Research on Improved Prediction Model of Blasting Vibration Speed by BP Neural Network

Abstract

In order to improve the feasibility and accuracy of the prediction model of blasting vibration velocity, a modified BP neural network prediction model of blasting vibration velocity was proposed by combining factor analysis method and BP neural network method. Select the case data to test the improved BP neural network network blasting vibration velocity prediction model. The test results: the relative average error between the predicted value and the actual value of the 14 training samples is 7.37%, and the relative error of the five prediction samples is 2.40% 2.23%, 3.68%, 2.39%, and 2.17% are all less than 10%, which proves that the improved BP neural network prediction model has better prediction accuracy.