Study on the air quantity of mine ventilation network based on BP neural network prediction model of friction resistance coefficient in roadway

In view of the problem that it was difficult to accurately assign the friction resistance coefficient of the roadway to be excavated by measurement in the ventilation network calculation, the BP neural network prediction model of roadway friction resistance coefficient was constructed. Taking the measured data of friction coefficient of various roadways in Shuangliu Coal Mine as training samples for learning and training, the expected error of the prediction model was less than 0.000 1. The model was used to predict the friction resistance coefficient of the mining roadway in 23 (4) 13 working face, which had not yet been completed.The predicted results were substituted into the ventilation network calculation model of Shuangliu Coal Mine, and this model was based on the Scott-Hinsley method of ventilation network calculation, the air quantity distribution of whole ventilation network in 23 (4) 13 working face had been completed during the mining period and the back-up period was calculated.The relative error between the calculation results and the field measurement results was less than 8%. The research results show that the BP neural network prediction model of friction resistance coefficient in roadway can be used to evaluate the friction resistance coefficient of the roadway to be excavated, which can realize the accurate calculation of ventilation network.