Prediction model of working face hypoxia based on improved generalized regression neural network

Abstract

In order to solve the problem of working face hypoxia in coal mine more effectively and reasonably, an improved general neural network (GRNN) model for prediction of oxygen concentration in coal mine was constructed, by taking the monitoring data of a working face in Shendong as samples and considering the interaction relationship between physical parameters, based on principal component analysis.Comparing the predicted oxygen concentration results with the measured data, it proves that the improved GRNN model has good fitting accuracy and generalization ability.By using the improved GRNN model, the original GRNN model and BP neural network model respectively in the comparative analysis of hypoxia problems, it found that the improved GRNN model has better effects and is more suitable for the prediction of hypoxia problems in coal mine face.The influence of inlet air pressure, outlet air pressure and inlet air temperature on the oxygen concentration were analyzed by the improved GRNN model.This improved GRNN model can give a reference to hypoxia prediction and hypoxia control technology of the working face.

Keywords

• hypoxia problem
• grnn
• prediction model
• generalization ability