期刊
CONSTRUCTION AND BUILDING MATERIALS
卷 348, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.conbuildmat.2022.128566
关键词
XGBoost; Non-steady-migration coefficients; Machine learning; Concrete durability; Permeability; Chloride transport
This study utilizes the machine learning algorithm XGBoost to predict the chloride migration coefficient of concrete. The verification results confirm the high accuracy of the model, suggesting its potential to replace laboratory testing.
This work adopts a state-of-the-art machine learning algorithm, XGBoost, to predict the chloride migration co-efficient (Dnssm) of concrete. An extensive database of experimental data covering various concrete types is created by gathering from research projects and previously published studies. A total of four Dnssm models are developed depending on the number and type of input features. All models are verified with unseen data using four statistical performance indicators and compared to other five tree-based algorithms. The verification results confirm that the XGBoost model predicts the Dnssm with high accuracy. The model has the potential to replace cumbersome, time-consuming and resource-intensive laboratory testing.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据