An Application Research Of Fuzzy Neural Network Control Used In Temperature System Of Boiler

The superheated steam temperature is the highest temperature in the whole steam-water running in the thermal power boiler, it has bigness infection to the thermal power safety and economy circulation. But the superheated steam temperature has big inertia, long time lag and nonlinearity characteristics, therefore, the control of superheated steam temperature has some difficulties, especially when disturbed variable is happened, would the control system be adjusted in time, keep the steam temperature error in range is very important to the control system.This paper is dedicated to solve the practical control problems in power station under the existence of thermal control system characterized by large delay and time varying. The paper adopts fuzzy neural network control that is the main regulator of the new type of steam temperature control system.The content of this paper has researched mainly included the following aspects:Firstly, this paper expatiates on the research meaning of the steam temperature and introduces the research status and developing trend. Based on some problems of the control method nowadays, we established the paper's start. This paper also researches the dynamic characteristics of steam temperature, establishes the mathematical models as well.Secondly, this paper not only briefly introduces the fuzzy control and neural network, but also focuses on the BP neural network. And fusion and classification of fuzzy system and neural network are introduced. Meanwhile, this paper carries on the preliminary introduction to the fuzzy neural network, and briefly introduces design of fuzzy neural network.Thirdly, the specific design process of steam temperature control system based on fuzzy neural network is in detail in this paper. The study ability of the neural network is used to adjust logical experience rule and proportional gene. And made use of the matlab proceeding simulative experiment, fuzzy neural network controller arrives the better simulative curve under the different load, we can find out fuzzy neural network control system has the very good robustness and very good control quality.Finally, for making up a gap of BP algorithm, this paper which combines genetic algorithm with fuzzy neural network, proposes genetic algorithm to globally optimize the fuzzy neural network, too. The improved genetic operators are given and the simulation for superheated steam temperature control system using this method is studied. The results show that the proposed method is valid.