Research on Infrared Methane Detecting System Based on Support Vector Machines Used in Mine

Methane does enormously harm to people and safety production in coal mine. A new infrared methane detecting system based on support vector machines is illustrated in the paper. Methane concentration is detected by using the infrared absorption principle. Optics structure that could compensate to power source anti-jamming, mismatch of the detectors, gas cell material´s absorption, and dust´s influence was used, it developed with dual light sources and dual detectors. In order to dispel the influence of temperature and humidity, the mathematical model of infrared methane sensor based on Support Vector Machines was built. Gaussian RBF kernel was adopted in the model The experimental results show that whole system runs very well with a high precision, a strong capacity of anti-jamming, a wide measurement range, a good selectivity, and an online detecting ability, satisfies the requirements of mine.