Application Of Information Fusion Techniques In Flame Detection

The safe and economic running in power plant is a field that should be paid more attention to. Information fusion techniques are used to colligate radiation signals of visible light and infrared ray, which are emitted by boiler burner flame, and estimate flame state in this thesis. Thus the veracity of flame detection and the safety of boiler running will be improved. The main research work of using fuzzy fusion method and neural network fusion method to detect flame is finished. The technique on how to get the furnace energy signal by fusing signals from the two kinds of flame probes, and the idea about importing this energy signal to combustion control system are given. The results of simulation show that this method can improve the qualities of combustion control greatly, and reduce energy consumption.The combination of Information fusion techniques and flame detection has wide application foreground, and is a valuable researching direction. Lu Jianfei (Control Theory and Control Engineering) Directed by Prof. Niu Yuguang...