Research on Hydraulic Concrete Strength Prediction Model Based on ANN-RBF Neural Network

Abstract

In recent years, with the continuous development of construction engineering level, the number of hydraulic buildings and dam projects has gradually increased, and the prediction of hydraulic concrete strength, as the main component of buildings, is particularly important. Based on the radial basis function (RBF) provided in the neural network (ANN), the SPSS27 platform is called, considering that the method has the characteristics of automatic adaptation to determine the network and the absence of the need to give initial weights artificially. The method is applied to the prediction of hydraulic concrete strength model, and experimental data are processed using the ANN-RBF method to obtain the results of the factors and their joint effects on the concrete strength, which is a more intuitive way to understand the interrelationship of the factors and their influence mechanism. The results show that the method is able to predict the results well and the research is of great importance for accurate prediction of the strength of hydraulic concrete.