基于改进粒子群算法与神经网络的磁轴承控制研究
|
摘要
磁轴承具有无摩擦、寿命长、无需润滑、回转精度高等优点,被广泛应用于航天、机械加工、动力传动、能源交通等领域。磁轴承控制系统是一个涉及了电磁学、控制科学、机械科学以及转子动力学等多门学科的复杂非线性开环不稳定系统。本文研究对象是主动磁轴承,采用基于改进粒子群算法优化的神经网络在线调整PID控制器参数的方式来实现对磁悬浮转子的闭环控制。本文主要做了以下几个方面的工作：
阐述磁轴承控制系统的基本构成和工作原理。通过分析磁轴承系统中的电磁关系建立磁轴承控制系统的数学模型。介绍PID控制算法并针对算法的不足提出改进措施。在此基础上提出磁轴承PID控制方案并对设计的磁轴承PID控制器设置相关参数进行仿真研究,在深入分析仿真结果后提出采用BP神经网络在线调整PID控制器参数KP,K1,KD的值。
提出磁轴承BP神经网络PID控制器设计方案。根据系统复杂程度设定BP神经网络结构,选取2个输入神经元,15个隐层神经元,3个输出神经元。BP网络的两个输入分别是磁悬浮转子的位移偏差和偏差的变化率,三个输出分别对应PID控制器的三个参数KP,K1,KD。先根据一组输入输出样本数据对BP神经网络进行离线训练,然后BP网络根据系统性能在线调整网络权值系数使得P1D控制器参数最优。
针对BP算法的不足引入粒子群算法。通过分析粒子群算法中各个参数对算法性能的影响,提出相应的改进方法,其中重点提出基于动态变异思想的改进粒子群算法。该算法主要对粒子群算法中的惯性权重w进行改进,即先使w线性衰减,再根据粒子收敛的具体情况对惯性权重w进行二次修正。利用改进粒子群算法替代BP算法优化神经网络的权值系数。在此基础上,提出基于改进粒子群算法优化的磁轴承神经网络PID控制方案。仿真结果表明,经改进粒子群算法优化设计的磁轴承神经网络PID控制方案不仅使磁悬浮转子具有优良的动态性能和稳态性能,而且使控制系统具备良好的抗干扰能力。
Magnetic bearings with no friction, long life, no lubrication, high turning precision, is widely used in aerospace, mechanical processing, power transmission, energy, transportation and other fields. Magnetic bearing control system is an equipment involved electromagnetic, control theory, mechanical theory, rotor dynamics and other subjects of the complex non-linear open-loop unstable system. The research object is the active magnetic bearings. In this paper, improved particle swarm optimization is used to optimize neural network and adjust the PID controller parameters online to achieve closed-loop control of magnetic suspension rotor. In this paper, I do the following work.
Magnetic bearing control system is described the basic structure and working principle. The mathematical model of Magnetic bearing system is established by analyzing the relationship between the electromagnetic magnetic bearing control system. The disadvantage of PID control algorithm is described and the improvement measures are proposed. The magnetic bearing PID controller design is proposed on the base of PID algorithms. Then the program is set right parameters to simulation. Deeply analysis the simulation results presented by BP neural network PID controller.
It is proposed a magnetic bearing BP neural network PID controller design. On the basis of the complexity of the system to set BP neural network structure, select 2 input neurons,15 hidden layer neurons, three output neurons. The two inputs are the displacement of the rotor magnetic deviation and deviation the rate of change, three outputs are corresponding to the three parameters of PID controller. A group of sample based on input s and outputs data is used to train BP neural network. BP network based on system performance and then adjust the network weights coefficient line to set the optimal PID controller parameters.
The particle swarm optimization is introduced to solve the advantage of the BP algorithm. Particle swarm algorithm is improved by analyzing the various parameters on algorithm performance, the corresponding improved method, which highlight the dynamic variation of ideas based on improved particle swarm optimization. The algorithm is mainly about the particle swarm algorithm to improve the weight of inertia, that is, firstly to adjust as the linear attenuation, according to the specific circumstances of the convergence of particle inertia weight for the second amendment. Alternative use of improved particle swarm optimization neural network BP algorithm weight value. On this basis, improved particle swarm optimization based on the magnetic bearing neural network PID control scheme is proposed.Simulation results show that the improved particle swarm optimization design of magnetic bearing PID neural network control scheme not only has excellent magnetic rotor dynamic performance and steady-state performance, but also the control system with good anti-jamming capability.
阐述磁轴承控制系统的基本构成和工作原理。通过分析磁轴承系统中的电磁关系建立磁轴承控制系统的数学模型。介绍PID控制算法并针对算法的不足提出改进措施。在此基础上提出磁轴承PID控制方案并对设计的磁轴承PID控制器设置相关参数进行仿真研究,在深入分析仿真结果后提出采用BP神经网络在线调整PID控制器参数KP,K1,KD的值。
提出磁轴承BP神经网络PID控制器设计方案。根据系统复杂程度设定BP神经网络结构,选取2个输入神经元,15个隐层神经元,3个输出神经元。BP网络的两个输入分别是磁悬浮转子的位移偏差和偏差的变化率,三个输出分别对应PID控制器的三个参数KP,K1,KD。先根据一组输入输出样本数据对BP神经网络进行离线训练,然后BP网络根据系统性能在线调整网络权值系数使得P1D控制器参数最优。
针对BP算法的不足引入粒子群算法。通过分析粒子群算法中各个参数对算法性能的影响,提出相应的改进方法,其中重点提出基于动态变异思想的改进粒子群算法。该算法主要对粒子群算法中的惯性权重w进行改进,即先使w线性衰减,再根据粒子收敛的具体情况对惯性权重w进行二次修正。利用改进粒子群算法替代BP算法优化神经网络的权值系数。在此基础上,提出基于改进粒子群算法优化的磁轴承神经网络PID控制方案。仿真结果表明,经改进粒子群算法优化设计的磁轴承神经网络PID控制方案不仅使磁悬浮转子具有优良的动态性能和稳态性能,而且使控制系统具备良好的抗干扰能力。
Magnetic bearings with no friction, long life, no lubrication, high turning precision, is widely used in aerospace, mechanical processing, power transmission, energy, transportation and other fields. Magnetic bearing control system is an equipment involved electromagnetic, control theory, mechanical theory, rotor dynamics and other subjects of the complex non-linear open-loop unstable system. The research object is the active magnetic bearings. In this paper, improved particle swarm optimization is used to optimize neural network and adjust the PID controller parameters online to achieve closed-loop control of magnetic suspension rotor. In this paper, I do the following work.
Magnetic bearing control system is described the basic structure and working principle. The mathematical model of Magnetic bearing system is established by analyzing the relationship between the electromagnetic magnetic bearing control system. The disadvantage of PID control algorithm is described and the improvement measures are proposed. The magnetic bearing PID controller design is proposed on the base of PID algorithms. Then the program is set right parameters to simulation. Deeply analysis the simulation results presented by BP neural network PID controller.
It is proposed a magnetic bearing BP neural network PID controller design. On the basis of the complexity of the system to set BP neural network structure, select 2 input neurons,15 hidden layer neurons, three output neurons. The two inputs are the displacement of the rotor magnetic deviation and deviation the rate of change, three outputs are corresponding to the three parameters of PID controller. A group of sample based on input s and outputs data is used to train BP neural network. BP network based on system performance and then adjust the network weights coefficient line to set the optimal PID controller parameters.
The particle swarm optimization is introduced to solve the advantage of the BP algorithm. Particle swarm algorithm is improved by analyzing the various parameters on algorithm performance, the corresponding improved method, which highlight the dynamic variation of ideas based on improved particle swarm optimization. The algorithm is mainly about the particle swarm algorithm to improve the weight of inertia, that is, firstly to adjust as the linear attenuation, according to the specific circumstances of the convergence of particle inertia weight for the second amendment. Alternative use of improved particle swarm optimization neural network BP algorithm weight value. On this basis, improved particle swarm optimization based on the magnetic bearing neural network PID control scheme is proposed.Simulation results show that the improved particle swarm optimization design of magnetic bearing PID neural network control scheme not only has excellent magnetic rotor dynamic performance and steady-state performance, but also the control system with good anti-jamming capability.
引文
[1]G.施韦策,H.布鲁勒,A.特拉克斯勒.主动磁轴承基础、性能及应用[M].北京：新时代出版社,1997
[2]苏义鑫,周祖德,胡业发,张丹红.磁力轴承功率放大器的研究[J].武汉理工大学报,2003,25(6)：43-45
[3]汪希平,袁崇军,谢友柏.磁悬浮轴承系统的控制策略与功放电路的设计[J].西安：西安交通大学学报,1995,29(12)：68-74
[4]江伟.磁轴承数字控制系统的研究[D].北京：清华大学,1990
[5]杨怀玉,陈龙.被动磁力轴承在磁悬浮技术中的应用[J].太原：机械工程与自动化,2005(04)：10-3
[6]EM097新技术系列报道之二,电主轴——当前最热门的功能部件,世界机电市场,1998.2
[7]陈立群.电磁轴承精度控制及其应用研究[D].西安,西安交通大学,1999
[8]韩卫沙,张京军.基于滑模控制的半主动悬架系统仿真分析[J].成都：西华大学学报(自然科学版).2011,19(2)：10-13
[9]樊仲光,梁家荣,肖剑.不确定奇异系统的Terminal滑模控制.北京：系统工程与电子技术,2010,01(2)：11-15
[10]魏海坤.神经网络结构设计的理论与方法[J].北京：国防工业出版社,2005：55-56
[11]付丽强.磁力轴承的鲁棒控制和神经网络控制[D].福州：福州大学,2001
[12]王勤.基于神经网络的磁轴承系统辨识和控制研究[D].武汉：武汉理工大学,2007
[13]徐春广,武涵,吕冬明等.基于神经网络的磁轴承自适应控制器[J].北京：机床与液压,2010,07(8)：25-30
[14]王士杰.常规PID调节系统的研究进展[J].上海：中国纺织大学学报,1994,4：104112
[15]王春麟,喻应东,胡业发等.磁力轴承模糊PID控制算法的研究[J].北京：机床与液压,2006,11(11)：11-20
[16]高志华,胡业发.磁力轴承系统PID控制特性的研究.太原：机械工程与自动化,2005,05(6)：33-34
[17]Eamshaw S. On the nature of molecular forces which regulate the constitution of aluminiferous ether[J].Tran Camb Phil Soc 7,1983:97-112
[18]G.Schweiter, H.Bleuler, A.Traxler. Active Magnetic Bearings Basics Properties and Application of Active magnetic Bearings. ETH:Switzerland,1994
[19]G.Schweitzer. Proceedings of the First International Symposium on Magnetic Bearings. Zurich:Switzerland:June 1988
[20]赵鸿宾.磁悬浮技术综述[M].国际学术动态[J].1992(5)：43-47
[21]李远景,张安喆.飞轮电池控制技术与发展[J].济南：科技信息,2008,30(3)：22-25
[22]张钢,殷庆振,蒋德得,谢振宇.磁悬浮轴承-柔性转子系统的结构设计.轴承,2010,6(10)：1-7
[23]孙首群,韩琳,卢华阳.电磁轴承柔性转子系统动态响应分析[J].西安：机械科学与技术.2007,02(9)：2-6
[24]朱秋,孙玉坤.最优控制理论在磁轴承控制系统中的应用研究[J].广州：控制理论与应用,2002,19(3)：479-483
[25]张金淼.H∞控制理论在磁悬浮轴承系统中的应用研究[D].南京：南京航空航天大学,2005
[26]范素香.基于H∞控制理论的磁悬浮系统控制研究[D].长沙：中南大学,2004
[27]Sheng Zhang, Asakura T.,Xiaoli Xu. Fault diagnosis system for rotary machines based on fuzzy neural networks; Advanced Intelligent Mechatronics,2003. AIM 2003. Proceedings. 2003 IEEE/ASME International Conference on Volume 1,20-24 July 2003 Page(s):199-204 vol.1
[28]任志淼.模糊控制系统的现状与展望[J].山西：山西电子技术,2011(01)
[29]吕治国,邓跃,刘中平.磁悬浮球系统的一种非线性控制方法研究[J].天津：航空精密制造技术,2011,2(10)：56-60
[30]朱盈,朱俊.多种PID控制及其仿真比较[J].工业控制计算机,2010,1(2)：13-17
[31]解启荣,姚荣斌,李生权等.基于动态神经网络的自整定PID控制策略[J].北京：微计算机信息,2010,1(12)：22-30
[32]廉师友.人工智能技术导论[M].西安：西安电子科技大学出版社,2000：164-165
[33]茹菲,李铁鹰.人工神经网络系统辨识综述.软件导刊,2011,3(2)：1-3
[34]王斐,张育中,闻时光,吴成东.基于过程神经网络的步态模式自动分类[J].沈阳：东北大学学报(自然科学版),2011,4(3)：45-49
[35]韩丰田,吴秋平,张嵘.有源静电轴承的滑模控制[J].北京：清华大学学报(自然科学版),2009,2(11)：23-27
[36]周保民,廖瑛.未知非线性系统自适应改进RBF滑模控制.北京：计算机工程与应用,2011,9(5)：31-38
[37]李辉,陈道琳,蔡敏.基于神经网络的模糊控制[J].哈尔滨：信息技术,2010,3(2)：54-55
[38]刘衍民,牛奔,赵庆祯.多目标优化问题的粒子群算法仿真研究[J].成都：计算机应用研究,2011,2(6)22-30
[39]王存睿,段晓东,刘向东等.改进的基本粒子群优化算法[J].上海：计算机工程,2004,30(21)
[40]王晓霞,王涛,谷根代等.基于改进粒子群优化的神经网络及应用[J].河北：华北电力大学学报,2009,9,(36)
[41]Lacher R C. Back-Propagation Learning in Expert Networks. IEEE Transaction on Neural Networks,1992,1(3):62-72
[42]Minakawa, T.,Ichikawa, Y.,Kunugi,. Development and implementation of a power system fault diagnosis expert system; Power Systems, IEEE Transactions on Volume 10, Issue 2, May 1995 Page(s):932-940 Digital Object Identifier 10.1109/59.387936
[43]Nguyen Derrick H, Widrow B. Neural networks for self-learning control systems. IEEE Control Systems Magazine, April,1990
[44]Isermann R. Fault diagnosis of machines via parameter estimation and Knowledge processing-tutorialpaper.Automatica,1993,29(4):815-835
[45]Anju Anand, Arunk. Hierarchical Analysis of Fault Trees with Dependencies, using Decomposition. IEEE Proceedings Annual Reliability And Maintainability symposium, 1998,69-75
[46]Michael Scharfe, Karl Meizer, Ralf Zimmermann. Development of a Magnetic-Bearing Momentum Wheel,2001
[47]Fujita M. Loop Shaping Based Robust Control of a Magnetic Bearing. IEEE Cont rol System Magazine,1993,13 (4):57-65
[48]Zhuang M., Atherton D. P. Automatic tuning of optimum PID controllers. proc. IEE, Pt. D, 1993,35.329-331
[49]高强,彭海军,吴志刚,钟万勰等.非线性动力学系统最优控制问题的保辛求解方法[J].湖南：动力学与控制学报,2010,1,(36)
[2]苏义鑫,周祖德,胡业发,张丹红.磁力轴承功率放大器的研究[J].武汉理工大学报,2003,25(6)：43-45
[3]汪希平,袁崇军,谢友柏.磁悬浮轴承系统的控制策略与功放电路的设计[J].西安：西安交通大学学报,1995,29(12)：68-74
[4]江伟.磁轴承数字控制系统的研究[D].北京：清华大学,1990
[5]杨怀玉,陈龙.被动磁力轴承在磁悬浮技术中的应用[J].太原：机械工程与自动化,2005(04)：10-3
[6]EM097新技术系列报道之二,电主轴——当前最热门的功能部件,世界机电市场,1998.2
[7]陈立群.电磁轴承精度控制及其应用研究[D].西安,西安交通大学,1999
[8]韩卫沙,张京军.基于滑模控制的半主动悬架系统仿真分析[J].成都：西华大学学报(自然科学版).2011,19(2)：10-13
[9]樊仲光,梁家荣,肖剑.不确定奇异系统的Terminal滑模控制.北京：系统工程与电子技术,2010,01(2)：11-15
[10]魏海坤.神经网络结构设计的理论与方法[J].北京：国防工业出版社,2005：55-56
[11]付丽强.磁力轴承的鲁棒控制和神经网络控制[D].福州：福州大学,2001
[12]王勤.基于神经网络的磁轴承系统辨识和控制研究[D].武汉：武汉理工大学,2007
[13]徐春广,武涵,吕冬明等.基于神经网络的磁轴承自适应控制器[J].北京：机床与液压,2010,07(8)：25-30
[14]王士杰.常规PID调节系统的研究进展[J].上海：中国纺织大学学报,1994,4：104112
[15]王春麟,喻应东,胡业发等.磁力轴承模糊PID控制算法的研究[J].北京：机床与液压,2006,11(11)：11-20
[16]高志华,胡业发.磁力轴承系统PID控制特性的研究.太原：机械工程与自动化,2005,05(6)：33-34
[17]Eamshaw S. On the nature of molecular forces which regulate the constitution of aluminiferous ether[J].Tran Camb Phil Soc 7,1983:97-112
[18]G.Schweiter, H.Bleuler, A.Traxler. Active Magnetic Bearings Basics Properties and Application of Active magnetic Bearings. ETH:Switzerland,1994
[19]G.Schweitzer. Proceedings of the First International Symposium on Magnetic Bearings. Zurich:Switzerland:June 1988
[20]赵鸿宾.磁悬浮技术综述[M].国际学术动态[J].1992(5)：43-47
[21]李远景,张安喆.飞轮电池控制技术与发展[J].济南：科技信息,2008,30(3)：22-25
[22]张钢,殷庆振,蒋德得,谢振宇.磁悬浮轴承-柔性转子系统的结构设计.轴承,2010,6(10)：1-7
[23]孙首群,韩琳,卢华阳.电磁轴承柔性转子系统动态响应分析[J].西安：机械科学与技术.2007,02(9)：2-6
[24]朱秋,孙玉坤.最优控制理论在磁轴承控制系统中的应用研究[J].广州：控制理论与应用,2002,19(3)：479-483
[25]张金淼.H∞控制理论在磁悬浮轴承系统中的应用研究[D].南京：南京航空航天大学,2005
[26]范素香.基于H∞控制理论的磁悬浮系统控制研究[D].长沙：中南大学,2004
[27]Sheng Zhang, Asakura T.,Xiaoli Xu. Fault diagnosis system for rotary machines based on fuzzy neural networks; Advanced Intelligent Mechatronics,2003. AIM 2003. Proceedings. 2003 IEEE/ASME International Conference on Volume 1,20-24 July 2003 Page(s):199-204 vol.1
[28]任志淼.模糊控制系统的现状与展望[J].山西：山西电子技术,2011(01)
[29]吕治国,邓跃,刘中平.磁悬浮球系统的一种非线性控制方法研究[J].天津：航空精密制造技术,2011,2(10)：56-60
[30]朱盈,朱俊.多种PID控制及其仿真比较[J].工业控制计算机,2010,1(2)：13-17
[31]解启荣,姚荣斌,李生权等.基于动态神经网络的自整定PID控制策略[J].北京：微计算机信息,2010,1(12)：22-30
[32]廉师友.人工智能技术导论[M].西安：西安电子科技大学出版社,2000：164-165
[33]茹菲,李铁鹰.人工神经网络系统辨识综述.软件导刊,2011,3(2)：1-3
[34]王斐,张育中,闻时光,吴成东.基于过程神经网络的步态模式自动分类[J].沈阳：东北大学学报(自然科学版),2011,4(3)：45-49
[35]韩丰田,吴秋平,张嵘.有源静电轴承的滑模控制[J].北京：清华大学学报(自然科学版),2009,2(11)：23-27
[36]周保民,廖瑛.未知非线性系统自适应改进RBF滑模控制.北京：计算机工程与应用,2011,9(5)：31-38
[37]李辉,陈道琳,蔡敏.基于神经网络的模糊控制[J].哈尔滨：信息技术,2010,3(2)：54-55
[38]刘衍民,牛奔,赵庆祯.多目标优化问题的粒子群算法仿真研究[J].成都：计算机应用研究,2011,2(6)22-30
[39]王存睿,段晓东,刘向东等.改进的基本粒子群优化算法[J].上海：计算机工程,2004,30(21)
[40]王晓霞,王涛,谷根代等.基于改进粒子群优化的神经网络及应用[J].河北：华北电力大学学报,2009,9,(36)
[41]Lacher R C. Back-Propagation Learning in Expert Networks. IEEE Transaction on Neural Networks,1992,1(3):62-72
[42]Minakawa, T.,Ichikawa, Y.,Kunugi,. Development and implementation of a power system fault diagnosis expert system; Power Systems, IEEE Transactions on Volume 10, Issue 2, May 1995 Page(s):932-940 Digital Object Identifier 10.1109/59.387936
[43]Nguyen Derrick H, Widrow B. Neural networks for self-learning control systems. IEEE Control Systems Magazine, April,1990
[44]Isermann R. Fault diagnosis of machines via parameter estimation and Knowledge processing-tutorialpaper.Automatica,1993,29(4):815-835
[45]Anju Anand, Arunk. Hierarchical Analysis of Fault Trees with Dependencies, using Decomposition. IEEE Proceedings Annual Reliability And Maintainability symposium, 1998,69-75
[46]Michael Scharfe, Karl Meizer, Ralf Zimmermann. Development of a Magnetic-Bearing Momentum Wheel,2001
[47]Fujita M. Loop Shaping Based Robust Control of a Magnetic Bearing. IEEE Cont rol System Magazine,1993,13 (4):57-65
[48]Zhuang M., Atherton D. P. Automatic tuning of optimum PID controllers. proc. IEE, Pt. D, 1993,35.329-331
[49]高强,彭海军,吴志刚,钟万勰等.非线性动力学系统最优控制问题的保辛求解方法[J].湖南：动力学与控制学报,2010,1,(36)