Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Fast prediction of the compressive strength of high-performance concrete through a k-nearest neighbor approach

Fast prediction of the compressive strength of high-performance concrete through a k-nearest... This investigation develops a machine learning model, namely the k-nearest neighbors (k-NN) model, for quickly forecasting the compressive strength at 28 age-days of high-performance concrete (HPC). To achieve this, the k-NN was first established through a total of 56 experimental data points collected from a published document. For that the cement (Ce), strength of cement (Sc), fly ash (Fa), water to binder ratio (W/B), sand (Sa), coarse aggregate (Co), air entraining (Ae), and superplasticizer (Sp) were selected as input parameters, whereas the compressive strength (fc-28′\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$f_{c - 28}^{^{\prime}}$$\end{document}) was considered an output variable. The data set was divided into two sets, one for training purposes and one for testing purposes, according to an approximate ratio of 7:3. Five statistical indicators, including the correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error (RMSE), and α20\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\alpha_{20}$$\end{document} were elected to evaluate the performance of the proposed k-NN model. The results showed that the k-NN model performed a good prediction of the compressive strength of HPC with high values of R2 (0.92) and α20\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\alpha_{20}$$\end{document} (0.98) coefficients and small values of MAE (2.77 MPa), MSE (11.18 MPa2), and RMSE (3.34 MPa) coefficients. Furthermore, the sensitivity and shapely additive explanations analysis revealed that the cement is the most important input parameter in the k-NN model to estimate the compressive strength of HPC. Finally, a graphical user interface (GUI) tool and a web application (WA) were constructed based on the proposed k-NN model to help rapidly determine the compressive strength of HPC. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Asian Journal of Civil Engineering Springer Journals

Fast prediction of the compressive strength of high-performance concrete through a k-nearest neighbor approach

Asian Journal of Civil Engineering , Volume 25 (1) – Jan 1, 2024

Loading next page...
 
/lp/springer-journals/fast-prediction-of-the-compressive-strength-of-high-performance-D6YtrQeJV9

References (37)

Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
1563-0854
eISSN
2522-011X
DOI
10.1007/s42107-023-00756-5
Publisher site
See Article on Publisher Site

Abstract

This investigation develops a machine learning model, namely the k-nearest neighbors (k-NN) model, for quickly forecasting the compressive strength at 28 age-days of high-performance concrete (HPC). To achieve this, the k-NN was first established through a total of 56 experimental data points collected from a published document. For that the cement (Ce), strength of cement (Sc), fly ash (Fa), water to binder ratio (W/B), sand (Sa), coarse aggregate (Co), air entraining (Ae), and superplasticizer (Sp) were selected as input parameters, whereas the compressive strength (fc-28′\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$f_{c - 28}^{^{\prime}}$$\end{document}) was considered an output variable. The data set was divided into two sets, one for training purposes and one for testing purposes, according to an approximate ratio of 7:3. Five statistical indicators, including the correlation coefficient (R2), mean square error (MSE), mean absolute error (MAE), and root mean square error (RMSE), and α20\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\alpha_{20}$$\end{document} were elected to evaluate the performance of the proposed k-NN model. The results showed that the k-NN model performed a good prediction of the compressive strength of HPC with high values of R2 (0.92) and α20\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\alpha_{20}$$\end{document} (0.98) coefficients and small values of MAE (2.77 MPa), MSE (11.18 MPa2), and RMSE (3.34 MPa) coefficients. Furthermore, the sensitivity and shapely additive explanations analysis revealed that the cement is the most important input parameter in the k-NN model to estimate the compressive strength of HPC. Finally, a graphical user interface (GUI) tool and a web application (WA) were constructed based on the proposed k-NN model to help rapidly determine the compressive strength of HPC.

Journal

Asian Journal of Civil EngineeringSpringer Journals

Published: Jan 1, 2024

Keywords: k-nearest neighbors; Compressive strength; High performance concrete; Graphical user interface; Web application

There are no references for this article.