Burning Control Method Of Boiler Base On Fuzzy Neural Network

Industrial boiler is important heat and drive fountain in industrial production and life, it consumed sizeable proportion in energy sources. It was a question for discussion problem in technical alteration and retrenching energy sources that improving thermal efficiency of boiler running, reducing expend of energy and decreasing the pollution of the environment.The application of Fuzzy Neural Network (FNN) in the control systems of industrial boilers is primarily studied in this dissertation; on the basis of analyzing the operating process and control system structure, taking fuzzy logical control technique and self-optimizing idea,the self-optimizing FNN controller for air-elding proportion was designed and developed. This design overcomes actively the defect in tradition control,automatically keeping track of the thermal efficiency and adjusting the air-elding proportion in industrial boiler. The controller based on fuzzy logic,neural networks and BP algorithm is introduced in this paper,and a new hybrid learning algorithm is proposed: Firstly, the initial membership functions of the fuzzy neural network are found by using the self-organization feature map algorithm; secondly, the compete algorithm is used to determine the fuzzy rules; finally,a modified BP algorithm is presented and used for optimized adjusting of the membership functions obtained. Under the discussion of FNN control theory,the compensatory FNN controller is designed. Through the introduction of compensatory fuzzy inference and quick arithmetic,the property of compensatory FNN is superior to that of common FNN. At last,simulation was also performed to the boiler control method of using compensatory fuzzy neural network by Matlab software,simulation results indicate that the control effect and the performance for tracking parameter perturbation and disturbances is better than that of the PID controller.