RESEARCH ON MODELING OF INFRARED CARBON MONOXIDE SENSOR USED IN MINE

摘要

Several modeling methods based on infrared absorption principle are illustrated and their existing problems are indicated. A new type of infrared carbon monoxide modeling method is presented, the mathematical model was set up by adopting radial basic function's (RBF) neural network model,a momentum factor's gradient descending method could be applied to adjust the parameters of RBF neural network. The experimental results show that it can dispel all kinds of influence such as temperature, pressure, humidity, and has a high precision, a strong capacity of anti-jamming, meet the requirements of mine.