A System Of Monitoring Boiler's Flame Based On DSP

Flame detection inside the boiler in the power plant is a very important issue because it has a close relation with the safety of people's life and property. The burning process of pulverized coal boiler is very complex that its working condition is very unstable. And the security of boilers is mainly decided by the stability of flame. To prevent the explosive event of boilers, coal powder must be completely burnt. If the burning process is unstable or the temperature is asymmetrical in boilers, it is very easy to get terrible results, and the efficiency of boilers will be synchronously reduced greatly.The modern flame detection system requires a higher accuracy and stability than the old ones. Besides a good detection algorithm, how to optimize the hardware is still of concern. In this dissertation, a flame detection system based on DSP has been developed. In the system, the DSP based technology is used as the basic desktop for flame image acquisition. Further more, the data exchange has been realized through the serial port between the DSP chip and a PC-based computer, speeding up the data processing for efficient flame detection. As for the flame detection algorithm, we use a BP neural network to recognize the state of combustion. Our system performs well in view of the detection accuracy and stability.