Prediction of Concrete Carbonation Depth Based on Support Vector Regression

Concrete carbonation depth forecasting is significant to avoid the cracking of concrete. In the study, support vector regression (SVR) which is the regression model of support vector machine (SVM) is proposed to forecast concrete carbonation depth. Water cement ratio, cement consumption and service time have an important influence on concrete carbonation depth, so they are important features in concrete carbonation depth forecasting. Real case data from historical concrete carbonation depth are used in the paper. The experimental results indicate that the proposed SVR model has higher forecasting accuracy than artificial neural network.