Prediction of the Sulfate Attack Resistance of Concrete Based on Machine-Learning AlgorithmsSource: Journal of Computing in Civil Engineering:;2024:;Volume ( 038 ):;issue: 006::page 04024043-1DOI: 10.1061/JCCEE5.CPENG-6064Publisher: American Society of Civil Engineers
Abstract: The thorough investigation into the evolution of concrete performance under sulfate attack environments holds significant importance for engineering applications in specific conditions. In this paper, a prediction model for the two evaluation indexes of sulfate attack resistance of concrete (SARC), namely compressive strength corrosion resistance coefficient and mass loss rate, is established based on four machine-learning algorithms: Support Vector Regression, Random Forest Regression, Gradient Boosting, and Extreme Gradient Boosting (XGB). A comparison of the various performances showed that the model based on the XGB algorithm had the strongest generalization ability and offered the best prediction of SARC (K test set R2=0.963, MLR test set R2=0.903). Feature importance and partial correlation analyses were performed for the two XGB models separately, and a graphical user interface was designed based on the two predictive models. The results reveal that the number of cycles, water-binder ratio, and cement content significantly influence the SARC. Moderately increasing cement, fly ash, and coarse aggregate content can enhance the SARC. Increasing the number of cycles, drying time, water-binder ratio, sand, and solution concentration will reduce the SARC. Therefore, measures such as moderately increasing the amount of cement, reducing the water-binder ratio, and increasing the fly ash content can be increased to improve the SARC, but overuse has no significant effect.
|
Collections
Show full item record
contributor author | Yue Li | |
contributor author | Junjie Shi | |
contributor author | Jiale Shen | |
contributor author | Kaikai Jin | |
contributor author | Mengtian Fan | |
contributor author | Xiaolong Liu | |
date accessioned | 2025-04-20T09:58:02Z | |
date available | 2025-04-20T09:58:02Z | |
date copyright | 9/14/2024 12:00:00 AM | |
date issued | 2024 | |
identifier other | JCCEE5.CPENG-6064.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4303745 | |
description abstract | The thorough investigation into the evolution of concrete performance under sulfate attack environments holds significant importance for engineering applications in specific conditions. In this paper, a prediction model for the two evaluation indexes of sulfate attack resistance of concrete (SARC), namely compressive strength corrosion resistance coefficient and mass loss rate, is established based on four machine-learning algorithms: Support Vector Regression, Random Forest Regression, Gradient Boosting, and Extreme Gradient Boosting (XGB). A comparison of the various performances showed that the model based on the XGB algorithm had the strongest generalization ability and offered the best prediction of SARC (K test set R2=0.963, MLR test set R2=0.903). Feature importance and partial correlation analyses were performed for the two XGB models separately, and a graphical user interface was designed based on the two predictive models. The results reveal that the number of cycles, water-binder ratio, and cement content significantly influence the SARC. Moderately increasing cement, fly ash, and coarse aggregate content can enhance the SARC. Increasing the number of cycles, drying time, water-binder ratio, sand, and solution concentration will reduce the SARC. Therefore, measures such as moderately increasing the amount of cement, reducing the water-binder ratio, and increasing the fly ash content can be increased to improve the SARC, but overuse has no significant effect. | |
publisher | American Society of Civil Engineers | |
title | Prediction of the Sulfate Attack Resistance of Concrete Based on Machine-Learning Algorithms | |
type | Journal Article | |
journal volume | 38 | |
journal issue | 6 | |
journal title | Journal of Computing in Civil Engineering | |
identifier doi | 10.1061/JCCEE5.CPENG-6064 | |
journal fristpage | 04024043-1 | |
journal lastpage | 04024043-16 | |
page | 16 | |
tree | Journal of Computing in Civil Engineering:;2024:;Volume ( 038 ):;issue: 006 | |
contenttype | Fulltext |