神经网络解耦PID控制器在火电机组中的应用研究
|
摘要
单元机组协调控制系统的被控对象之间存在强耦合,且响应特性差异巨大,常规机炉协调控制系统的控制策略一般不能满足电网对单元机组协调控制的要求。常规PID控制算法原理简明,参数物理意义明确,理论分析体系完整且应用经验丰富,但鲁棒性比较差。而神经网络具有很强的逼近任意非线性函数的能力,并具有自适应学习、并行分布处理和较强的鲁棒性及容错性等特点。将传统PID控制与现代控制和智能控制理论相结合,能在很大程度上改善控制对象的控制品质。
基于PID和神经网络的上述特点,将神经网络与PID控制相结合,提出了一种神经网络解耦PID在线调整控制器参数的控制策略。结合BP神经网络的学习算法和工作原理,详细分析了利用神经网络自动调整PID控制器参数的算法、原理和实现步骤,以及利用神经网络对多变量强耦合系统进行分散解耦的算法、原理及其实现步骤。神经网络通过自身在线学习对强耦合系统进行解耦,神经网络PID控制器根据对象参数发生变化时,系统误差的变化来调整神经网络的权值,以此来改变网络中比例、积分和微分作用的相对强弱,使系统具备较好的动态和静态性能,实现系统解耦控制的要求。
最后,用所设计的控制系统对单元机组进行了大量的仿真研究。仿真结果表明:该控制系统响应速度快、超调量小、稳态精度高,能够快速跟踪系统输出并进行有效控制,且具有一定的自适应性和鲁棒性,控制方案切实可行。有效地避免了单纯PID控制鲁棒性差的不足,满足实时控制的要求,对于研究非线性、参数时变的强耦合控制系统提供了一种新的思路,具有一定的理论意义和广阔的应用前景。
As the strong coupling among the controlled object of unit coordinated control system and the large differences in response characteristics,the control strategy of conventional boiler-turbine coordinated control system can not meet the requirements of coordination and control for power grid unites. The principium of conventional PID algorithm is simple and clear in physical parameters meaning. The system of theoretical analysis is integrated and abundant application experienced. But it has poor robustness. The neural network approach has a strong ability to close with any nonlinear function, and has more advantages such as self-adaptive learning, parallel distributed processing, strong robustness, fault-tolerance and so on. The quality of the controlling object can be great improved due to the combination of traditional PID control and modern control theory
Based on the above-mentioned characteristics of the PID and neural network, and the combination of them, a new control strategy is advanced which is adjusting controller parameters online by neural network decoupling PID. According to BP neural network learning algorithm and the working principle, this report indicates a detailed analysis of the algorithm, principle and realization for adjusting controller parameters automatically by neural network, moreover, the algorithm, principle and its implementation steps for multivariable strong coupling system decentralized-decoupling by neural network are also shown. Neural network can decouples strong-coupling through its online learning, while the neural network PID can adjust the weights of neural networks based on the change of system error due to object parameters change. Because of the above-mentioned characteristics, system have preferable dynamic and static performance, achieves the requirements of decoupling control.
Finally, a large number of simulation studies are implemented by this control system. The result indicates: this control system has fast response, small overshoot, high steady state precision, moreover, it can track system output quickly and control effectively, additionally, it has a certain self-adaptability and robustness. So, the control program is feasible. This project effectively avoids the robustness of a simple PID controlling, satisfy the requirements of real-time control, provides a new approach on strong decoupling control system research of nonlinear, parameters time-variant, has a certain theoretical significance and wide application prospects.
基于PID和神经网络的上述特点,将神经网络与PID控制相结合,提出了一种神经网络解耦PID在线调整控制器参数的控制策略。结合BP神经网络的学习算法和工作原理,详细分析了利用神经网络自动调整PID控制器参数的算法、原理和实现步骤,以及利用神经网络对多变量强耦合系统进行分散解耦的算法、原理及其实现步骤。神经网络通过自身在线学习对强耦合系统进行解耦,神经网络PID控制器根据对象参数发生变化时,系统误差的变化来调整神经网络的权值,以此来改变网络中比例、积分和微分作用的相对强弱,使系统具备较好的动态和静态性能,实现系统解耦控制的要求。
最后,用所设计的控制系统对单元机组进行了大量的仿真研究。仿真结果表明:该控制系统响应速度快、超调量小、稳态精度高,能够快速跟踪系统输出并进行有效控制,且具有一定的自适应性和鲁棒性,控制方案切实可行。有效地避免了单纯PID控制鲁棒性差的不足,满足实时控制的要求,对于研究非线性、参数时变的强耦合控制系统提供了一种新的思路,具有一定的理论意义和广阔的应用前景。
As the strong coupling among the controlled object of unit coordinated control system and the large differences in response characteristics,the control strategy of conventional boiler-turbine coordinated control system can not meet the requirements of coordination and control for power grid unites. The principium of conventional PID algorithm is simple and clear in physical parameters meaning. The system of theoretical analysis is integrated and abundant application experienced. But it has poor robustness. The neural network approach has a strong ability to close with any nonlinear function, and has more advantages such as self-adaptive learning, parallel distributed processing, strong robustness, fault-tolerance and so on. The quality of the controlling object can be great improved due to the combination of traditional PID control and modern control theory
Based on the above-mentioned characteristics of the PID and neural network, and the combination of them, a new control strategy is advanced which is adjusting controller parameters online by neural network decoupling PID. According to BP neural network learning algorithm and the working principle, this report indicates a detailed analysis of the algorithm, principle and realization for adjusting controller parameters automatically by neural network, moreover, the algorithm, principle and its implementation steps for multivariable strong coupling system decentralized-decoupling by neural network are also shown. Neural network can decouples strong-coupling through its online learning, while the neural network PID can adjust the weights of neural networks based on the change of system error due to object parameters change. Because of the above-mentioned characteristics, system have preferable dynamic and static performance, achieves the requirements of decoupling control.
Finally, a large number of simulation studies are implemented by this control system. The result indicates: this control system has fast response, small overshoot, high steady state precision, moreover, it can track system output quickly and control effectively, additionally, it has a certain self-adaptability and robustness. So, the control program is feasible. This project effectively avoids the robustness of a simple PID controlling, satisfy the requirements of real-time control, provides a new approach on strong decoupling control system research of nonlinear, parameters time-variant, has a certain theoretical significance and wide application prospects.
引文
[1]刘吉臻.协调控制与给水全程控制[M].北京:水利电力出版社,1995.
[2]刘晨辉.多变量过程控制解耦理论[M].北京:水利电力出版社,1984.
[3]李遵基.热工自动控制系统[M].北京:中国电力出版社,1997.
[4]刘金琨.先进PID控制及其MATLAB仿真[M].北京:电子工业出版社,2003.
[5]李士勇.模糊控制、神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1996.
[6]陈彦桥.单元机组模糊多模型协调控制系统研究[D].华北电力大学博士学位论文(保定),2003.
[7]曾德良.汽包锅炉的动态模型结构与负荷/压力增量预测模型[J].中国电机工程学报,2000,20(12) :75-79.
[8] Liu changliang.Nonlinear Boiler Model of 300MW Power Unit for system Dynamic Performance studies[J].2001 IEEE ISIE,Vol.2,June.
[9] Hunt K.J. , R Haas , R Murray Smith . Neural networks for control systems-A survey[J].Automatic,1992,28(6):1083-1112.
[10] Widrow B. And Lehr M.A. 30 years of adaptive neural networks:Perceptron Madaline,and BP [Z].IEEE Proc.1990,78:1550-1560.
[11]肖健梅,王锡淮,鲍敏中.神经网络在船舶主柴油机建模中的应用[J].船舶工程,2001 (6):46-48.
[12]徐英,杨尔辅.一类基于RBF神经网络的动态系统在线自适应辨识方法[J].信息与控制, 2001,30(6):508-512.
[13]王一晶,左志强.基于改进BP网络的广义预测控制快速算法[J].基础自动化,2002, 9(2):10-12.
[14]刘光中,李晓峰.人工神经网络BP算法的改进和结构的自调整[J].运筹学学报,2001,5(1),81-88.
[15]刘志远,吕剑红,陈来九.新型RBF神经网络及在热工过程建模中的应用[J].中国电机工程学报,2002,22(9),109-122.
[16]柴天佑.多变量自适应解耦控制及应用[M].北京:科学出版社,2001.
[17]江征风,高晋华.神经网络自适应控制系统的特性、应用与发展[J].武汉理工大学学报,2006,28(4):17-21.
[18]欧阳黎明.MALAB控制系统设计[M].北京:国防工业出版社,2001.
[19]张云,周世官.单元机组的多模型神经网络控制[J].重庆工业高等专科学校学报,2004,6(3):25-27.
[20]侯媛彬,杜京义,汪梅.神经网络[M].陕西:西安电子科技大学出版社,2007.
[21]朱双东,艾智斌,阎夏.BP网络学习算法改进方案的探析[J].石油化工高等学报,1999,9(3):77-81.
[22]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.
[23]张良杰,李衍达.模糊神经网络技术的新发展[J].信息与控制,1995,24(1):39-45.
[24]王立红.神经网络辨识研究的现状[J].辽宁工学学报,2004,24(3):15-17.
[25]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[26]黄忠霖.控制系统MATLAB计算及仿真[M].北京:国防工业出版社,2004.
[27]徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1999.
[28]张华磊.神经网络-模糊控制在协调控制系统中的应用[D].华北电力大学硕士学位论文,2004.
[29]曾德良,刘吉臻.单元机组智能协调控制系统的发展和应用[J].电力情报,1998,(3):6-10.
[30]薛昊洋.广义PID-NN在单元机组协调控制系统中的应用[D].华北电力大学硕士学位论文,2005.
[31]曹永军.火电单元机组实现神经网络广义预测控制的研究[D].内蒙古工业大学硕士学位论文,2006.
[32]凌呼君,王文兰,冯永祥.广义预测控制在火电厂单元机组协调控制中的应用研究[J].自动化技术与应用,2003,22(5):5-7,14.
[33]何克忠,郝忠恕.计算机控制系统分析与设计[M].北京:清华大学出版社,1988.
[34]俞忠原,陈一民.工业过程控制计算机系统[M].北京:北京理工大学出版社,1995.
[35]张宇河,金钰.计算机控制系统[M].北京:北京理工大学出版社,1996.
[36]张杰,邹继刚,李文秀.多输入多输出系统的神经网络PID解耦控制器[J].哈尔滨工程大学学报,2000,21(5):6～9.
[37]龚菲,王永骥.基于神经网络的PID参数自整定与实时控制[J].华中科技大学学报,2002,30(10):69～71.
[38]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003.
[39] MingwangZhao.Neural-net-based adaptive PID regulator with attenuating excitationsignal[J].IEEE Transactions on Power Systems,1994,3:2931-2932. [40 ] Akhyar,S.Omatu,S.Self-tuning PID control by neural-networks[J].IEEE Transactions on Power Systems,1993,3:2749-2752.
[41]李新利,白焰.基于互相关函数的神经网络解耦器在线学习算法[J].华北电力大学学报,2002,29(2):63～67.
[42]李明,林永君,马永光.自适应神经元非模型多变量系统解耦控制[J].计算机仿真,2003,20(3):68～71.
[43]朱燕飞.单元机组负荷汽压对象的神经网络解耦控制系统研究[D].华北电力大学硕士学位论文,2002.
[44]舒怀林.PID神经元网络多变量控制系统分析[J].自动化学报,1999,25(1):105~111.
[45]舒怀林.PID控制与神经网络的结合及PID神经网络非线性控制系统[C].Proceedings of The 19thChinese Control Conference(CCCC 2000), Hong Kong, China,2000,626~630.
[46] Shu Huailin. PID Neural Network Control for Complex Systems[C]. Proceedings of International Conference on Computational Intelligence for Modelling,Control and Automation(CIMCA99’), IOS Press,1999,166~171.
[47]舒怀林,郭秀才.多变量强耦合时变系统的PID神经网络控制[J].工矿自动化,2003,(5):16-18.
[2]刘晨辉.多变量过程控制解耦理论[M].北京:水利电力出版社,1984.
[3]李遵基.热工自动控制系统[M].北京:中国电力出版社,1997.
[4]刘金琨.先进PID控制及其MATLAB仿真[M].北京:电子工业出版社,2003.
[5]李士勇.模糊控制、神经控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,1996.
[6]陈彦桥.单元机组模糊多模型协调控制系统研究[D].华北电力大学博士学位论文(保定),2003.
[7]曾德良.汽包锅炉的动态模型结构与负荷/压力增量预测模型[J].中国电机工程学报,2000,20(12) :75-79.
[8] Liu changliang.Nonlinear Boiler Model of 300MW Power Unit for system Dynamic Performance studies[J].2001 IEEE ISIE,Vol.2,June.
[9] Hunt K.J. , R Haas , R Murray Smith . Neural networks for control systems-A survey[J].Automatic,1992,28(6):1083-1112.
[10] Widrow B. And Lehr M.A. 30 years of adaptive neural networks:Perceptron Madaline,and BP [Z].IEEE Proc.1990,78:1550-1560.
[11]肖健梅,王锡淮,鲍敏中.神经网络在船舶主柴油机建模中的应用[J].船舶工程,2001 (6):46-48.
[12]徐英,杨尔辅.一类基于RBF神经网络的动态系统在线自适应辨识方法[J].信息与控制, 2001,30(6):508-512.
[13]王一晶,左志强.基于改进BP网络的广义预测控制快速算法[J].基础自动化,2002, 9(2):10-12.
[14]刘光中,李晓峰.人工神经网络BP算法的改进和结构的自调整[J].运筹学学报,2001,5(1),81-88.
[15]刘志远,吕剑红,陈来九.新型RBF神经网络及在热工过程建模中的应用[J].中国电机工程学报,2002,22(9),109-122.
[16]柴天佑.多变量自适应解耦控制及应用[M].北京:科学出版社,2001.
[17]江征风,高晋华.神经网络自适应控制系统的特性、应用与发展[J].武汉理工大学学报,2006,28(4):17-21.
[18]欧阳黎明.MALAB控制系统设计[M].北京:国防工业出版社,2001.
[19]张云,周世官.单元机组的多模型神经网络控制[J].重庆工业高等专科学校学报,2004,6(3):25-27.
[20]侯媛彬,杜京义,汪梅.神经网络[M].陕西:西安电子科技大学出版社,2007.
[21]朱双东,艾智斌,阎夏.BP网络学习算法改进方案的探析[J].石油化工高等学报,1999,9(3):77-81.
[22]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.
[23]张良杰,李衍达.模糊神经网络技术的新发展[J].信息与控制,1995,24(1):39-45.
[24]王立红.神经网络辨识研究的现状[J].辽宁工学学报,2004,24(3):15-17.
[25]袁曾任.人工神经元网络及其应用[M].北京:清华大学出版社,1999.
[26]黄忠霖.控制系统MATLAB计算及仿真[M].北京:国防工业出版社,2004.
[27]徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1999.
[28]张华磊.神经网络-模糊控制在协调控制系统中的应用[D].华北电力大学硕士学位论文,2004.
[29]曾德良,刘吉臻.单元机组智能协调控制系统的发展和应用[J].电力情报,1998,(3):6-10.
[30]薛昊洋.广义PID-NN在单元机组协调控制系统中的应用[D].华北电力大学硕士学位论文,2005.
[31]曹永军.火电单元机组实现神经网络广义预测控制的研究[D].内蒙古工业大学硕士学位论文,2006.
[32]凌呼君,王文兰,冯永祥.广义预测控制在火电厂单元机组协调控制中的应用研究[J].自动化技术与应用,2003,22(5):5-7,14.
[33]何克忠,郝忠恕.计算机控制系统分析与设计[M].北京:清华大学出版社,1988.
[34]俞忠原,陈一民.工业过程控制计算机系统[M].北京:北京理工大学出版社,1995.
[35]张宇河,金钰.计算机控制系统[M].北京:北京理工大学出版社,1996.
[36]张杰,邹继刚,李文秀.多输入多输出系统的神经网络PID解耦控制器[J].哈尔滨工程大学学报,2000,21(5):6～9.
[37]龚菲,王永骥.基于神经网络的PID参数自整定与实时控制[J].华中科技大学学报,2002,30(10):69～71.
[38]闻新,周露,李翔,等.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003.
[39] MingwangZhao.Neural-net-based adaptive PID regulator with attenuating excitationsignal[J].IEEE Transactions on Power Systems,1994,3:2931-2932. [40 ] Akhyar,S.Omatu,S.Self-tuning PID control by neural-networks[J].IEEE Transactions on Power Systems,1993,3:2749-2752.
[41]李新利,白焰.基于互相关函数的神经网络解耦器在线学习算法[J].华北电力大学学报,2002,29(2):63～67.
[42]李明,林永君,马永光.自适应神经元非模型多变量系统解耦控制[J].计算机仿真,2003,20(3):68～71.
[43]朱燕飞.单元机组负荷汽压对象的神经网络解耦控制系统研究[D].华北电力大学硕士学位论文,2002.
[44]舒怀林.PID神经元网络多变量控制系统分析[J].自动化学报,1999,25(1):105~111.
[45]舒怀林.PID控制与神经网络的结合及PID神经网络非线性控制系统[C].Proceedings of The 19thChinese Control Conference(CCCC 2000), Hong Kong, China,2000,626~630.
[46] Shu Huailin. PID Neural Network Control for Complex Systems[C]. Proceedings of International Conference on Computational Intelligence for Modelling,Control and Automation(CIMCA99’), IOS Press,1999,166~171.
[47]舒怀林,郭秀才.多变量强耦合时变系统的PID神经网络控制[J].工矿自动化,2003,(5):16-18.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |