Prediction of Coal Spontaneous Combustion in Goaf Based on the BP Neural Network

On the basis of the gas monitoring system with beam tube, the BP neural network model for forecasting the temperature of coal spontaneous combustion was established. The temperature of goaf can be forecast by using the concentration values of carbon monoxide and the concentration values of carbon dioxide. By comparing prediction results with the actual monitoring data, the results show that this method significantly improves the prediction accuracy of spontaneous combustion in goaf. This predicting model proves efficient enough to provide scientific basis for spontaneous combustion prevention in goaf.