Research on Improved BP Neural Network Gangue Powder Concrete Compressive Strength Prediction Model

Abstract

In order to improve the accuracy of the gangue powder concrete compressive strength prediction model, the factor analysis method is combined with the BP neural network method to propose an improved BP neural network gangue powder concrete compressive strength prediction model. The actual data from the project site was selected to test the accuracy of the improved BP neural network gangue powder concrete compressive strength prediction model. The final result: the relative average error between the predicted value and the actual value of the 10 groups of training samples is 4.36%. The relative errors of the samples are 3.24%, 4.92%, 1.68%, 3.54%, and 2.23%, and the average relative errors are 3.122%, both of which are less than 10%, proving that the improved BP neural network prediction model has good prediction accuracy.