A NOVEL CARBON MONOXIDE DETECTION SYSTEM BASED ON INFRARED ABSORPTION USED IN MINE
At present carbon monoxide detection system has the general problems of low detecting precision, easily poisoning and aging, short service life, narrow measurement range and bed anti-jamming ability. Considering the complexity of the circumstance and the diversity of the interference factors in mine, dual light sources and four detectors system is introduced into the new optical structure and most of the interference factors such as power source anti-jamming,mismatch of the detectors, gas cell materials absorption, and dusts influence and etc can be compensated. In addition, an infrared carbon monoxide (CO) sensors mathematical model is built by adopting radial basic functions (RBF) neural network model, so as to dispel the influence of temperature,pressure and humidity. A momentum factors gradient descending method can be applied to adjust the parameters of RBF neural network. The experimental results have shown that the whole system has a high precision, a strong capacity of anti-jamming, a wide measurement range, a good selectivity,and an online detecting ability.
Infrared absorption Carbon monoxide Optics structure Rbf neural network Mathematical model
YU-KAI HE RU-LIN WANG YU-QIANG YANG
Department of public computer teaching and research, BoHai University, Jinzhou 121000,china;Institut Institute of Mechnical and Electronic Engineering, China University of Mining and Technology, Beijin Department of public computer teaching and research, BoHai University, Jinzhou 121000,china
国际会议
2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)
大连
英文
645-649
2006-08-13（万方平台首次上网日期，不代表论文的发表时间）