自适应控制在随动系统测试装置中的应用与研究
|
摘要
关于人工神经网络与自适应结合的研究,近年来已经成为智能控制学科的热点之一。由于自适应控制具有很强的鲁棒性,神经网络则具有自学习功能和良好的容错能力,研究如何把神经网络与自适应控制结合起来,发挥各自的优势,对控制理论与应用研究具有重要的意义。
本文针对随动加载与测试系统,主要对其中的阻力矩加载系统建模与控制等方面进行研究。本文首先阐述了神经网络的基本问题和理论,详细研究了典型的前向神经网络(BP网络)的学习和训练算法,针对BP网络训练算法速度较慢且易于陷入局部极小点的不足,提出LM—BP算法。
接着本文研究了神经网络的模型辨识问题,分析了神经网络辨识的基本结构,讨论了BP网络辨识问题。并采集了一组磁粉制动器恒速下的实验数据,进行了基于神经网络的非线性系统离线的正模型辨识,并分析了辨识结果。
最后,本文采用神经网络与自适应相结合的方法构造了基于辨识模型的智能控制器。接着结合阻力矩加载系统的控制研究了神经网络间接自校正控制器算法,并进行了仿真研究。经过大量的系统仿真试验,所设计的间接自校正控制器可以使系统具有良好的动、静态性能,能够实现对阻力矩加载系统精确的控制。
The research of combination of neural network and adaptive theory has been an important topic in the intelligent control. As neural network adaptive control not only has the good robustness as that in the adaptive systems, but also has the ability of self-learning and good fault-tolerant, it is very interesting for the control theory and application to research how to combine neural network with adaptive control.
The paper mainly researches the modeling and control for the resisting moment loading system in a loading and test device for servo system. The paper firstly expounds the basic problem and theory of neural network, and a typical multi-layer feed-forward artificial neural networks named BP network has been studied. But traditional BP neural network has many defects, such as slow training velocity and converge to a local minimum point, while LM-BP algorithm has much better performance.
The paper then researches the model identification based on neural network, presents the normal structures of neural network identification and discusses the identification for BP neural network. According to a set of experiment data of magnetic particle brake running in constant speed, the paper has made system identifications of positive and offline model based on neural networks, and analyses identification result.
Finally, the method incorporates adaptive theory with neural network to obtain an intelligent controller, on account of model identification. The paper, combining the method and the control of resisting moment loading system, researches the neural network of indirect self-tuning controller algorithm, and carries out simulation studies. A set of simulation results shows that the design of indirect self-tuning controller can make the system has good dynamic and static performance, and realizes precise control of resisting moment loading system.
本文针对随动加载与测试系统,主要对其中的阻力矩加载系统建模与控制等方面进行研究。本文首先阐述了神经网络的基本问题和理论,详细研究了典型的前向神经网络(BP网络)的学习和训练算法,针对BP网络训练算法速度较慢且易于陷入局部极小点的不足,提出LM—BP算法。
接着本文研究了神经网络的模型辨识问题,分析了神经网络辨识的基本结构,讨论了BP网络辨识问题。并采集了一组磁粉制动器恒速下的实验数据,进行了基于神经网络的非线性系统离线的正模型辨识,并分析了辨识结果。
最后,本文采用神经网络与自适应相结合的方法构造了基于辨识模型的智能控制器。接着结合阻力矩加载系统的控制研究了神经网络间接自校正控制器算法,并进行了仿真研究。经过大量的系统仿真试验,所设计的间接自校正控制器可以使系统具有良好的动、静态性能,能够实现对阻力矩加载系统精确的控制。
The research of combination of neural network and adaptive theory has been an important topic in the intelligent control. As neural network adaptive control not only has the good robustness as that in the adaptive systems, but also has the ability of self-learning and good fault-tolerant, it is very interesting for the control theory and application to research how to combine neural network with adaptive control.
The paper mainly researches the modeling and control for the resisting moment loading system in a loading and test device for servo system. The paper firstly expounds the basic problem and theory of neural network, and a typical multi-layer feed-forward artificial neural networks named BP network has been studied. But traditional BP neural network has many defects, such as slow training velocity and converge to a local minimum point, while LM-BP algorithm has much better performance.
The paper then researches the model identification based on neural network, presents the normal structures of neural network identification and discusses the identification for BP neural network. According to a set of experiment data of magnetic particle brake running in constant speed, the paper has made system identifications of positive and offline model based on neural networks, and analyses identification result.
Finally, the method incorporates adaptive theory with neural network to obtain an intelligent controller, on account of model identification. The paper, combining the method and the control of resisting moment loading system, researches the neural network of indirect self-tuning controller algorithm, and carries out simulation studies. A set of simulation results shows that the design of indirect self-tuning controller can make the system has good dynamic and static performance, and realizes precise control of resisting moment loading system.
引文
[1]S.Bittanti,L.Piroddi.GMV Technique for Nonlinear Control with Neural Networks[J].IEE Proc.-Control Theory Application.2001,141(2):57-69
[2]V.Etxebarria.Adaptive Control of Discrete Systems using Neural Networks[J].IEE Proc.-Control Theory Application.1998,140(4):209-215
[3]Knapp Timothy D,Budman Hector M.,Broderick Gordon.Adaptive control of a CSTR with a neural network model[J].Journal of Process Control.2001,11(1):53-68
[4]M.S.Ahmed,I.A.Tasadduq.Neural-net Controller for Nonlinear Plants:Design Approach through Linearization[J].IEE Proc.-Control Theory Application.1994,141(5):315-321
[5]M.A.EI-Sharkawi,A.A.EI-Samahy,M.L.El-Sayed.High Performance Drive of DC Brushless Motors Using Neural Networks[J].IEEE Trans.on Energy Conversion.2004,9(2):317-322
[6]Huang S.N,Tan K.K,Lee T.H.Adaptive motion control using neural network approximations[J].Automatica.2002,38(2):227-233
[7]Calise Anthony J.,Hovakimyan Naira Idan Moshe.Adaptive output feedback control of nonlinear systems using neural networks[J].Automatica.2005,37(8):1201-1211
[8]Wang Dan,Huang Jie.Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form[J].Automatica.2002,38(8):1365-1372
[9]Pham D.T.,Oh S.J.Identification of plant inverse dynamics using neural networks[J].Artificial Intelligence in Engineering.1999,13(3):309-320
[10]胡寿松.自动控制原理[M].北京.科学出版社.2001
[11]M.J.Willis,C.Di Massimo,G.A.Montague,etc.Artificial Neural Networks in Process Engineering[J].IEE Proceedings-D.1997,138(3):256-265
[12]Jean Saint Donat,Naveen Bhat,Thomas J,McAvoy.Neural Net Based Model Predictive Control[J].International Journal of Control.1991,54(6):1453-1468
[13]冯宁,张宾.基于CAN总线的通用串口适配器的设计[J].测控技术.2006,(2):25-28
[14]邬宽明.CAN总线原理和应用系统设计[M].北京.北京航空航天大学出版社.1996
[15]磁粉制动器使用说明书.江苏航天机电制造有限公司
[16]李清新.伺服系统与机床电器控制[M].北京.机械工业出版社.1994
[17]王子博.编码器四倍频电路的单片机高速算法设计[J].控制与检测.2007,11(2):73-75
[18]李为民,姜漫.基于光电编码器的速度反馈与控制技术[J].工控技术.2004,(23):84-88
[19]王忠勇.基于CPLD的光电码盘计数器的设计[J].仪器仪表用户.2007,14(2):58-59
[20]赵建周,李安伏.基于光电码盘传感器的位置检测控制电路设计[J].电气传动自动化.2007,29(1):52-56
[21]信息产业部电子第21所.轴角转换器分册
[22]杜新妮,李俊武.一种伺服系统控制算法检测装置的实现[J].火炮发射与控制学报.2006,(4):32-36
[23]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[J].北京.清华大学出版社.2005
[24]李国勇.智能控制及其MATLAB实现[M].北京.电子工业出版社.2006
[25]孙增圻.智能控制理论与技术[M].第1版.北京.清华大学出版社,1997
[26]李人厚.智能控制理论和方法[M].西安.西安电子科技大学出版社,1999
[27]王永骥,涂健.神经元网络控制[M].机械工业出版社,1998
[28]汪小帆.径向基函数神经网络的新型混合递推学习算法[J].控制理论与应用.1998,15(2):272-275
[29]R.K.Eleley.A Learning Architecture for Control BP NN[J].Proc.of 1988.IEEE Int.conf.on NN,1988:587-596
[30]Hecht-Nielsen.Theory of the Backpropagation Neural Network[J].IJCNN'89,1989:593-606
[31]张立民.人工神经网络的模型及其应用[M].上海.复旦大学出版社.1993
[32]欧阳凯.神经计算中坐标变换的网络模型的泛化特性[J].自动化学报.1997,23(4):475-481
[33]王殿方.改进的BP算法及其在辨识中的应用[M].智能控制与智能自动化(中卷).北京.科学出版社.1993,726-731
[34]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京.清华大学出版社.2005
[35]K.Kristinsson.System Identification and Control Using Genetic Algorithms[J].IEEE Trans.On Neural Networks.1992,22(5):1033-1046
[36]王立红.神经网络辨识研究的现状[J].辽宁工学院学报.2004,24(3):15-17
[37]马晓敏,周忙来.基于神经网络的非线性动态系统辨识[J].中国控制会议论文集. 1995,708-712
[38]陈祥光,黄聪明.神经网络智能控制系统辨识模型结构的研究[J].北京理工大学学报.1999,19(1):53-57
[39]黄金泉,孙建国.非线性系统的动态神经网络自适应辨识[J].南京航空航天大学学报.1999,31(3):275-279
[40]翟楠松.神经网络在自适应系统建模中的应用研究[D].哈尔滨工业大学.2003
[41]邓自立,郭一新.动态系统分析及其应用[M].辽宁.辽宁科学技术出版社.1985
[42]张兴华.一种神经网络辨识的混合学习算法[J].计算机工程与应用.2004,28(3):33-36
[43]邓薇.MATLAB函数速查手册[M].北京.人民邮电出版社.2008
[44]侯媛彬,汪梅,王立琦.系统辨识及其MATLAB仿真[M].北京.科学出版社.2004
[45]王钰,郭其一.基于改进BP神经网络的预测模型及其应用[J].计算机测量与控制.2003,13(1):42-44
[46]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京.电子工业出版社.2008
[47]刘兴堂.应用自适应控制[M].西安.西北工业大学出版社.2003
[48]吴振顺.自适应控制理论与应用[M].哈尔滨.哈尔滨工业大学出版社.2005
[49]史维祥.电液伺服系统自适应控制的新发展[J].机床与液压.1995,(6):80-85
[50]张云生,祝晓红.自适应控制器设计及应用[M].北京.国防工业出版社.2005
[51]韩曾晋.自适应控制[M].北京.清华大学出版社.1995
[52]吴世昌.自适应控制[M].北京.机械工业出版社.2000
[53]李清泉.自适应控制系统理论、设计与应用[M].北京.科学出版社.1990
[54]谭永红.神经网络自适应PID控制及应用[J].模式识别与人工智能.1993,6(1):81-85
[55]李鑫,李众,张丽娟.模糊自适应在线调整PID参数控制器[J].仪器仪表应用.2004,(4):23-28
[56]杨霞,任敏,于立新.模糊逻辑参数自整定PID复合控制的设计.沈阳工业大学学报.2002,24(1):23-28
[57]陶永华.新型PID控制及其运用[M].北京.机械工业出版社.2002
[58]刘金琨.先进PID控制及其MATLAB仿真[M].北京.电子工业出版社.2003
[59]杨承志,孙棣华,张长胜.系统辨识与自适应控制[M].重庆.重庆大学出版社.2003
[60]向志容,刘国荣.一类非线性系统的自适应控制[J].计算机仿真.2007,24(9): 141-144
[61]黄长水,阮荣耀.一类非线性系统的自适应控制[J].华东师范大学学报.2000,(3):12-18
[2]V.Etxebarria.Adaptive Control of Discrete Systems using Neural Networks[J].IEE Proc.-Control Theory Application.1998,140(4):209-215
[3]Knapp Timothy D,Budman Hector M.,Broderick Gordon.Adaptive control of a CSTR with a neural network model[J].Journal of Process Control.2001,11(1):53-68
[4]M.S.Ahmed,I.A.Tasadduq.Neural-net Controller for Nonlinear Plants:Design Approach through Linearization[J].IEE Proc.-Control Theory Application.1994,141(5):315-321
[5]M.A.EI-Sharkawi,A.A.EI-Samahy,M.L.El-Sayed.High Performance Drive of DC Brushless Motors Using Neural Networks[J].IEEE Trans.on Energy Conversion.2004,9(2):317-322
[6]Huang S.N,Tan K.K,Lee T.H.Adaptive motion control using neural network approximations[J].Automatica.2002,38(2):227-233
[7]Calise Anthony J.,Hovakimyan Naira Idan Moshe.Adaptive output feedback control of nonlinear systems using neural networks[J].Automatica.2005,37(8):1201-1211
[8]Wang Dan,Huang Jie.Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form[J].Automatica.2002,38(8):1365-1372
[9]Pham D.T.,Oh S.J.Identification of plant inverse dynamics using neural networks[J].Artificial Intelligence in Engineering.1999,13(3):309-320
[10]胡寿松.自动控制原理[M].北京.科学出版社.2001
[11]M.J.Willis,C.Di Massimo,G.A.Montague,etc.Artificial Neural Networks in Process Engineering[J].IEE Proceedings-D.1997,138(3):256-265
[12]Jean Saint Donat,Naveen Bhat,Thomas J,McAvoy.Neural Net Based Model Predictive Control[J].International Journal of Control.1991,54(6):1453-1468
[13]冯宁,张宾.基于CAN总线的通用串口适配器的设计[J].测控技术.2006,(2):25-28
[14]邬宽明.CAN总线原理和应用系统设计[M].北京.北京航空航天大学出版社.1996
[15]磁粉制动器使用说明书.江苏航天机电制造有限公司
[16]李清新.伺服系统与机床电器控制[M].北京.机械工业出版社.1994
[17]王子博.编码器四倍频电路的单片机高速算法设计[J].控制与检测.2007,11(2):73-75
[18]李为民,姜漫.基于光电编码器的速度反馈与控制技术[J].工控技术.2004,(23):84-88
[19]王忠勇.基于CPLD的光电码盘计数器的设计[J].仪器仪表用户.2007,14(2):58-59
[20]赵建周,李安伏.基于光电码盘传感器的位置检测控制电路设计[J].电气传动自动化.2007,29(1):52-56
[21]信息产业部电子第21所.轴角转换器分册
[22]杜新妮,李俊武.一种伺服系统控制算法检测装置的实现[J].火炮发射与控制学报.2006,(4):32-36
[23]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[J].北京.清华大学出版社.2005
[24]李国勇.智能控制及其MATLAB实现[M].北京.电子工业出版社.2006
[25]孙增圻.智能控制理论与技术[M].第1版.北京.清华大学出版社,1997
[26]李人厚.智能控制理论和方法[M].西安.西安电子科技大学出版社,1999
[27]王永骥,涂健.神经元网络控制[M].机械工业出版社,1998
[28]汪小帆.径向基函数神经网络的新型混合递推学习算法[J].控制理论与应用.1998,15(2):272-275
[29]R.K.Eleley.A Learning Architecture for Control BP NN[J].Proc.of 1988.IEEE Int.conf.on NN,1988:587-596
[30]Hecht-Nielsen.Theory of the Backpropagation Neural Network[J].IJCNN'89,1989:593-606
[31]张立民.人工神经网络的模型及其应用[M].上海.复旦大学出版社.1993
[32]欧阳凯.神经计算中坐标变换的网络模型的泛化特性[J].自动化学报.1997,23(4):475-481
[33]王殿方.改进的BP算法及其在辨识中的应用[M].智能控制与智能自动化(中卷).北京.科学出版社.1993,726-731
[34]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京.清华大学出版社.2005
[35]K.Kristinsson.System Identification and Control Using Genetic Algorithms[J].IEEE Trans.On Neural Networks.1992,22(5):1033-1046
[36]王立红.神经网络辨识研究的现状[J].辽宁工学院学报.2004,24(3):15-17
[37]马晓敏,周忙来.基于神经网络的非线性动态系统辨识[J].中国控制会议论文集. 1995,708-712
[38]陈祥光,黄聪明.神经网络智能控制系统辨识模型结构的研究[J].北京理工大学学报.1999,19(1):53-57
[39]黄金泉,孙建国.非线性系统的动态神经网络自适应辨识[J].南京航空航天大学学报.1999,31(3):275-279
[40]翟楠松.神经网络在自适应系统建模中的应用研究[D].哈尔滨工业大学.2003
[41]邓自立,郭一新.动态系统分析及其应用[M].辽宁.辽宁科学技术出版社.1985
[42]张兴华.一种神经网络辨识的混合学习算法[J].计算机工程与应用.2004,28(3):33-36
[43]邓薇.MATLAB函数速查手册[M].北京.人民邮电出版社.2008
[44]侯媛彬,汪梅,王立琦.系统辨识及其MATLAB仿真[M].北京.科学出版社.2004
[45]王钰,郭其一.基于改进BP神经网络的预测模型及其应用[J].计算机测量与控制.2003,13(1):42-44
[46]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京.电子工业出版社.2008
[47]刘兴堂.应用自适应控制[M].西安.西北工业大学出版社.2003
[48]吴振顺.自适应控制理论与应用[M].哈尔滨.哈尔滨工业大学出版社.2005
[49]史维祥.电液伺服系统自适应控制的新发展[J].机床与液压.1995,(6):80-85
[50]张云生,祝晓红.自适应控制器设计及应用[M].北京.国防工业出版社.2005
[51]韩曾晋.自适应控制[M].北京.清华大学出版社.1995
[52]吴世昌.自适应控制[M].北京.机械工业出版社.2000
[53]李清泉.自适应控制系统理论、设计与应用[M].北京.科学出版社.1990
[54]谭永红.神经网络自适应PID控制及应用[J].模式识别与人工智能.1993,6(1):81-85
[55]李鑫,李众,张丽娟.模糊自适应在线调整PID参数控制器[J].仪器仪表应用.2004,(4):23-28
[56]杨霞,任敏,于立新.模糊逻辑参数自整定PID复合控制的设计.沈阳工业大学学报.2002,24(1):23-28
[57]陶永华.新型PID控制及其运用[M].北京.机械工业出版社.2002
[58]刘金琨.先进PID控制及其MATLAB仿真[M].北京.电子工业出版社.2003
[59]杨承志,孙棣华,张长胜.系统辨识与自适应控制[M].重庆.重庆大学出版社.2003
[60]向志容,刘国荣.一类非线性系统的自适应控制[J].计算机仿真.2007,24(9): 141-144
[61]黄长水,阮荣耀.一类非线性系统的自适应控制[J].华东师范大学学报.2000,(3):12-18