火电厂主蒸汽温度的模糊神经网络控制系统的研究
|
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。
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.
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。
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.
引文
[1] 易继锴, 侯媛彬. 智能控制技术. 北京:北京工业大学出版社,1999,9.
[2] 火电机组控制中提高. DCS 应用水平的途径. 中国电力,2000,10.
[3] 郭晨. 智能控制原理及应用. 大连:大连海事大学出版社,1998,1.
[4] 费敏锐. 智能控制方法的交叉综合及其应用 控制理论与应用,1996.
[5] 王凌. 智能优化算法及其应用. 北京:清华大学出版社, 2001.
[6] 姚峻,沈丛奇. DCS 系统设计思想及组态方法的探讨. 华东电力,2002,1.
[7] 俞金寿,何衍庆. 集散控制系统原理及应用. 北京:化学工业出版社,1995.
[8] 王常力,廖道文. 集散型控制系统的设计与应用. 清华大学出版社,1993,6.
[9] 王国玉,翟永杰等. 单神经元自适应控制在 DCS 中的实现研究. 控制工程, 2002,7.
[10] 阎平凡,张长水. 人工神经网络与模拟进化计算. 清华大学出版社,2000.
[11] 李人厚. 智能控制控制和方法. 西安:西安电子科技大学出版社,1999,10.
[12] 赵振宇,徐用懋. 模糊理论和神经网络的基础与应用. 清华大学出版社,1996.6.
[13] 谭永红,神经网络自适应 PID 控制及其应用. 模式识别与人工智能,1993,6.
[14] 王耀南,董调生,蔡自兴. 基于神经网络的智能 PID 控制及应用. 信息与控制,1994,23(3).
[15] 刘志远,吕剑虹,陈来九. 智能 PID 控制器在电厂热工过程控制中的应用. 中国电机工程学报,2002.8.
[16] 袁曾任. 人工神经元网络及其应用. 北京:清华大学出版社, 1999.
[17] 何玉彬,李新忠. 神经网络控制技术及其应用. 北京:科学出版社,2000.
[18] 李士勇. 模糊控制·神经控制和智能控制论,哈尔滨:哈尔滨工业大学出版社,1996.
[19] 焦李成. 神经网络计算. 西安:西安电子科技大学出版社 2000.
[20] 王士同. 神经模糊系统及其应用[M]. 北京:北京航空航天大学出版社,1998,6.
[21] 徐宁,虞厥邦. 神经计算机的研究与发展. 计算机科学,2001,28(9).
[22] 胡一靓,吕剑虹等. 一类自适应模糊控制方法研究及在锅炉汽温控制中的应用. 中国电机工程学报,2003.1,23(1).
[23] 韩璞,张丽静. 热工过程控制系统参数优化方法的研究. 华北电力学院学报,1993,20(1).
[24] 马平,朱燕飞,牛征. 基于神经网络的主汽温控制系统. 华北电力大学学报,2001,28(2).
[25] 刘金琨. 先进 PID 控制及其 MATLAB 仿真. 北京:电子工业出版社,2003,1.
[26] 王中胜,韩璞. PID 控制器参数自整定方法. 电力情报,1997,4.
[27] 张玉铎,王满稼. 热工自动控制系统. 水利电力出版社,1985.
[28] 王萧,任思聪. 非线性系统模糊神经网络直接自适应控制. 西北工业大学学报,1997.11,15(4).
[29] 荣雅君,窦春霞,袁石文. 过热汽温模糊神经网络预测控制器的设计. 中国电机工程学报, 2003.1,23(1):170-173.
[30] 王耀南,神经网络自适应模糊控制在温度控制系统中的应用. 信息与控制,1996.8,25(4):245-251.
[31] 张丽香,于晋春,谢克明. 模糊自适应导前微分方式的过热汽温控制系统. 动力工程,2002.8,22(4):1893-1896.
[32] 许东,吴铮. 基于 Matlab6.x 的系统分析与设计——神经网络.西安电子科技大学出版社,2002.
[33] 王耀南. 一种神经网络自组织模糊控制与应用. 模式识别与人工智能,1994.17(4),285-293.
[34] Jang J S R,self-learning fuzzy controllers based on temporal back propagation[J],IEEE Trans,Neural Networks,1992,3(5).
[35] yager R, Implementing fuzzy logical controllers using a neural network framework [J].Fuzzy Sets and Systems,1992,3(5).
[36] Diedrich, C.; Simon, R.; Riedl, R.; Christian Diedrich, Engineering of Distributed. Control Systems, Industrial Electronics, 2000. ISIE2000. Proceedings of the 2000 IEEE International Symposium on, Volume: 2, 4-8 Dec. 2000.
[37] Chapman, C. M.Distributed Control for Distributed Systems, Control i.n Building Energy Management Systems, IEE Colloquium on, 30 Ma.y 1990.
[38] Wang, S. Z.;Chen, R.Wang,Research and Design of a Distributed Control System for Process Automation, Industrial Technology, 1994. Proceedings of the IEEE International Conference on,5-9 Dec. 1994.
[39] Kane 一 Esrig, Y,;Azuma, M.Kobayashi,D.DCS Mesh Architecture with Distributed Control:Risk and Cost, Communications, 1993. ICC93. Geneva. Technical Program, Conference Record, IEEE International Conference on, Volume:2,23-26 May 1993.
[40] Decker, D. L.What is in Store for DCS Systems, Pulp and Paper Industry Technical Conference, 2001 Conference Record of. Tune 2001.
[41] Moradi,M. H.New techniques for PID Controller Design, Control Applications, 2003. CCA 2003. Proceedings of 2003 IEEE Conference on,Volume: 1,23-25 June 2003.
[42] Moradi,M. H.;PID tuning based on model matching, Control Applications, 2003. CCA2003. Proceedings of 2003 IEEE Conference on, Volume: 1,23-25 June 2003.
[43] Wen Ta,Tam,P.K.S.;PID tuning for integrating processes, Control Applications, 1998,Proceedings of the 1998 IEEE International Conference on,Volume:2,1-4 Sept.1998.
[44] Myungsoo Jun;Safonov, M.G.Automatic PID tuning:an application of unfalsified control,Computer Aided Control System Design, 1999. Proceedings of the 1999 IEEE International Symposium on, 22-27 Aug. 1999.
[45] 范永胜等.基于动态特性机理分析的锅炉过热汽温自适应模糊控制系统研究.电机工程学报,1997,17(1):23—28.
[2] 火电机组控制中提高. DCS 应用水平的途径. 中国电力,2000,10.
[3] 郭晨. 智能控制原理及应用. 大连:大连海事大学出版社,1998,1.
[4] 费敏锐. 智能控制方法的交叉综合及其应用 控制理论与应用,1996.
[5] 王凌. 智能优化算法及其应用. 北京:清华大学出版社, 2001.
[6] 姚峻,沈丛奇. DCS 系统设计思想及组态方法的探讨. 华东电力,2002,1.
[7] 俞金寿,何衍庆. 集散控制系统原理及应用. 北京:化学工业出版社,1995.
[8] 王常力,廖道文. 集散型控制系统的设计与应用. 清华大学出版社,1993,6.
[9] 王国玉,翟永杰等. 单神经元自适应控制在 DCS 中的实现研究. 控制工程, 2002,7.
[10] 阎平凡,张长水. 人工神经网络与模拟进化计算. 清华大学出版社,2000.
[11] 李人厚. 智能控制控制和方法. 西安:西安电子科技大学出版社,1999,10.
[12] 赵振宇,徐用懋. 模糊理论和神经网络的基础与应用. 清华大学出版社,1996.6.
[13] 谭永红,神经网络自适应 PID 控制及其应用. 模式识别与人工智能,1993,6.
[14] 王耀南,董调生,蔡自兴. 基于神经网络的智能 PID 控制及应用. 信息与控制,1994,23(3).
[15] 刘志远,吕剑虹,陈来九. 智能 PID 控制器在电厂热工过程控制中的应用. 中国电机工程学报,2002.8.
[16] 袁曾任. 人工神经元网络及其应用. 北京:清华大学出版社, 1999.
[17] 何玉彬,李新忠. 神经网络控制技术及其应用. 北京:科学出版社,2000.
[18] 李士勇. 模糊控制·神经控制和智能控制论,哈尔滨:哈尔滨工业大学出版社,1996.
[19] 焦李成. 神经网络计算. 西安:西安电子科技大学出版社 2000.
[20] 王士同. 神经模糊系统及其应用[M]. 北京:北京航空航天大学出版社,1998,6.
[21] 徐宁,虞厥邦. 神经计算机的研究与发展. 计算机科学,2001,28(9).
[22] 胡一靓,吕剑虹等. 一类自适应模糊控制方法研究及在锅炉汽温控制中的应用. 中国电机工程学报,2003.1,23(1).
[23] 韩璞,张丽静. 热工过程控制系统参数优化方法的研究. 华北电力学院学报,1993,20(1).
[24] 马平,朱燕飞,牛征. 基于神经网络的主汽温控制系统. 华北电力大学学报,2001,28(2).
[25] 刘金琨. 先进 PID 控制及其 MATLAB 仿真. 北京:电子工业出版社,2003,1.
[26] 王中胜,韩璞. PID 控制器参数自整定方法. 电力情报,1997,4.
[27] 张玉铎,王满稼. 热工自动控制系统. 水利电力出版社,1985.
[28] 王萧,任思聪. 非线性系统模糊神经网络直接自适应控制. 西北工业大学学报,1997.11,15(4).
[29] 荣雅君,窦春霞,袁石文. 过热汽温模糊神经网络预测控制器的设计. 中国电机工程学报, 2003.1,23(1):170-173.
[30] 王耀南,神经网络自适应模糊控制在温度控制系统中的应用. 信息与控制,1996.8,25(4):245-251.
[31] 张丽香,于晋春,谢克明. 模糊自适应导前微分方式的过热汽温控制系统. 动力工程,2002.8,22(4):1893-1896.
[32] 许东,吴铮. 基于 Matlab6.x 的系统分析与设计——神经网络.西安电子科技大学出版社,2002.
[33] 王耀南. 一种神经网络自组织模糊控制与应用. 模式识别与人工智能,1994.17(4),285-293.
[34] Jang J S R,self-learning fuzzy controllers based on temporal back propagation[J],IEEE Trans,Neural Networks,1992,3(5).
[35] yager R, Implementing fuzzy logical controllers using a neural network framework [J].Fuzzy Sets and Systems,1992,3(5).
[36] Diedrich, C.; Simon, R.; Riedl, R.; Christian Diedrich, Engineering of Distributed. Control Systems, Industrial Electronics, 2000. ISIE2000. Proceedings of the 2000 IEEE International Symposium on, Volume: 2, 4-8 Dec. 2000.
[37] Chapman, C. M.Distributed Control for Distributed Systems, Control i.n Building Energy Management Systems, IEE Colloquium on, 30 Ma.y 1990.
[38] Wang, S. Z.;Chen, R.Wang,Research and Design of a Distributed Control System for Process Automation, Industrial Technology, 1994. Proceedings of the IEEE International Conference on,5-9 Dec. 1994.
[39] Kane 一 Esrig, Y,;Azuma, M.Kobayashi,D.DCS Mesh Architecture with Distributed Control:Risk and Cost, Communications, 1993. ICC93. Geneva. Technical Program, Conference Record, IEEE International Conference on, Volume:2,23-26 May 1993.
[40] Decker, D. L.What is in Store for DCS Systems, Pulp and Paper Industry Technical Conference, 2001 Conference Record of. Tune 2001.
[41] Moradi,M. H.New techniques for PID Controller Design, Control Applications, 2003. CCA 2003. Proceedings of 2003 IEEE Conference on,Volume: 1,23-25 June 2003.
[42] Moradi,M. H.;PID tuning based on model matching, Control Applications, 2003. CCA2003. Proceedings of 2003 IEEE Conference on, Volume: 1,23-25 June 2003.
[43] Wen Ta,Tam,P.K.S.;PID tuning for integrating processes, Control Applications, 1998,Proceedings of the 1998 IEEE International Conference on,Volume:2,1-4 Sept.1998.
[44] Myungsoo Jun;Safonov, M.G.Automatic PID tuning:an application of unfalsified control,Computer Aided Control System Design, 1999. Proceedings of the 1999 IEEE International Symposium on, 22-27 Aug. 1999.
[45] 范永胜等.基于动态特性机理分析的锅炉过热汽温自适应模糊控制系统研究.电机工程学报,1997,17(1):23—28.