Prediction of Coal and Gas Outburst based on Factor Analysis and BP Neural Network

In order to improve the feasibility and accuracy of coal and gas outburst prediction, an improved BP neural network prediction method was proposed by combining factor analysis method with BP neural network method. Based on the original data of the main influencing factors related to coal and gas outburst in Pingdingshan No. 8 Coal Mine, factor analysis method was used to reduce dimension on the original data of 9 influencing factors of coal and gas outburst, and three common factors were obtained; three common factors were substituted for 9 coal and gas outburst factors as input layer parameters of BP neural network, and a prediction model of coal and gas outburst combined with factor analysis method and BP neural network method was established to predict coal and gas outburst in Pingdingshan No. 8 Coal Mine. The coal and gas outburst samples from Pingdingshan No. 8 Coal Mine were selected to verify the improved BP neural network prediction method. The results show that the relative errors of the three predicted samples are 1.79%, 3.54% and 0.83% respectively, all less than 10.00%. The improved BP neural network prediction method can effectively solve the problems of low data processing efficiency, slow iteration rate and low accuracy of the traditional BP neural network due to too many parameters in the input layer