Research on Steam Cloud Explosion Overpressure Prediction Model Based on Improved BP Neural Network

Abstract

In order to improve the feasibility and accuracy of steam cloud explosion overpressure prediction, a combination of factor analysis method and BP neural network method is proposed to propose an improved BP neural network prediction method. According to the original data of the main influencing factors of steam cloud explosion overpressure, the factor analysis method is used to reduce the dimensional data of the five steam cloud explosion overpressure factors, and obtain a common factor; replace the original with a common factor. As an input layer parameter of BP neural network, a steam cloud explosion overpressure prediction model is established by combining the factor analysis method with BP neural network method to predict the overpressure of steam cloud explosion. The improved BP neural network prediction method is verified by the example data. The final verification result is that the relative average error between the predicted and actual values of the 15 training samples is 2.51%, which proves that the improved BP neural network model with training has a good fitting effect. The relative errors of the five predicted samples were 0.77%, 1.34%, 2.07%, 3.96%, and 6.27%, both of which were less than 10%, which proved that the improved BP neural network prediction model has better prediction accuracy.