| Title |
Dwarf mongoose-tree-based analysis for estimating the frost durability of recycled aggregate concrete |
| ID_Doc |
17260 |
| Authors |
Zhang, LT; Zhang, QL; Liang, S; Zhang, D; Chen, DJ |
| Title |
Dwarf mongoose-tree-based analysis for estimating the frost durability of recycled aggregate concrete |
| Year |
2024 |
| Published |
|
| DOI |
10.1007/s41939-024-00577-2 |
| Abstract |
A promising approach to enhancing sustainability within the construction industry is the development of recycled aggregate concrete (RAC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RAC$$\end{document}), which involves substituting natural aggregates with recycled materials. This innovative material not only reduces the environmental impact associated with the extraction and processing of natural aggregates but also promotes the circular economy by repurposing waste materials. Evaluating the frost durability of RAC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RAC$$\end{document} through the Durability Factor (Df) is critical for several reasons in the realms of construction and civil engineering. This study investigates the frost durability of recycled aggregate concrete (RAC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RAC$$\end{document}) by utilizing data mining techniques to predict the durability factor (Df) in cold regions. The necessity for this research arises from the growing need for sustainable construction practices, particularly through the use of recycled materials. We employed least square support vector regression (LSSVR\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$LSSVR$$\end{document}) and Random Forest (RF\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RF$$\end{document}) analysis to assess the frost resistance of RAC, focusing on key input parameters such as concrete components, recycled aggregate characteristics, treatment processes, and air-entraining agents. Our findings reveal that the RF model, enhanced by the dwarf mongoose algorithm (RFDM\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RFDM$$\end{document}), outperforms the LSSVR model (LSDM) in both the training and testing phases. Specifically, the RFDM achieved a training deviation of approximately 40% and a testing variance of around 20%, indicating its superior predictive accuracy. The RFDM\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RFDM$$\end{document} model's lower error indicators demonstrate its reliability and effectiveness compared to LSSVR\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$LSSVR$$\end{document}, making it a preferred choice for predicting the Df of RAC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RAC$$\end{document} in frigid conditions. This study not only contributes to understanding the frost resistance of RAC\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$RAC$$\end{document} but also highlights the advantages of using advanced data mining techniques in civil engineering applications. |
| Author Keywords |
Concrete; Recycled aggregate; Cold climate; Frost durability; Dwarf mongoose algorithm |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Emerging Sources Citation Index (ESCI) |
| EID |
WOS:001311968700001 |
| WoS Category |
Engineering, Multidisciplinary; Engineering, Mechanical; Materials Science, Multidisciplinary |
| Research Area |
Engineering; Materials Science |
| PDF |
|