基于神经网络的自适应逆控制研究
|
摘要
控制理论的目标就是使得给定动态系统(对象)的特性尽可能准确地按照指定使用者的要求运行。这种对象控制问题可以分成三个独立的任务：对象的动态稳定性、对象动态控制和对象扰动控制。常规的控制方法是用反馈同时来处理和控制这三个任务，这时只能在三个方面进行折中处理以寻求控制的最优解。
自适应逆控制是一种分别处理这三种任务的控制方法。首先，对象是稳定的，对象不稳定的可以进行镇定。其次，对象是使用前馈控制器来控制的；第三，扰动控制器用来消除对象的干扰。自适应滤波器既可以作为控制器又可以作为扰动消除器，然后自适应算法分别优化使之达到各自的最优控制。
具体地说，自适应逆控制是用被控对象传递函数的逆作为串联控制器来对系统的动态特性作开环控制，从而避免了因反馈而可能引起的不稳定问题；同时又能做到对系统动态特性的控制与对象扰动的控制分开处理而互不影响。这是一个十分可贵的特点。且该控制器是自适应的，并将其调节到使对象及其控制器的总体动态响应达到最优。在其中使要用到反馈的，但反馈仅限在自适应过程本身采用。和传统的控制不一样，自适应逆控制采用反馈不是为了控制系统中的信号流动，而是用于控制系统中的可变参数。
以前自适应逆控制的研究主要集中于运用信号处理的方法尤其Wiener滤波器理论来建模与控制。这种方法对于研究线性系统来说是相当成功的。但对于非线性系统来说，还用这种方法来研究其效果不是太理想。尤其对于某类不能用精确数学模型描述的对象，其逆模型用传统的方法难以建立。而神经网络本质的并行结构在处理实时性要求高的自动控制领域中所显示出的极大的优越性使得逆控制在控制系统和调节器的设计中得到进一步发展。
作者把神经网络在非线性系统建模与控制中的优点引入自适应逆控制中来。从而提出一种基于对象—正模型—逆模型建模的神经网络自适应逆控制系统结构。我们采用基于BP算法的前馈神经网络构造对象辨识器和逆控制器。经过针对不同的对象，在环境及其参数变化时进行大量的仿真实验，证明了所设计的控制结构是合理和有效的，并且具有很强的鲁棒性。同时也对神经网络自适应逆控制系统的稳定性进行了初步的探讨与分析，最后我们对于神经网络自适应逆控制系统中值得关注的几个问题进行了分析与总结。
神经网络自适应逆控制是一种用神经网络构成无模型直接自适应控制系统的方法。具有对模型要求低、鲁棒性好、自适应能力强、适用于数字计算机控制
昆明理工大学硕士学位论文
中英文摘要
的优点，将之用于工业过程控制中可以取得较好的控制品质。
The goal of control theory is to make a given dynamic system (the "plant") behave in a user-specified as accurately as possible. This objective may be broken down into three separate tasks: stabilization of the plant dynamics; control of plant dynamics; and control of plant disturbance. Conventionally, one uses feedback to treat
all three problems simultaneously. Compromises are necessary to achieve good solutions.
Adaptive inverse control is a method to treat the three control tasks separately. First, the plant is stable or the plant is stabilized; secondly, the plant is controlled using a feedforward controller, thirdly, a disturbance canceller is used to reject plant disturbances. Adaptive filters are used as controller and disturbance canceller, and algorithms adapt the transfer functions of the filters to achieve excellent control respectively.
Concretely, adaptive inverse control is an open loop control toward dynamic characteristic of system by acting inverse of plant transfer function as series controller, so it avoids instability as a result of feedback. At the same time, because the control of dynamic characteristic of system and plant disturbance is to be treated separately and that has not influence mutually. It is an important trait. Moreover this controller is adaptive and regulates collective dynamic response of plant and controller to achieve excellent control. Feedback is used in control, but it is just limited to adaptive process. Adaptive inverse control dominates alterable parameters rather than signal flow in system not so as conventional control.
The research of adaptive inverse control mainly concentrated on modeling and control by utilizing the way of signal process especially Wiener filter theory ago. This method is fairly successful to research linear system. But it is not an ideal method for nonlinear system. Especially toward the plant without exactly mathematic model, it is difficult to exact inverse model for conventional method. However neural network with natural parallel structure shows huge advantage in the field of automatic control with high real-time. Consequently it promotes the more development of inverse control in the design of control system and regulator.
Author introduces the advantage of neural network in modeling and control of
nonlinear system into adaptive inverse control. Consequently the paper puts forward a structure of neural network adaptive inverse control based on plant-positive model-inverse model modeling. Feedforward neural network based on BP algorithm constructs identification of plant and inverse controller. For different plants with the variety of circumstance and parameter, a mass of simulations testify the project structure of control to be reasonable and effective, besides strong robustness. At the same time the stabilization of adaptive inverse control system based on neural network is discussed and analyzed simply. Ultimately several problems deserved attention are analyzed and summarized.
Adaptive inverse control based on neural network is a method of non-model direct adaptive control system constituted by neural network. It has an advantages of low modek good robustness , strong adaptation and is applicable for the control of digital computer. It may acquire the better control quality if adaptive inverse control based on neural network applies to industrial process control.
自适应逆控制是一种分别处理这三种任务的控制方法。首先，对象是稳定的，对象不稳定的可以进行镇定。其次，对象是使用前馈控制器来控制的；第三，扰动控制器用来消除对象的干扰。自适应滤波器既可以作为控制器又可以作为扰动消除器，然后自适应算法分别优化使之达到各自的最优控制。
具体地说，自适应逆控制是用被控对象传递函数的逆作为串联控制器来对系统的动态特性作开环控制，从而避免了因反馈而可能引起的不稳定问题；同时又能做到对系统动态特性的控制与对象扰动的控制分开处理而互不影响。这是一个十分可贵的特点。且该控制器是自适应的，并将其调节到使对象及其控制器的总体动态响应达到最优。在其中使要用到反馈的，但反馈仅限在自适应过程本身采用。和传统的控制不一样，自适应逆控制采用反馈不是为了控制系统中的信号流动，而是用于控制系统中的可变参数。
以前自适应逆控制的研究主要集中于运用信号处理的方法尤其Wiener滤波器理论来建模与控制。这种方法对于研究线性系统来说是相当成功的。但对于非线性系统来说，还用这种方法来研究其效果不是太理想。尤其对于某类不能用精确数学模型描述的对象，其逆模型用传统的方法难以建立。而神经网络本质的并行结构在处理实时性要求高的自动控制领域中所显示出的极大的优越性使得逆控制在控制系统和调节器的设计中得到进一步发展。
作者把神经网络在非线性系统建模与控制中的优点引入自适应逆控制中来。从而提出一种基于对象—正模型—逆模型建模的神经网络自适应逆控制系统结构。我们采用基于BP算法的前馈神经网络构造对象辨识器和逆控制器。经过针对不同的对象，在环境及其参数变化时进行大量的仿真实验，证明了所设计的控制结构是合理和有效的，并且具有很强的鲁棒性。同时也对神经网络自适应逆控制系统的稳定性进行了初步的探讨与分析，最后我们对于神经网络自适应逆控制系统中值得关注的几个问题进行了分析与总结。
神经网络自适应逆控制是一种用神经网络构成无模型直接自适应控制系统的方法。具有对模型要求低、鲁棒性好、自适应能力强、适用于数字计算机控制
昆明理工大学硕士学位论文
中英文摘要
的优点，将之用于工业过程控制中可以取得较好的控制品质。
The goal of control theory is to make a given dynamic system (the "plant") behave in a user-specified as accurately as possible. This objective may be broken down into three separate tasks: stabilization of the plant dynamics; control of plant dynamics; and control of plant disturbance. Conventionally, one uses feedback to treat
all three problems simultaneously. Compromises are necessary to achieve good solutions.
Adaptive inverse control is a method to treat the three control tasks separately. First, the plant is stable or the plant is stabilized; secondly, the plant is controlled using a feedforward controller, thirdly, a disturbance canceller is used to reject plant disturbances. Adaptive filters are used as controller and disturbance canceller, and algorithms adapt the transfer functions of the filters to achieve excellent control respectively.
Concretely, adaptive inverse control is an open loop control toward dynamic characteristic of system by acting inverse of plant transfer function as series controller, so it avoids instability as a result of feedback. At the same time, because the control of dynamic characteristic of system and plant disturbance is to be treated separately and that has not influence mutually. It is an important trait. Moreover this controller is adaptive and regulates collective dynamic response of plant and controller to achieve excellent control. Feedback is used in control, but it is just limited to adaptive process. Adaptive inverse control dominates alterable parameters rather than signal flow in system not so as conventional control.
The research of adaptive inverse control mainly concentrated on modeling and control by utilizing the way of signal process especially Wiener filter theory ago. This method is fairly successful to research linear system. But it is not an ideal method for nonlinear system. Especially toward the plant without exactly mathematic model, it is difficult to exact inverse model for conventional method. However neural network with natural parallel structure shows huge advantage in the field of automatic control with high real-time. Consequently it promotes the more development of inverse control in the design of control system and regulator.
Author introduces the advantage of neural network in modeling and control of
nonlinear system into adaptive inverse control. Consequently the paper puts forward a structure of neural network adaptive inverse control based on plant-positive model-inverse model modeling. Feedforward neural network based on BP algorithm constructs identification of plant and inverse controller. For different plants with the variety of circumstance and parameter, a mass of simulations testify the project structure of control to be reasonable and effective, besides strong robustness. At the same time the stabilization of adaptive inverse control system based on neural network is discussed and analyzed simply. Ultimately several problems deserved attention are analyzed and summarized.
Adaptive inverse control based on neural network is a method of non-model direct adaptive control system constituted by neural network. It has an advantages of low modek good robustness , strong adaptation and is applicable for the control of digital computer. It may acquire the better control quality if adaptive inverse control based on neural network applies to industrial process control.
引文
[1] B.Widrow and E.Walach. Adaptive Inverse Control. Prentice Hall P T R, Upper Saddle River, NJ, 1996
[2] D. Carbonell Oliver. Neural Networks Based Nonlinear Adaptive Inverse Control Algorithms. Thesis for the Engineer degree, Stanford University, Stanford, CA, September 1996
[3] Gregory L. Plett. Adaptive Inverse Control of Plants with Disturbances. PhD thesis, Stanford University, Stanford, CA, May, 1998
[4] D. Nguyen. Applications of Neural Networks in Adaptive Control. PhD thesis, Stanford University, Stanford, CA, June 1991
[5] S.W. Pich'e. Steepest Descent Algorithms for Neural Network Controllers and Filters. IEEE Transactions on Neural Networks, 5(2):198-212, March 1994
[6] B. Widrow and M.A. Lehr. 30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation. Proceedings of the IEEE, 78(9):1415-42, September 1990
[7] Malinowski A, Inrada J M and Lilly J H. Inverse Control of Nonlinear Systems Using Neural-network Observer and Inverse Mapping Approach. In Proc. IEEE. Int. Conf. Neural Network. Univ. Western Australia. 1995, 2513-2518.
[8] D. Nguyen. Applications of Neural Networks in Adaptive Control. PhD thesis, Stanford University, Stanford, CA, June 1991
[9] (美)B.威德罗，(以)E.瓦莱斯．自适应逆控制．刘树堂译．西安：西安交通大学出版社，2000
[10] 史忠科．神经网络控制理论．西安：西北工业大学出版社．1997
[11] 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
[12] 韩璞，张海琳，张丽静．神经网络自适应逆控制的仿真研究．华北电力大学学报，vol．28，No．3，July，2001
[13] 李士勇．模糊控制、神经网络控制和智能控制．哈尔滨：哈尔滨工业大学出版社．1996
[14] 焦李成．神经网络计算．西安：西安电子科技大学出版社．1993
[15] 楼顺天，施阳．基于MATLAB的系统分析与设计——神经网络，西安：西安电子科技大学出版社．2000
[16] 刘建昌．AGC系统的神经网络自适应控制．控制与决策，1998，13[17]：438—442
[17] 马晓敏．基于神经网络的动态逆模型辨识及闭环控制．控制理论与应用，1997，14[6]：829—1657
[18] 潘巨辉．非线性系统辨识及其仿真研究——应用神经网络．计算机仿真，1993，No．2．32—38
[19] 陈克安，马远良．自适应有源噪声控制——原理、算法及实现．西安：西北工业大学出版社．1993
[20] August Kaelin and Daniel von Grunigen. On the Use of A Priori Knowledge in Adaptive Inverse Control. Switzerland
[21] August Kaelin, D.Cachlin and F. Egger. An Adaptive Feedforword A Weight optimized Controller for the Active Reduction of Stochastic Sound. Proceedings of the Fourth International Congress on Sound and Vibration, vol.1, 475-485,1996
[22] L. Jin, P. N. Nikiforuk and M. M. Gupta. Direct Adaptive Output Tracking Control Using Multilayed Neural Network, IEE Pro-D. Vol. 140, No.6,393—398, 1993
[23] 施阳，慕春棣．基于非线性参数神经网络的非线性系统稳定自适应控制，信息与控制，2000，Vol．29，No．6
[24] 党映农，韩崇昭．基于Voterra基函数网络的自适应逆控制方法．西安交通大学学报，2000，34[9]：8—12
[25] 陈祥光，黄聪明．神经网络智能控制系统辨识结构的研究．北京理工大学学报，1999，Vol．19，No．1
[26] 诸勇，钱积新．参数未知非线性系统的神经网络自适应逆控制．浙江大学学报，2000，Vol．34，No．6
[27] 黄金泉，孙建国．非线性系统的动态神经网络的自适应辨识．南京航空航天大学学报，1999，Vol．31，No．3
[28] 陆璐，李天石，施维祥．非线性系统神经网络稳定自适应控制器的研究，控制与决策，1998，Vol．13，No．5
[29] 胡泽新．神经网络自适应控制系统研究，控制与决策，1995，7[5]：361—366
[30] 薛家福，黄石生．非线性系统的神经网络辨识与控制方法．计算机科学，1995，[4]：51—55
[31] 任学梅，高为柄．基于神经网络非线性系统辨识和控制的研究．控制理论与应用，1995，12[2]：147—15
[32] 许小鸣，杨煜普，厉筠怿．基于神经网络的智能控制——基于神经网络的非线性系统辨识．化工自动化及仪表，1995，22[3]：53—59
[33] 陈祥光，黄聪明．改进BP反传算法在智能控制系统中的应用．北京理工大学学报，1997，17[4]：481-487
[34] 薛定宇．控制系统计算机辅助设计——MATALB语言及应用．北京：清华大学出版社，1996
[35] 杨大力，刘泽民．一种基于神经网络的自适应回波消除器．通信学报，1993，14[16]：16—21
[36] 王耀南．智能控制系统．长沙：湖南大学出版社，1996
[37] 方崇智，萧德云．过程辨识．北京：清华大学出版社，1996
[38] 李明忠，王福利．基于递归神经网络的一类非线性无模型系统的自适应控制．控制与决策，1997，12[1]：64—67
[2] D. Carbonell Oliver. Neural Networks Based Nonlinear Adaptive Inverse Control Algorithms. Thesis for the Engineer degree, Stanford University, Stanford, CA, September 1996
[3] Gregory L. Plett. Adaptive Inverse Control of Plants with Disturbances. PhD thesis, Stanford University, Stanford, CA, May, 1998
[4] D. Nguyen. Applications of Neural Networks in Adaptive Control. PhD thesis, Stanford University, Stanford, CA, June 1991
[5] S.W. Pich'e. Steepest Descent Algorithms for Neural Network Controllers and Filters. IEEE Transactions on Neural Networks, 5(2):198-212, March 1994
[6] B. Widrow and M.A. Lehr. 30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation. Proceedings of the IEEE, 78(9):1415-42, September 1990
[7] Malinowski A, Inrada J M and Lilly J H. Inverse Control of Nonlinear Systems Using Neural-network Observer and Inverse Mapping Approach. In Proc. IEEE. Int. Conf. Neural Network. Univ. Western Australia. 1995, 2513-2518.
[8] D. Nguyen. Applications of Neural Networks in Adaptive Control. PhD thesis, Stanford University, Stanford, CA, June 1991
[9] (美)B.威德罗，(以)E.瓦莱斯．自适应逆控制．刘树堂译．西安：西安交通大学出版社，2000
[10] 史忠科．神经网络控制理论．西安：西北工业大学出版社．1997
[11] 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
[12] 韩璞，张海琳，张丽静．神经网络自适应逆控制的仿真研究．华北电力大学学报，vol．28，No．3，July，2001
[13] 李士勇．模糊控制、神经网络控制和智能控制．哈尔滨：哈尔滨工业大学出版社．1996
[14] 焦李成．神经网络计算．西安：西安电子科技大学出版社．1993
[15] 楼顺天，施阳．基于MATLAB的系统分析与设计——神经网络，西安：西安电子科技大学出版社．2000
[16] 刘建昌．AGC系统的神经网络自适应控制．控制与决策，1998，13[17]：438—442
[17] 马晓敏．基于神经网络的动态逆模型辨识及闭环控制．控制理论与应用，1997，14[6]：829—1657
[18] 潘巨辉．非线性系统辨识及其仿真研究——应用神经网络．计算机仿真，1993，No．2．32—38
[19] 陈克安，马远良．自适应有源噪声控制——原理、算法及实现．西安：西北工业大学出版社．1993
[20] August Kaelin and Daniel von Grunigen. On the Use of A Priori Knowledge in Adaptive Inverse Control. Switzerland
[21] August Kaelin, D.Cachlin and F. Egger. An Adaptive Feedforword A Weight optimized Controller for the Active Reduction of Stochastic Sound. Proceedings of the Fourth International Congress on Sound and Vibration, vol.1, 475-485,1996
[22] L. Jin, P. N. Nikiforuk and M. M. Gupta. Direct Adaptive Output Tracking Control Using Multilayed Neural Network, IEE Pro-D. Vol. 140, No.6,393—398, 1993
[23] 施阳，慕春棣．基于非线性参数神经网络的非线性系统稳定自适应控制，信息与控制，2000，Vol．29，No．6
[24] 党映农，韩崇昭．基于Voterra基函数网络的自适应逆控制方法．西安交通大学学报，2000，34[9]：8—12
[25] 陈祥光，黄聪明．神经网络智能控制系统辨识结构的研究．北京理工大学学报，1999，Vol．19，No．1
[26] 诸勇，钱积新．参数未知非线性系统的神经网络自适应逆控制．浙江大学学报，2000，Vol．34，No．6
[27] 黄金泉，孙建国．非线性系统的动态神经网络的自适应辨识．南京航空航天大学学报，1999，Vol．31，No．3
[28] 陆璐，李天石，施维祥．非线性系统神经网络稳定自适应控制器的研究，控制与决策，1998，Vol．13，No．5
[29] 胡泽新．神经网络自适应控制系统研究，控制与决策，1995，7[5]：361—366
[30] 薛家福，黄石生．非线性系统的神经网络辨识与控制方法．计算机科学，1995，[4]：51—55
[31] 任学梅，高为柄．基于神经网络非线性系统辨识和控制的研究．控制理论与应用，1995，12[2]：147—15
[32] 许小鸣，杨煜普，厉筠怿．基于神经网络的智能控制——基于神经网络的非线性系统辨识．化工自动化及仪表，1995，22[3]：53—59
[33] 陈祥光，黄聪明．改进BP反传算法在智能控制系统中的应用．北京理工大学学报，1997，17[4]：481-487
[34] 薛定宇．控制系统计算机辅助设计——MATALB语言及应用．北京：清华大学出版社，1996
[35] 杨大力，刘泽民．一种基于神经网络的自适应回波消除器．通信学报，1993，14[16]：16—21
[36] 王耀南．智能控制系统．长沙：湖南大学出版社，1996
[37] 方崇智，萧德云．过程辨识．北京：清华大学出版社，1996
[38] 李明忠，王福利．基于递归神经网络的一类非线性无模型系统的自适应控制．控制与决策，1997，12[1]：64—67