Research on the Prediction Model of Coal and Gas Outburst Based on Principal Component Analysis and Radial Basis Function Neural Network

Abstract

To improve the accuracy and efficiency of coal and gas outburst prediction, the principal component analysis was combined with radial basis function neural network for the prediction of the situation of coal and gas outburst in this paper. The impact factors of coal and gas outburst in a coal mine are the object of the study. Principal component analysis method was used to extract the principal component factors, and then the large contribution of three principal components was selected to replace the original nine factors, with the main ingredient as an input parameter radial basis function neural network. Coal and gas outburst is divided into four levels to build predictive models of coal and gas outburst. 16 outstanding groups of typical samples of the neural network prediction model were selected for training, and three groups of testing samples were tested with trained neural network prediction model, with results showing that projections are consistent with the actual situation.