Research On Air Preheater Hot Spots Detection System Based On IR Thermal Image On Linux

Air preheater is a kind of important heat exchanger in power plant units. After-burning might be caused by inadequate combustion of fuel or badly heat-dispersed condition aroused by low air or gas velocity after boiler outage,so should avoid the fire of it. At present, thermocouple or infrared sensors are used as temperature measurement units in most air preheater hot spots detection systems. The after-burning is alarmed or not was judged by the result of temperature measure value compared to the alarm threshold value set in advanced. However, when fire is brought out in air preheater, temperature degree covers a great range. So, it is hard to set appropriate value to detect all the hot spots at any time and much more experience and working conditions is depended on.So a method for air preheater hot spots detection based on IR thermal image is presented in the paper based on the analysis of airpreheater fire condition and characteristics.The new system is on Linux operation system and could get enough hot spots from the air preheater then constitute a gray scaled image by data transform ,and then denoise the image by soft-threshold based on lifting scheme wavelet transform and extract the features of the image by wavelet packet transform. Finally determine the state of the air preheater based on the distance of eigenvector of two images. The method is more robust and better than the method used before.