the CS. Through the application of ML models, this study not only ascertains the significance of algorithms including RF, SVR, and XGB in precisely forecasting the CS of UHPGC, but also reveals essential understandings regarding the importance of steel fiber content, L/B ratio, and various other pivotal variables, consequently facilitating the development of refined formulations and improved functionalities in eco-friendly construction materials. ? 2024 Elsevier Ltd Final 2025-03-03T07:42:12Z 2025-03-03T07:42:12Z 2024 Article 10.1016/j.conbuildmat.2024.136884 2-s2.0-85195300809 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195300809&doi=10.1016%2fj.conbuildmat.2024.136884&partnerID=40&md5=8018b5283639b82c799454ed03cb7175 https://irepository.uniten.edu.my/handle/123456789/36392 436 136884 Elsevier Ltd Scopus
institution	Universiti Tenaga Nasional
building	UNITEN Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tenaga Nasional
content_source	UNITEN Institutional Repository
url_provider	http://dspace.uniten.edu.my/
topic	Adaptive boosting Fly ash Forecasting Forestry Geopolymers High performance concrete Inorganic polymers Polypropylenes Potassium hydroxide Silica fume Sodium hydroxide Steel fibers Binder ratio Compressive strength prediction- extreme gradient boosting Geopolymer concrete Gradient boosting Machine learning models Random forests Strength prediction Support vector regressions Ultra high performance Ultra-high-performance geopolymer concrete Compressive strength
spellingShingle	Adaptive boosting Fly ash Forecasting Forestry Geopolymers High performance concrete Inorganic polymers Polypropylenes Potassium hydroxide Silica fume Sodium hydroxide Steel fibers Binder ratio Compressive strength prediction- extreme gradient boosting Geopolymer concrete Gradient boosting Machine learning models Random forests Strength prediction Support vector regressions Ultra high performance Ultra-high-performance geopolymer concrete Compressive strength Abdellatief M. Hassan Y.M. Elnabwy M.T. Wong L.S. Chin R.J. Mo K.H. Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
description	Ultra-high-performance geopolymer concrete (UHPGC) is a new category of traditional UHPC developed to meet the desire for ultra-high-strength and green building materials. In the current study, random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGB) are used to forecast the compressive strength (CS) of UHPGC. Firstly, the findings of the 113 CS tests available in the previous studies were extracted. Twelve feature variables, including GGBS, silica fume, fly ash, and rice husk ash contents as precursors, the Na2SiO3, NaOH, KOH, and extra water content, polypropylene fiber, steel fiber, liquid-to-binder (L/B) ratio, and curing temperature, were investigated. After analyzing the extracted data, it was found that there were more mixtures of steel fiber-based UHPGCs and synthetic fibers compared to mixtures without fibers. This may reduce the accuracy and comprehensiveness of the predictive models used. To address this issue, several experiments were designed, performed, and tested. Overall, the dataset of 128 CS results was used to develop the machine learning (ML) models. The findings validate the effectiveness of the RF, SVR, and XGB models in accurately predicting the strength of the UHPGC, as constructed by their excellent predictive accuracy (R2 > 0.84). The XGB model performance is superior to the RF and SVR models. The feature importance analysis determined that the steel fiber content and L/B ratio were the top two elements that might profoundly impact the CS. Additionally, NaOH and silica fume also have a positive correlation with CS. Conversely, the extra water and percentage of GGBS exhibit a low correlation with the CS. Through the application of ML models, this study not only ascertains the significance of algorithms including RF, SVR, and XGB in precisely forecasting the CS of UHPGC, but also reveals essential understandings regarding the importance of steel fiber content, L/B ratio, and various other pivotal variables, consequently facilitating the development of refined formulations and improved functionalities in eco-friendly construction materials. ? 2024 Elsevier Ltd
author2	57855303900
author_facet	57855303900 Abdellatief M. Hassan Y.M. Elnabwy M.T. Wong L.S. Chin R.J. Mo K.H.
format	Article
author	Abdellatief M. Hassan Y.M. Elnabwy M.T. Wong L.S. Chin R.J. Mo K.H.
author_sort	Abdellatief M.
title	Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
title_short	Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
title_full	Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
title_fullStr	Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
title_full_unstemmed	Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study
title_sort	investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: a comparative study
publisher	Elsevier Ltd
publishDate	2025
_version_	1825816104826568704
score	13.244109

Investigation of machine learning models in predicting compressive strength for ultra-high-performance geopolymer concrete: A comparative study

Similar Items