Research on infrared methane sensor mathematical model based on RBF neural network used in mine

Methane which is dangerous to mine safety production can be detected by using the infrared absorption principle. Infrared absorption spectrum theory is illustrated and the exiting problems of absorption model are indicated. In order to improve the capability of the methane sensor, the mathematical model was built by adopting radial basic function´s (RBF) neural network model, so as to eliminate the influence of temperature and humidity. a momentum factor´s gradient descending method could be applied to adjust the parameters of RBF neural network. The experimental results show that errors of the concentration of methane is greatly reduced , and the model has a high precision, can eliminate all kinds of environment influence such as temperature and humidity, satisfies the demands of mine.