Research on Mine Gas Monitoring System Based on Multi Sensor Data Fusion

Abstract

At present the majority of mine gas monitoring systems have the following shortcomings: inaccuracy in measuring, poor in real-time and anti-interference. This paper presents a two-level-fusion design for sensor system information by patch estimation theory and BP neural network ,and the simulation have been carried out with many mines’ measured data .The results show that the method can greatly improve the accuracy and reliability of measurement, and can make a real-time objective evaluation to the mine safety situation.