神经网络预测控制应用研究
|
摘要
基于神经网络的预测控制是国内外复杂工业过程控制领域中研究的前沿问题之一。本文根据预测控制的三大机理,在分析基本的预测控制算法的基础上,设计了一种新颖的基于BP神经网络模型的广义预测控制算法,并开展了神经网络预测控制在微创手术遥操作机器人系统和三容水箱系统中的应用研究。
本文绪论对预测控制和神经网络产生的历史背景、发展历程、研究现状、发展趋势和存在的问题作了简要的综述,并扼要的讲述了神经网络预测控制复合控制方法的应用研究和发展方向。
第二章首先针对三种典型预测控制算法讨论了预测控制的基本结构和原理,深入分析了预测控制的模型预测、反馈校正与滚动优化方法。然后通过分析三种常见的神经网络模型对神经网络控制原理进行简单的探讨。
第三章在微创手术遥操作机器人系统模型的基础上,针对遥操作机器人微创手术中,由呼吸运动和心跳产生的组织周期性位移干扰设计了一种广义预测控制方案。通过MATLAB仿真实验表明,系统能在遥操作机器人系统模型下较好的消除这种由呼吸运动和心跳产生的周期性扰动。
第四章以工业过程中大时延、非线性系统三容水箱为研究对象,分别进行PID算法、广义预测控制算法和神经网络预测控制算法的仿真实验,从而体现了神经网络预测控制复合控制算法在工业过程控制装置上的实用性和先进性。
第五章设计了遥操作机器人系统的LabVIEW实验平台,实现实验装置的串口通信、数据采集卡以及网络通讯,并完成了主从手位置跟踪实验。在LabVIEW平台界面上,实验操作更加简便,数据观察更加直观。
最后对全文进行总结,并结合自己的研究心得,指出一些可深入研究或有待解决的问题。
Predictive control based on neural networks is one of the forward problems on study in the field of complex industrial process control. This paper, according to predictive control theory, designs a novel generalized predictive control algorithm based on BP neural network. Also, in this paper, neural network predictive control algorithm is studied for minimally invasive surgical teleoperation robot system and three-container water tanks system.
In Ch.1, the background, the present development, the tendency and problems of the predictive control and the neural networks are summarized briefly. The application research and the development direction of the compound control method the neural network predictive control are discribed briefly.
In Ch.2, first, aiming at the typical predictive control algorithm, the basic structure and the theory of the predictive control are discussed. Then, neural network control theory is simply discussed through the analysis of three common neural network models.
In Ch.3, In order to eliminate disturbance of periodic deformations of organs due to respiratory movements and heart beating, during minimally invasive surgery with teleoperation robot, this paper designs an algorithm of generalized predictive controller scheme, based on the minimally invasive surgical teleoperation robot system model. The curves of MATLAB show that the system can reject better the cyclic disturbances.
In Ch.4, the simulation experiments of PID, GPC and NNPC algorithms are made, taken the three-container water tanks of the long time delay and nonlinear system in industrial process, as the research object. The results of the experiments show that the compound control method of the neural network predictive control algorithm is practical and advanced in industrial process control equipments.
In Ch.5, the LabVIEW platform of the teleoperation robot system is established for serial port communication, data acquisition card, network communication and the experiment of master-slave tracking position. In the LabVIEW platform interface, the experimental operation is more convenient and the observation data is more intuitive.
In the end, the paper is summed up. Some problems which can be deeply studied are presented according to personal experiences and ideas.
本文绪论对预测控制和神经网络产生的历史背景、发展历程、研究现状、发展趋势和存在的问题作了简要的综述,并扼要的讲述了神经网络预测控制复合控制方法的应用研究和发展方向。
第二章首先针对三种典型预测控制算法讨论了预测控制的基本结构和原理,深入分析了预测控制的模型预测、反馈校正与滚动优化方法。然后通过分析三种常见的神经网络模型对神经网络控制原理进行简单的探讨。
第三章在微创手术遥操作机器人系统模型的基础上,针对遥操作机器人微创手术中,由呼吸运动和心跳产生的组织周期性位移干扰设计了一种广义预测控制方案。通过MATLAB仿真实验表明,系统能在遥操作机器人系统模型下较好的消除这种由呼吸运动和心跳产生的周期性扰动。
第四章以工业过程中大时延、非线性系统三容水箱为研究对象,分别进行PID算法、广义预测控制算法和神经网络预测控制算法的仿真实验,从而体现了神经网络预测控制复合控制算法在工业过程控制装置上的实用性和先进性。
第五章设计了遥操作机器人系统的LabVIEW实验平台,实现实验装置的串口通信、数据采集卡以及网络通讯,并完成了主从手位置跟踪实验。在LabVIEW平台界面上,实验操作更加简便,数据观察更加直观。
最后对全文进行总结,并结合自己的研究心得,指出一些可深入研究或有待解决的问题。
Predictive control based on neural networks is one of the forward problems on study in the field of complex industrial process control. This paper, according to predictive control theory, designs a novel generalized predictive control algorithm based on BP neural network. Also, in this paper, neural network predictive control algorithm is studied for minimally invasive surgical teleoperation robot system and three-container water tanks system.
In Ch.1, the background, the present development, the tendency and problems of the predictive control and the neural networks are summarized briefly. The application research and the development direction of the compound control method the neural network predictive control are discribed briefly.
In Ch.2, first, aiming at the typical predictive control algorithm, the basic structure and the theory of the predictive control are discussed. Then, neural network control theory is simply discussed through the analysis of three common neural network models.
In Ch.3, In order to eliminate disturbance of periodic deformations of organs due to respiratory movements and heart beating, during minimally invasive surgery with teleoperation robot, this paper designs an algorithm of generalized predictive controller scheme, based on the minimally invasive surgical teleoperation robot system model. The curves of MATLAB show that the system can reject better the cyclic disturbances.
In Ch.4, the simulation experiments of PID, GPC and NNPC algorithms are made, taken the three-container water tanks of the long time delay and nonlinear system in industrial process, as the research object. The results of the experiments show that the compound control method of the neural network predictive control algorithm is practical and advanced in industrial process control equipments.
In Ch.5, the LabVIEW platform of the teleoperation robot system is established for serial port communication, data acquisition card, network communication and the experiment of master-slave tracking position. In the LabVIEW platform interface, the experimental operation is more convenient and the observation data is more intuitive.
In the end, the paper is summed up. Some problems which can be deeply studied are presented according to personal experiences and ideas.
引文
[1] MBAlib.诺伯特·维纳—控制论之父[EB]. http://wiki.mbalib.com/wiki/%E8%AF%BA%E4%BC%AF%E7%89%B9%C2%B7%E7%BB%B4%E7%BA%B3. 2010-01-22.
[2]诸静.控制理论十年回顾与展望[J].浙江大学学报. 1993,27(4):1-7.
[3]丁宝苍,罗小锁,罗霄,等.先进控制理论[M].北京:电子工业出版社, 2010. 1-2.
[4]马亮.基于Elman神经网络的预测控制研究及应用[D].黑龙江:哈尔滨工程大学硕士学位论文. 2008:1-12
[5]百度百科.智能控制[EB]. http://baike.baidu.com/view/126735.htm#sub126735. 2011-02-27.
[6]王国军,陈松乔.自动控制理论发展综述[J].微型机与应用. 2000,(6):4-7.
[7]谢承泮.神经网络发展综述[J].科技情报开发与经济. 2006,16(12):148-150.
[8] J.Richalet, A.Rault, J.L.Testud, et al. Model Predictive Heuristic Control: Applications to Industrial Processes[J]. Automatica. 1978,14(5):413-438
[9] R.Rouhani, R.K.Mehra. Model Algorithmic Control (MAC): Basic Theortical Properties[J]. Automatica. 1982,18(4):401-414.
[10] C.R.Cutler, B.L.Ramaker. Dynamic Matrix Control: A Computer Control Algorithm[C]. Proc. of Joint Automatic Control Conference. San Francisco. 1980.
[11]陈增强,袁著祉,李玉梅,等.工业锅炉的加权预测自校正控制[J].自动化学报. 1993,19(01):46-53.
[12] M.Mahfouf, D.A.Linkens, A.J.Asbury, et al. Generalized Predictive Control (GPC) in the Operating Theatre[J]. IEE Proc. D. 1992,139(4):404-420.
[13]齐亮,俞孟蕻.基于支持向量机的船舶航向广义预测控制研究[J].中国航海. 2007,(3):54-56.
[14] M.Mercang?z, F.J.Doyle. Distributed Model Predictive Control of an expe-rimental four-tank system[J]. journal of Process Control. 2007,17(3):297-308.
[15]孙富春,李莉,孙增圻.非线性系统神经网络自适应控制的发展现状及展望[J].控制理论与应用. 2005,22(2):254-260.
[16]史一平.有界导数神经网络非线性预测控制应用研究[D].浙江:浙江大学硕士学位论文. 2008:2
[17]戴文战,娄海川,杨爱萍.非线性系统神经网络预测控制研究进展[J].控制理论与应用. 2009,26(5):521-530.
[18] W.E.Staib, J.N.Mcnames. Operating Experience from Intelligent Arc Furnace Installations[J]. Iron and Steel Engineer. 1994,71(5):38-40.
[19] R.N.Jose, H.wang. A Direct Adaptive Neural Nerwork Control for Unknown Nonlinear System and Its Application[J]. IEEE Trans on Nerual Network. 1998,9(1):27-33.
[20] J.Q.Hu, E.Rose. Generalized Predictive Control Using a Neural-Fuzzy Model[J]. Int. J. of System Sciences. 1999,30(1):117-122.
[21] M.Bongards. Improving the Efficiency of a Waster Water Treatment Plant bu Fuzzy Control and Neural Networks[J]. Waster Science and Technology. 2001,43(11):189-196.
[22]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.
[23]陈增强,袁著祉,刘宗信,等.涤纶片基拉膜生产线横向分布神经网络自校正预测控制[J].自动化学报. 2001,27(3):332-337.
[24]杜福银,徐扬.基于递归神经网络的预测模糊控制[J].西南交通大学学报. 2006,41(6):773-736.
[25]李届家,郭宏伟,文达.神经网络预测器在铝电解过程控制中的应用[J].沈阳建筑大学学报:自然科学版. 2006,22(6):1023-1026.
[26]陆冬娜.基于神经网络的非线性模型预测控制[D].浙江:浙江工业大学硕士学位论文. 2007:8.
[27]诸静.智能预测控制及其应用[M].浙江:浙江大学出版社, 2003. 29,30-35,43-44,39-40,50-51,107-109,114,116-118,134-137.
[28] P.R.Maurath, D.A.Mellichamp, D.E.Seborg. Predictive Controller Design for SISO Systems[C]. Proc. A.C.C. Boston. 1988.
[29] P.M.Bruijin, L.J.Bootsma. Predictive Control Using Impulse Response Models[C]. 6th IFAC/IFIP Conference. Dusseldorf. 1980.
[30]倪宏伟.基于神经网络的预测控制方法及其应用研究[D].湖南:中南大学硕士学位论文. 2006:11-16,16-19,28.
[31] D.W.Clarke, C.Mohtadi, P.S.Tuffs. Generalized Predictive Control[J]. PartⅠ. The Basic algorithm. 1987,23(2):137-148.
[32]焦李成.神经网络计算[M].西安:西安电子科技大学出版社, 1993.
[33]安志银.基于神经网络旋转二级倒立摆系统的预测控制研究[D].河北:燕山大学硕士学位论文. 2010:12-14.
[34]李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社, 2005. 31-35.
[35] J.J.Hopfield, D.W.Tank. Neural Computation of Decision in OptimizationProblems[J]. Bio Logical Cybernetics. 1985,(52):141-152.
[36]杜志江,孙立宁,富历新.医疗机器人发展概况综述[J].机器人. 2003,25(2):182-187.
[37] J.Arata, M.Mitsuishi, S.Warisawa, et al. Development of a dexterous minimally-invasive surgical system with augmented force feedback capability[C]. Proc. OfIEEE/RSJ International Conf. on Intelligent Robots and systems. 2005:3207-3212.
[38] M.Tavakoli, R.V.Patel, M.Moallem. A haptic interface for computer-integrated endoscopic surgery and training[J]. Virtual Reality. 2006,(9):160-176.
[39] M.Hashizume, K.Tsugawa. Robotic Surgery and Cancer: the Present State, Problems and Future Vision[J]. Japanese Journal of Clinical Oncology. 2004,(34):227-237.
[40]刘少强,黄惟一,王爱民,等.用于微创外科手术的遥控机器人系统研究现状及趋势[J].机器人. 2002,7(2):283-287.
[41] J.Gangloff, R.Ginhoux, J.Marescaux, et al. Model Predictive Control for Compensation of Cyclic Organ Motions in Teleoperated Laparoscopic Surgery[J]. IEEETransactions on Control Systems Technology. 2006,14(2):235-246.
[42]徐晶晶,陈孝凯,曾庆军.遥操作机器人系统软组织环境触觉建模实验[J].江苏科技大学学报:自然科学版. 2010,24(1):79-82.
[43]王伟.广义预测控制理论及其应用[M].北京:科学出版社, 1998. 9.
[44]郭旭,熊蓉,胡协和.全方位移动机器人的运动预测控制[J].电机与控制学报. 2007,11(1):79-82,87.
[45]曾庆军,王捍兵,徐晶晶.基于软组织环境的遥操作机器人系统预测控制研究[C].29th中国控制会议论文集.北京. 2010:3148-3152.
[46]王捍兵,曾庆军.基于软组织环境的遥操作机器人系统广义预测控制[J].东南大学学报:自然科学版. 2010,40(S1):337-342.
[47]焦军.基于网络的控制系统研究及应用[D].江苏:江苏科技大学硕士学位论文. 2007:50.
[48]陈家衡.预测函数控制及其应用研究[D].江苏:江苏科技大学硕士学位论文. 2007:45-51.
[49]徐涛.网络环境下遥操作机器人系统鲁棒控制研究[D].江苏:江苏科技大学硕士学位论文. 2007:48-58.
[50]张桐,陈国顺,王正林.精通LabVIEW程序设计[M].北京:电子工业出版社, 2008. 2-3.
[2]诸静.控制理论十年回顾与展望[J].浙江大学学报. 1993,27(4):1-7.
[3]丁宝苍,罗小锁,罗霄,等.先进控制理论[M].北京:电子工业出版社, 2010. 1-2.
[4]马亮.基于Elman神经网络的预测控制研究及应用[D].黑龙江:哈尔滨工程大学硕士学位论文. 2008:1-12
[5]百度百科.智能控制[EB]. http://baike.baidu.com/view/126735.htm#sub126735. 2011-02-27.
[6]王国军,陈松乔.自动控制理论发展综述[J].微型机与应用. 2000,(6):4-7.
[7]谢承泮.神经网络发展综述[J].科技情报开发与经济. 2006,16(12):148-150.
[8] J.Richalet, A.Rault, J.L.Testud, et al. Model Predictive Heuristic Control: Applications to Industrial Processes[J]. Automatica. 1978,14(5):413-438
[9] R.Rouhani, R.K.Mehra. Model Algorithmic Control (MAC): Basic Theortical Properties[J]. Automatica. 1982,18(4):401-414.
[10] C.R.Cutler, B.L.Ramaker. Dynamic Matrix Control: A Computer Control Algorithm[C]. Proc. of Joint Automatic Control Conference. San Francisco. 1980.
[11]陈增强,袁著祉,李玉梅,等.工业锅炉的加权预测自校正控制[J].自动化学报. 1993,19(01):46-53.
[12] M.Mahfouf, D.A.Linkens, A.J.Asbury, et al. Generalized Predictive Control (GPC) in the Operating Theatre[J]. IEE Proc. D. 1992,139(4):404-420.
[13]齐亮,俞孟蕻.基于支持向量机的船舶航向广义预测控制研究[J].中国航海. 2007,(3):54-56.
[14] M.Mercang?z, F.J.Doyle. Distributed Model Predictive Control of an expe-rimental four-tank system[J]. journal of Process Control. 2007,17(3):297-308.
[15]孙富春,李莉,孙增圻.非线性系统神经网络自适应控制的发展现状及展望[J].控制理论与应用. 2005,22(2):254-260.
[16]史一平.有界导数神经网络非线性预测控制应用研究[D].浙江:浙江大学硕士学位论文. 2008:2
[17]戴文战,娄海川,杨爱萍.非线性系统神经网络预测控制研究进展[J].控制理论与应用. 2009,26(5):521-530.
[18] W.E.Staib, J.N.Mcnames. Operating Experience from Intelligent Arc Furnace Installations[J]. Iron and Steel Engineer. 1994,71(5):38-40.
[19] R.N.Jose, H.wang. A Direct Adaptive Neural Nerwork Control for Unknown Nonlinear System and Its Application[J]. IEEE Trans on Nerual Network. 1998,9(1):27-33.
[20] J.Q.Hu, E.Rose. Generalized Predictive Control Using a Neural-Fuzzy Model[J]. Int. J. of System Sciences. 1999,30(1):117-122.
[21] M.Bongards. Improving the Efficiency of a Waster Water Treatment Plant bu Fuzzy Control and Neural Networks[J]. Waster Science and Technology. 2001,43(11):189-196.
[22]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.
[23]陈增强,袁著祉,刘宗信,等.涤纶片基拉膜生产线横向分布神经网络自校正预测控制[J].自动化学报. 2001,27(3):332-337.
[24]杜福银,徐扬.基于递归神经网络的预测模糊控制[J].西南交通大学学报. 2006,41(6):773-736.
[25]李届家,郭宏伟,文达.神经网络预测器在铝电解过程控制中的应用[J].沈阳建筑大学学报:自然科学版. 2006,22(6):1023-1026.
[26]陆冬娜.基于神经网络的非线性模型预测控制[D].浙江:浙江工业大学硕士学位论文. 2007:8.
[27]诸静.智能预测控制及其应用[M].浙江:浙江大学出版社, 2003. 29,30-35,43-44,39-40,50-51,107-109,114,116-118,134-137.
[28] P.R.Maurath, D.A.Mellichamp, D.E.Seborg. Predictive Controller Design for SISO Systems[C]. Proc. A.C.C. Boston. 1988.
[29] P.M.Bruijin, L.J.Bootsma. Predictive Control Using Impulse Response Models[C]. 6th IFAC/IFIP Conference. Dusseldorf. 1980.
[30]倪宏伟.基于神经网络的预测控制方法及其应用研究[D].湖南:中南大学硕士学位论文. 2006:11-16,16-19,28.
[31] D.W.Clarke, C.Mohtadi, P.S.Tuffs. Generalized Predictive Control[J]. PartⅠ. The Basic algorithm. 1987,23(2):137-148.
[32]焦李成.神经网络计算[M].西安:西安电子科技大学出版社, 1993.
[33]安志银.基于神经网络旋转二级倒立摆系统的预测控制研究[D].河北:燕山大学硕士学位论文. 2010:12-14.
[34]李国勇.智能控制及其MATLAB实现[M].北京:电子工业出版社, 2005. 31-35.
[35] J.J.Hopfield, D.W.Tank. Neural Computation of Decision in OptimizationProblems[J]. Bio Logical Cybernetics. 1985,(52):141-152.
[36]杜志江,孙立宁,富历新.医疗机器人发展概况综述[J].机器人. 2003,25(2):182-187.
[37] J.Arata, M.Mitsuishi, S.Warisawa, et al. Development of a dexterous minimally-invasive surgical system with augmented force feedback capability[C]. Proc. OfIEEE/RSJ International Conf. on Intelligent Robots and systems. 2005:3207-3212.
[38] M.Tavakoli, R.V.Patel, M.Moallem. A haptic interface for computer-integrated endoscopic surgery and training[J]. Virtual Reality. 2006,(9):160-176.
[39] M.Hashizume, K.Tsugawa. Robotic Surgery and Cancer: the Present State, Problems and Future Vision[J]. Japanese Journal of Clinical Oncology. 2004,(34):227-237.
[40]刘少强,黄惟一,王爱民,等.用于微创外科手术的遥控机器人系统研究现状及趋势[J].机器人. 2002,7(2):283-287.
[41] J.Gangloff, R.Ginhoux, J.Marescaux, et al. Model Predictive Control for Compensation of Cyclic Organ Motions in Teleoperated Laparoscopic Surgery[J]. IEEETransactions on Control Systems Technology. 2006,14(2):235-246.
[42]徐晶晶,陈孝凯,曾庆军.遥操作机器人系统软组织环境触觉建模实验[J].江苏科技大学学报:自然科学版. 2010,24(1):79-82.
[43]王伟.广义预测控制理论及其应用[M].北京:科学出版社, 1998. 9.
[44]郭旭,熊蓉,胡协和.全方位移动机器人的运动预测控制[J].电机与控制学报. 2007,11(1):79-82,87.
[45]曾庆军,王捍兵,徐晶晶.基于软组织环境的遥操作机器人系统预测控制研究[C].29th中国控制会议论文集.北京. 2010:3148-3152.
[46]王捍兵,曾庆军.基于软组织环境的遥操作机器人系统广义预测控制[J].东南大学学报:自然科学版. 2010,40(S1):337-342.
[47]焦军.基于网络的控制系统研究及应用[D].江苏:江苏科技大学硕士学位论文. 2007:50.
[48]陈家衡.预测函数控制及其应用研究[D].江苏:江苏科技大学硕士学位论文. 2007:45-51.
[49]徐涛.网络环境下遥操作机器人系统鲁棒控制研究[D].江苏:江苏科技大学硕士学位论文. 2007:48-58.
[50]张桐,陈国顺,王正林.精通LabVIEW程序设计[M].北京:电子工业出版社, 2008. 2-3.