无刷直流电机遗传RBF神经网络控制
|
摘要
无刷直流电机(BLDCM)体积小、重量轻、效率高,又克服了有刷直流电机机械换向带来的一系列缺点,因此在各个领域得到广泛应用。针对本身具有时变性、非线性、强耦合等特征的无刷直流电机,高性能的调速控制方法成为一个重要的研究方向,本文研究了智能控制算法在无刷直流电机控制中的应用。
PID控制是工业控制中最常用的方法,但用其对具有复杂非线性特性的对象或过程进行控制难以达到满意的效果。神经网络控制具有非线性映射能力、学习能力和自适应能力,是一种不依赖模型的控制方式,但是,神经网络的结构和初始值的选取影响控制器的性能,采用反复试验初始值的方法很难得到最优参数的控制器,这影响了该控制器的广泛应用。由Holland首先提出的遗传算法是模拟生物在自然环境中的遗传和进化过程而形成的一种随机搜索的全局优化算法,该方法可以全局搜索得到最优参数。基于遗传算法的控制器的参数优化成为控制器设计的一种有效方法。
针对径向基函数(RBF)神经网络的结构确定和隐层节点参数调节的不足,本文提出了一种基于遗传算法训练RBF神经网络控制器的无刷直流电机自适应控制方法。该方法利用遗传算法离线训练RBF神经网络的结构和隐层节点参数,构成速度控制器,在电机运行中通过控制器的在线修正,自适应地调节神经网络参数,同时电流环迅速跟踪给定电流的变化,达到使系统适应环境变化的目的。MATLAB仿真结果表明,该方法响应速度快、控制精度高,同时具有适应性好、鲁棒性强等优点。最后设计了以TMS320F2812为核心的电机调速系统硬件电路,对无刷直流电机调速系统进行了研究。
The brushless DC motors (BLDCM) have small sizes, low weight, and large power to volume ratio, and receive much attention in every field. Compared with brush DC motors, BLDCM overcome a series drawbacks brought by mechanical converted direction. The BLDCM is a multi-variable and non-linear system, so the research about the high performance of speed regulation becomes an important direction. This paper researches the application of intelligence algorithm in the control of BLDCM system.
Classical PID control is most common method in industry, but this method can’t gain satisfying effect to the complex and non-linear object or process. Neural network control has the ability of expressing arbitrary nonlinear mapping, learning and self-adaptive. The selection of topology structure and initial value influence the capability of controller, and the method of trial and error has much difficult in getting optimization parameter controller. Genetic algorithm first put forwarded by Holland is a global optimization algorithm of random search that simulate the process of inheritance and evolution formed in natural condition. Parameter optimization based on genetic algorithm becomes an effective method in designing controller.
To solve the deficiency of Radial Basis Function (RBF) neural network such as decision of structure and adjustment of parameters in hidden-unit, this paper presents an adaptive speed control approach based on genetic algorithm. In this approach, the RBF neural network whose structure and parameters of hidden-unit have been trained by genetic algorithm off-line constitutes a speed loop controller. The controller tunes parameters of neural network adaptively via the self-modifiability of network on-line. At the same time, the current loop controller traces the change of given current rapidly, so that the system can adapt to the variational environment. The results of MATLAB simulation prove that the approach has lots of good performances in response speed, control accuracy, adaptability and robust. Finally, a hard circuit based on digital signal processor (DSP) TMS320F2812 is designed to further research speed regulation system of BLDCM.
PID控制是工业控制中最常用的方法,但用其对具有复杂非线性特性的对象或过程进行控制难以达到满意的效果。神经网络控制具有非线性映射能力、学习能力和自适应能力,是一种不依赖模型的控制方式,但是,神经网络的结构和初始值的选取影响控制器的性能,采用反复试验初始值的方法很难得到最优参数的控制器,这影响了该控制器的广泛应用。由Holland首先提出的遗传算法是模拟生物在自然环境中的遗传和进化过程而形成的一种随机搜索的全局优化算法,该方法可以全局搜索得到最优参数。基于遗传算法的控制器的参数优化成为控制器设计的一种有效方法。
针对径向基函数(RBF)神经网络的结构确定和隐层节点参数调节的不足,本文提出了一种基于遗传算法训练RBF神经网络控制器的无刷直流电机自适应控制方法。该方法利用遗传算法离线训练RBF神经网络的结构和隐层节点参数,构成速度控制器,在电机运行中通过控制器的在线修正,自适应地调节神经网络参数,同时电流环迅速跟踪给定电流的变化,达到使系统适应环境变化的目的。MATLAB仿真结果表明,该方法响应速度快、控制精度高,同时具有适应性好、鲁棒性强等优点。最后设计了以TMS320F2812为核心的电机调速系统硬件电路,对无刷直流电机调速系统进行了研究。
The brushless DC motors (BLDCM) have small sizes, low weight, and large power to volume ratio, and receive much attention in every field. Compared with brush DC motors, BLDCM overcome a series drawbacks brought by mechanical converted direction. The BLDCM is a multi-variable and non-linear system, so the research about the high performance of speed regulation becomes an important direction. This paper researches the application of intelligence algorithm in the control of BLDCM system.
Classical PID control is most common method in industry, but this method can’t gain satisfying effect to the complex and non-linear object or process. Neural network control has the ability of expressing arbitrary nonlinear mapping, learning and self-adaptive. The selection of topology structure and initial value influence the capability of controller, and the method of trial and error has much difficult in getting optimization parameter controller. Genetic algorithm first put forwarded by Holland is a global optimization algorithm of random search that simulate the process of inheritance and evolution formed in natural condition. Parameter optimization based on genetic algorithm becomes an effective method in designing controller.
To solve the deficiency of Radial Basis Function (RBF) neural network such as decision of structure and adjustment of parameters in hidden-unit, this paper presents an adaptive speed control approach based on genetic algorithm. In this approach, the RBF neural network whose structure and parameters of hidden-unit have been trained by genetic algorithm off-line constitutes a speed loop controller. The controller tunes parameters of neural network adaptively via the self-modifiability of network on-line. At the same time, the current loop controller traces the change of given current rapidly, so that the system can adapt to the variational environment. The results of MATLAB simulation prove that the approach has lots of good performances in response speed, control accuracy, adaptability and robust. Finally, a hard circuit based on digital signal processor (DSP) TMS320F2812 is designed to further research speed regulation system of BLDCM.
引文
[1]王季秩,无刷电机的现在与将来,微特电机,1999,27(5):23-24
[2]张琛,直流无刷电动机原理及应用,机械工业出版社:北京,2004
[3]胡文静,永磁无刷直流电动机的发展及展望,微电机,2002,35(4):36-38
[4]叶金虎,无刷直流电动机,科学出版社,1982
[5]李烨,严新平,永磁无刷电动机技术发展水平及应用前景,微电机,2001,34(1):31-33
[6] Fengtai Huang,Dapeng Tien.A.Neural network approach to position sensorless control of brushless DC motors.Proc. IEEE IECON 22nd International Conference,1996,2:1167-1170
[7] Yufang Jin,Zhangjun Tang,Yangyang Wen, et al.High performance adaptive control for BLDC motor with real-time estimation of uncertainties.Applied Power Electronics Conference and Exposition,APEC '06,Twenty-First Annual IEEE.2006.3:19-23
[8] Buchnik.Y,Rabinovici.R.Speed and position estimation of brushless DC motor in very low speeds.Electrical and Electronics Engineers in Israel,23rd IEEE Convention of 6-7 Sept,2004:317-320
[9] Changliang Xia,Junhua Liu,Wei Yu, et al.Variable structure control of BLDCM based on extended state observer.Mechatronics and Automation,2005 IEEE International Conference Volume 2,2005 :568-571
[10]纪志成,沈艳霞,薛花,无刷直流电机自适应模糊控制的研究,中国电机工程学报,2005,25[5]:104-109
[11] Chang-Liang Xia,Wei Chen.Senseless control of brushless DC motors at low speed using neural networks . Machine Learning and Cybernetics ,2005.Proceedings of 2005 International Conference on Volume 2, 18-21 Aug.2005:1099-1103
[12]徐丽娜,神经网络控制,电子工业出版社,2002
[13]孙增圻,智能控制理论与技术,清华大学出版社,广西科学技术出版社,1997
[14]高隽,人工神经网络原理及仿真实例,机械工业出版社,2003
[15]陈炜,无刷直流电机卡尔曼法转子位置检测及模型参考自适应控制:[硕士学位论文],天津;天津大学,2003
[16] Miler,T.J.E.Brushless Permanent-Magnet and Reluctance Motor Drives.Oxford Science,Oxford,1989
[17] B.K.博斯,姜建国译,电力电子学与变频传动技术与应用,中国矿业大学出版社,1999
[18]朱耀忠,电机与电力拖动,北京航空航天大学出版社,2005
[19]黄立培,电动机控制,清华大学出版社,2003
[20]张相军,无刷直流电机无位置传感器控制技术的研究:[博士学位论文],上海;上海大学,2001
[21]牛海清,谢运祥,无刷直流电动机及其控制技术的发展,微电机,2002(5)
[22]王小平,曹立明,遗传算法-理论、应用,西安交通大学出版社,2002.1
[23]夏长亮,徐绍辉,基于遗传算法的超声波电机模糊自适应速度控制,中国电机工程学报,2003,23(3):99-103
[24]夏长亮,郭培健,史婷娜等,基于模糊遗传算法的无刷直流电机自适应控制,中国电机工程学报,2005,25(11):129-133
[25]夏定纯,人工智能技术与方法,华中科技大学出版社,2004
[26]王宏生,人工智能及其应用,国防工业出版社,2006
[27]李翔,从复杂到有序-神经网络智能控制理论新进展,上海交通大学出版社,2006
[28]虞和济,陈长征,张省等,基于神经网络的智能诊断,冶金工业出版社,2000
[29]戴先中,多变量非线性系统的神经网络逆控制方法,科学出版社,2005.12
[30]王凌,郑大钟,径向基函数神经网络结构的混合优化策略,清华学报:自然科学版,1999.39(7):50-53
[31]魏海坤,徐嗣鑫,宋文忠,RBF网学习的进化优选算法,控制理论与应用,2000,17(4):604-608
[32]赵清林,郭艳兵,梅强,齐占庆,确定RBF神经网络中心点的方法综述,广东自动化与信息工程,2002(2)
[33]阎平凡,张长水,人工神经网络与模拟进化计算,清华大学出版社,2000
[34]雷英杰,张善文,李续武等,遗传算法工具箱及应用,2005
[35]张明君,张化光,遗传算法优化的BP神经网络PID控制器,电气自动化,2005,27(6):3-5
[36]李红利,张晓彤,兰立柱等,基于遗传算法的RBF神经网络的优化设计方法,计算机仿真,2003,20(11):67-69
[37]董玲娇,冯冬青,基于改进遗传算法的模糊RBF神经网络控制器设计,计算机技术与自动化,2005,24(4):13-15
[38]王旭东,劭惠鹤,RBF神经网络理论及其在控制中的应用,信息与控制,1997,26(4):272-284
[39]石红瑞,刘勇,刘宝坤等,基于混合递阶遗传算法的径向基神经网络学习算法及其应用,控制理论与应用,2002(8)
[40]郑丕谔,马艳华,RBF神经网络的递阶遗传训练新方法,控制与决策,2003(3)
[41]夏长亮,祁温雅,杨荣等,基于混合递阶遗传算法和RBF神经网络的超声波电动机自适应速度控制,电工技术学报,2004(9)
[42]李方方,赵英凯,许必熙,基于递阶遗传算法优化神经网络的研究,机械与电子,2006(2)
[43] Man K . F , Tang K S . Genetic Algorithms for Control and Signal Processing.London:Spring-Vertag,1997
[44]郭培健,基于模糊遗传算法的无刷直流电机速度控制:[硕士学位论文],天津;天津大学,2004
[45]夏长亮,祁温雅,杨荣等,基于RBF神经网络的超声波电机参数辨识与模型参考自适应控制,中国电机工程学报,2004,24(7):18-22
[46]夏长亮,王娟,史婷娜等,基于自适应径向基函数神经网络的无刷直流电机直接电流控制,中国电机工程学报,2003,23(6):123-12
[47]王娟,基于RBFNN的无刷直流电机直接电流控制与转矩分析:[硕士学位论文],天津;天津大学,2003
[48]李正军,基于自抗扰控制器的无刷直流电机控制:[硕士学位论文],天津;天津大学,2004
[49] S Yilmaz, K Howard,T David A.Direct model reference adaptive control of permanent magnet brushless DC motors . IEEE Conference on Control Applications-Proceedings,1997.9:633-638
[50] M A Sartori,P J Antsaklis.Implementations of learning control systems using neural networks.IEEE Control System Magazine,1992,12(2): 49-57
[51] K Kyeong-Hwa,Y Myung-Joong.DSP-based high-speed sensorless control for a brushless DC motor using a DC link voltage.Electric Power Components and Systems,2002,30(9):889-906
[52] S Jianwen, N Dennis, T Maxime,et al.A novel microcontroller- based sensorless brushless DC (BLDC) motor drive for automotive fuel pumps.IEEE Transactions on Industry Applications,2003,39(6):1734-1740
[53] S Tomonobu, T Mutuwo, D Shinji,et al.Sensorless vector control of brushless DC motors using disturbance observer.PESC Record-IEEE Annual PowerElectronics Specialists Conference,1995,2:772-777
[54]苏奎峰,吕强,耿庆锋等,TMS320F2812原理与开发,电子工业出版社,2005
[55]孟繁荣,李一凡,龙三平,基于TMS320F2812的永磁同步电机调速系统设计,工业技术,2006(17):95-96
[56]夏俭军,张兴华,一种高性能DSP芯片TMS320F2812,微处理机,2005,12(6):80-82
[57]苏永芝,苏奎锋,吕强,应用F2812实现全数字交流伺服电机控制系统,装备指挥技术学院学报,2004,15(4):73-76
[58]王淑芳,张国英,马景兰等,基于DSP的数据采集系统开发与实现,北京石油化工学院学报,2003,13(1):7-12.
[59]王仁祥,王小曼,通用变频器选型、应用与维修,人民邮电出版社,2005
[60]佟纯厚,交流电动机晶闸管调速系统,机械工业出版社,1988
[61]天津电气传动设计研究所,电气传动自动化技术手册,机械工业出版社,2005
[62]张燕宾,电动机变频调速图解,中国电力出版社合,2003
[63]贺益康,交流电机调速系统计算机仿真,浙江大学出版社,1993
[64]楚斌,IR2110功率驱动集成芯片应用,电子工程师,2004,30(10):33-35
[2]张琛,直流无刷电动机原理及应用,机械工业出版社:北京,2004
[3]胡文静,永磁无刷直流电动机的发展及展望,微电机,2002,35(4):36-38
[4]叶金虎,无刷直流电动机,科学出版社,1982
[5]李烨,严新平,永磁无刷电动机技术发展水平及应用前景,微电机,2001,34(1):31-33
[6] Fengtai Huang,Dapeng Tien.A.Neural network approach to position sensorless control of brushless DC motors.Proc. IEEE IECON 22nd International Conference,1996,2:1167-1170
[7] Yufang Jin,Zhangjun Tang,Yangyang Wen, et al.High performance adaptive control for BLDC motor with real-time estimation of uncertainties.Applied Power Electronics Conference and Exposition,APEC '06,Twenty-First Annual IEEE.2006.3:19-23
[8] Buchnik.Y,Rabinovici.R.Speed and position estimation of brushless DC motor in very low speeds.Electrical and Electronics Engineers in Israel,23rd IEEE Convention of 6-7 Sept,2004:317-320
[9] Changliang Xia,Junhua Liu,Wei Yu, et al.Variable structure control of BLDCM based on extended state observer.Mechatronics and Automation,2005 IEEE International Conference Volume 2,2005 :568-571
[10]纪志成,沈艳霞,薛花,无刷直流电机自适应模糊控制的研究,中国电机工程学报,2005,25[5]:104-109
[11] Chang-Liang Xia,Wei Chen.Senseless control of brushless DC motors at low speed using neural networks . Machine Learning and Cybernetics ,2005.Proceedings of 2005 International Conference on Volume 2, 18-21 Aug.2005:1099-1103
[12]徐丽娜,神经网络控制,电子工业出版社,2002
[13]孙增圻,智能控制理论与技术,清华大学出版社,广西科学技术出版社,1997
[14]高隽,人工神经网络原理及仿真实例,机械工业出版社,2003
[15]陈炜,无刷直流电机卡尔曼法转子位置检测及模型参考自适应控制:[硕士学位论文],天津;天津大学,2003
[16] Miler,T.J.E.Brushless Permanent-Magnet and Reluctance Motor Drives.Oxford Science,Oxford,1989
[17] B.K.博斯,姜建国译,电力电子学与变频传动技术与应用,中国矿业大学出版社,1999
[18]朱耀忠,电机与电力拖动,北京航空航天大学出版社,2005
[19]黄立培,电动机控制,清华大学出版社,2003
[20]张相军,无刷直流电机无位置传感器控制技术的研究:[博士学位论文],上海;上海大学,2001
[21]牛海清,谢运祥,无刷直流电动机及其控制技术的发展,微电机,2002(5)
[22]王小平,曹立明,遗传算法-理论、应用,西安交通大学出版社,2002.1
[23]夏长亮,徐绍辉,基于遗传算法的超声波电机模糊自适应速度控制,中国电机工程学报,2003,23(3):99-103
[24]夏长亮,郭培健,史婷娜等,基于模糊遗传算法的无刷直流电机自适应控制,中国电机工程学报,2005,25(11):129-133
[25]夏定纯,人工智能技术与方法,华中科技大学出版社,2004
[26]王宏生,人工智能及其应用,国防工业出版社,2006
[27]李翔,从复杂到有序-神经网络智能控制理论新进展,上海交通大学出版社,2006
[28]虞和济,陈长征,张省等,基于神经网络的智能诊断,冶金工业出版社,2000
[29]戴先中,多变量非线性系统的神经网络逆控制方法,科学出版社,2005.12
[30]王凌,郑大钟,径向基函数神经网络结构的混合优化策略,清华学报:自然科学版,1999.39(7):50-53
[31]魏海坤,徐嗣鑫,宋文忠,RBF网学习的进化优选算法,控制理论与应用,2000,17(4):604-608
[32]赵清林,郭艳兵,梅强,齐占庆,确定RBF神经网络中心点的方法综述,广东自动化与信息工程,2002(2)
[33]阎平凡,张长水,人工神经网络与模拟进化计算,清华大学出版社,2000
[34]雷英杰,张善文,李续武等,遗传算法工具箱及应用,2005
[35]张明君,张化光,遗传算法优化的BP神经网络PID控制器,电气自动化,2005,27(6):3-5
[36]李红利,张晓彤,兰立柱等,基于遗传算法的RBF神经网络的优化设计方法,计算机仿真,2003,20(11):67-69
[37]董玲娇,冯冬青,基于改进遗传算法的模糊RBF神经网络控制器设计,计算机技术与自动化,2005,24(4):13-15
[38]王旭东,劭惠鹤,RBF神经网络理论及其在控制中的应用,信息与控制,1997,26(4):272-284
[39]石红瑞,刘勇,刘宝坤等,基于混合递阶遗传算法的径向基神经网络学习算法及其应用,控制理论与应用,2002(8)
[40]郑丕谔,马艳华,RBF神经网络的递阶遗传训练新方法,控制与决策,2003(3)
[41]夏长亮,祁温雅,杨荣等,基于混合递阶遗传算法和RBF神经网络的超声波电动机自适应速度控制,电工技术学报,2004(9)
[42]李方方,赵英凯,许必熙,基于递阶遗传算法优化神经网络的研究,机械与电子,2006(2)
[43] Man K . F , Tang K S . Genetic Algorithms for Control and Signal Processing.London:Spring-Vertag,1997
[44]郭培健,基于模糊遗传算法的无刷直流电机速度控制:[硕士学位论文],天津;天津大学,2004
[45]夏长亮,祁温雅,杨荣等,基于RBF神经网络的超声波电机参数辨识与模型参考自适应控制,中国电机工程学报,2004,24(7):18-22
[46]夏长亮,王娟,史婷娜等,基于自适应径向基函数神经网络的无刷直流电机直接电流控制,中国电机工程学报,2003,23(6):123-12
[47]王娟,基于RBFNN的无刷直流电机直接电流控制与转矩分析:[硕士学位论文],天津;天津大学,2003
[48]李正军,基于自抗扰控制器的无刷直流电机控制:[硕士学位论文],天津;天津大学,2004
[49] S Yilmaz, K Howard,T David A.Direct model reference adaptive control of permanent magnet brushless DC motors . IEEE Conference on Control Applications-Proceedings,1997.9:633-638
[50] M A Sartori,P J Antsaklis.Implementations of learning control systems using neural networks.IEEE Control System Magazine,1992,12(2): 49-57
[51] K Kyeong-Hwa,Y Myung-Joong.DSP-based high-speed sensorless control for a brushless DC motor using a DC link voltage.Electric Power Components and Systems,2002,30(9):889-906
[52] S Jianwen, N Dennis, T Maxime,et al.A novel microcontroller- based sensorless brushless DC (BLDC) motor drive for automotive fuel pumps.IEEE Transactions on Industry Applications,2003,39(6):1734-1740
[53] S Tomonobu, T Mutuwo, D Shinji,et al.Sensorless vector control of brushless DC motors using disturbance observer.PESC Record-IEEE Annual PowerElectronics Specialists Conference,1995,2:772-777
[54]苏奎峰,吕强,耿庆锋等,TMS320F2812原理与开发,电子工业出版社,2005
[55]孟繁荣,李一凡,龙三平,基于TMS320F2812的永磁同步电机调速系统设计,工业技术,2006(17):95-96
[56]夏俭军,张兴华,一种高性能DSP芯片TMS320F2812,微处理机,2005,12(6):80-82
[57]苏永芝,苏奎锋,吕强,应用F2812实现全数字交流伺服电机控制系统,装备指挥技术学院学报,2004,15(4):73-76
[58]王淑芳,张国英,马景兰等,基于DSP的数据采集系统开发与实现,北京石油化工学院学报,2003,13(1):7-12.
[59]王仁祥,王小曼,通用变频器选型、应用与维修,人民邮电出版社,2005
[60]佟纯厚,交流电动机晶闸管调速系统,机械工业出版社,1988
[61]天津电气传动设计研究所,电气传动自动化技术手册,机械工业出版社,2005
[62]张燕宾,电动机变频调速图解,中国电力出版社合,2003
[63]贺益康,交流电机调速系统计算机仿真,浙江大学出版社,1993
[64]楚斌,IR2110功率驱动集成芯片应用,电子工程师,2004,30(10):33-35