【作者】 曾蓉；

【导师】 段其昌；

【作者基本信息】 重庆大学 ， 控制理论与控制工程， 2007， 硕士

【摘要】 在现代火力发电厂中,主汽温的控制要求是非常严格的,但是由于主汽温对象具有大延迟、大惯性、非线性以及时变性的特性,导致了对其控制比较困难。采用常规的PID控制手段很难取得良好的控制效果。若应用现代控制理论中的自适应控制、最优控制等控制手段,则需要建立被控对象的数学模型,而且往往控制系统的计算量大、实时性差。这些缺点使其很难满足实际生产过程的需要从而极大地限制了其在现代电站中的应用。随着发电机组向大容量、高参数方向发展,电站中各生产环节的特性越来越复杂而对其控制品质的要求却越来越高,急需新的控制技术来对其进行有效的控制。神经网络具有表示任意非线性关系和学习等能力,通过恰当选择网络层次和隐层单元数能够以任意精度逼近任意连续函数及其各阶导数。为时变、非线性对象的动态特性的辩识提供了简单而有效的一般性的方法,解决了时变、非线性对象控制中的瓶颈问题。因此基于神经网络的各种先进控制技术是解决现代电站中控制难题的一条有效途径。模糊系统善于表达知识,推理类似于人的思维,但过于依赖人的主观因素,缺乏学习和自适应的能力。本文紧密结合我国电厂的实际情况,以解决电厂实际运行中存在的控制问题为出发点,抓住火电厂热工控制系统普遍存在的大滞后和特性时变的特点,采用的模糊神经网络控制是一种基于神经网络理论和模糊逻辑的复合智能控制,通过利用神经网络的学习能力来优化模糊逻辑的经验规则以及比例因子的调整,从而来实现对主汽温的有效控制。并且利用matlab进行仿真试验,模糊神经网络控制器在不同负荷下都能得到很好的仿真曲线,可以看出模糊神经网络控制系统具有很好鲁棒性和良好的控制品质。更多还原

【Abstract】 In modern thermal power plant,it is very strict that the control of main steam temperature,but because of the big delay of the main steam temperature object’s characteristic,big inertial,nonlinear and the variety model with variety time,which causing as to it’s control more difficult. It is very difficult to obtain good effect of control by conventional PID control.It is necessary to set up the mathematics models of controlled plants if applying control means of modern control theory such as self-adaptive control,optimal control.And these control systems have large calculation and bad character of real time in general.These disadvantages make them be not able to meet the need of real production process and limit the application of them in modern power station.Now the generator units are developing towards large capacity and high parameters. The characters of production units of power station become more and more complex but the demand to quality of control becomes more and more strict.The new control means are in bad need to control them effectively.Neural network has the ability of learning and expressing any nonlinear relation.It can approximate any continuous function and their any order derivatives with any precision if it has the correct layers of networks and the correct number of hidden units.So all kinds of advanced control means based on neural network is an effective way that resolve the control problem of modern power station.Fuzzy control is good at expressing knowledge and its logical reasoning is similar to man’s thought.But this system depends on the man’s subjective factor too much and lack the capacity of adaptation and learning.This dissertation 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 dissertation adopt fuzzy neural network control that is a kind of compound intelligence control based on the nerve network theories and the fuzzy logical, the study ability of the neural network is used to optimize logical experience rule and adjust proportional gene, which can be realize to the valid control of the main steam temperature.And make 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.更多还原