摘要
开关磁阻电动机(Switched Reluctance Motor,SRM)具有结构简单、工作可靠、效率高和成本较低等优点,在很多领域都显示出强大的竞争力,但是其位置传感器的存在不仅削弱了SRM结构简单的优势,而且降低了系统高速运行的可靠性,增加了成本,于是探索实用的无位置传感器检测转子位置的方案便成为开关磁阻电机驱动系统(SwitchedReluctance Motor Drive,SRD)研究的热点。SRM高度非线性的电磁特性决定了在精确的数学模型基础上实现无位置传感器控制十分困难,而人工神经网络的出现为解决这个问题提供了新的思路。BP(Back Propagation)神经网络是目前研究最多、应用最广泛的一种多层前馈神经网络,具有收敛速度快、非线性逼近能力强等优点。本文提出了一种利用改进的BP网络来实现SRM无位置传感器的转子位置检测方法,该方法以电机三相绕组的相电流、磁链作为输入,转子位置作为输出,建立SRM电流、磁链与转子位置之间的非线性映射,从而实现SRM无位置传感器的转子位置检测。
在现阶段,为了保证神经网络的检测精度与收敛速度,神经网络的训练样本数据一般都是电机在某一特定条件下的运行数据,并不能反映电机的实际运行情况。针对这一情况,本文提出了一种训练数据实时更新的思想,并将其引入到神经网络的输入向量中。在神经网络训练过程中,根据电机的实际运行情况,将不同运行情况下的三相绕组的相电流、磁通、转子位置角作为训练样本,分批次对建立的神经网络模型进行训练,直到网络的检测精度趋于稳定并达到要求为止。
仿真结果表明,本文所提出的改进的BP神经网络在电机不同的运行情况下都能够实现SRM转子位置的准确检测,从而实现了电机的无位置传感器控制。神经网络检测精度高,动态特性好,具有较好的自适应性和鲁棒性。
Due to its simple construction, reliability, high efficiency and low cost, switched reluctance motor (SRM) has shown huge competitive power in many fields. But mechanical position sensors add to the cost, complexity and potential unreliability at high speed and this has motivated the investigation of sensorless position estimation. Because of its high nonlinear electromagnetism characteristic, the sensorless control based on accurate model of SRM is hard to be accomplished. In recent years, artificial neural network(ANN) technology has made a great progress, which gives a new method to accomplish position sensorless control of SRM.A novel indirect detecting method of SRM's rotor postion based on BP(Back Propagation) neural network is presented in this paper. For the adopted network,the training data set is comprised of magnetization data of the SRM for which three-phase current and flux linkage are inputs and the corresponding position is the output, the BP neural network can build up a correlation among phase current, phase flux linkage and position, thereby facilitating elimination of the rotor position sensor.
At the present stage, in order to ensure the forecast precision and the convergence rate of the neural network, the neural network's training sample data is generally the electrical motor's operation data under the specified condition which can not reflect the real running situation of the electrical motor. In view of this situation, this paper proposes a method based on training data real-time renewal, and introduces the idea to the input vector of neural network. In neural network's training process, according to the real running situation of the electrical motor, takes the three-phase current, flux linkage and rotor position in different operation circumstances as training sample, to train the established neural network model in batches, until the network's forecast precision tends to be stable and meet the requirement.
The simulation results show that the improved BP neural networks proposed in the paper can realize SRM rotor position's accurate prediction in case of different operation of the electrical motor,and realizing the motor's control without position sensor. The neural network has high forecast precision, favorable dynamic characteristics, better adaptability and robustness.
引文
[1]徐丙垠.畅想开关磁阻电动机(SRD)的未来[N].科技日报,2006-5-22(5).
[2]徐捷.SRD系统在棉花加工行业的应用前景[J].中国棉花加工,2006,6:24-26.
[3]Ehsani M,Fahimi B.Elimination of Position Sensors in Switched Reluctance Motor Drives:State of the Art and Future Trends[J].IEEETrans.Ind.Electron,2002,Feb,49,No.1:40-47.
[4]龙瑜.磁阻电动机模糊控制的研究[J].中国农机化,2006,(04),85-87.
[5]胡崇岳.现代交流调速技术[M].北京:机械工业出版社,1998.
[6]吴建华.开关磁阻电即设计与应用[M].北京:机械工业出版社,2006.
[7]孙建忠,白凤仙.特种电机及其控制[M].北京:中国水利水电出版社,2005.
[8]王宏华.开关型磁阻电动机调速控制技术[M].北京:机械工业出版社,1995.
[9]刘敏,周建国,贾好来.SR电机调速系统技术研究热点[J].中小型电机,2001,28(5):11-13.
[10]艾武,吴保全,曹家勇等.SRM间接位置检测技术综述[J].中小型电机,2004,31(2):48-54.
[11]Acarnley P P,Hill B J,Hooper C W.Detection of Rotor Position in Stepping and Switched Motors by Monitoring of Current Wave forms[J].IEEE Trans.on Industrial Electronics,1985,32(3):215-222.
[12]Panda S K,Amaratunga G A J.Waveform Detection Technique for lndirect Rotor Position Sensing of SwitchwedReluctanceMotorDrives[J].Partl.Analysis,IEEE.Proc.B,1993,140(1):80-88.
[13]张莲,陈鸿雁.开关磁阻电动机调速系统位置检测技术评述[J].重庆工学院报,2002,16(3):65-68.
[14]Broeck H.Vetal.Switched Reluctance Driveand PWM Induction Motor Drive ComPared for Low cost Application[J].Proc.EPE,1993,6:71-76.
[15]EImas C,Zelaya-De.Position Sensorless Operation of a Switched Reluctance Drive Based on Observer[C].Power Electronics and Applications,1993,Fifth European Conference on,1993,6(13-16):A21-27.
[16]Preston M A,Lyons J P.A switched reluctance motor model with mutual coupling and multi-phase excitation[J].IEEE Transactions on Magnetics,1991,Nov,6:5423-5425.
[17]Ehsani M,Husain I and Kuikami A B.Elimination of Discrete Position Sensor and Current Sensor in Switched Reluctance Motor Drivers[J].IEEE Transactions on Industry Applications,1992,1(ⅠA-28):128-135.
[18]Ehsani M and Husain I.Rotor Position Sensing in Switched Reluctance Motor Drivers by Measuring Mutually Induced Voltages[J].IEEE Transactions on IAS,1992,3:p422-429.
[19]王旭东,孙奕黄.无位置传感器开关磁阻电动机位置的检洲与预报[J].中国电机工程学报,2002(7):5-8.
[20]Cheok A,Ertugrul N A.Model Free Fuzzy Logic Based Rotor Position Sensorless Switched Reluctance Motor Drives[C].Industry Applications Conference,1996,Thirty-first IAS Annual Meeting, IAS96 Conference Record of the 1996,1(6-10):761-783.
[21]A.Bellini,,F Flipetti,G Franceschinietal.Position Sensorless Control of a SRM Drive using ANN-Techniques[C].Proc.IEEE IAS Annu.Meeting,1998:533-539.
[22]D S Reay,B W Williams.Sensorless Position Detection using Neural Networks for the Control of Switched Reluctance Motors[J].Proc,IEEEInt,Conf,Contr,Applicat,1999,2:1073-1077.
[23]周素莹,林辉.基于神经网络的开关磁阻电机转子位置估计[J].微电机,2006,39(2):16-18.
[24]詹琼华,王双红.开关磁阻电动机电容式位置检测技术[J].电工技术学报,1999,14(3):1-5.
[25]毛良明,,经亚枝,樊小明等.反串线圈法间接位置检测技术在开关磁阻发电机系统中的应用研究[J].中国电机工程学报,2000,20(10):27-30.
[26]Hoang Le-Huy,Patrice Brunelle.A Versatile Nonlinear Switched Reluctance Motor Model in Simulink using Realistic and Analytical Magnetization Characteristics[J].Industrial Electronics Society,2005,IECON 2005,32nd Annual conference of IEEE Volume,Issue,6-10 Nov.2005 Page(s):6-10.
[27]Simon Haykin.Neural Networks A Comprehensive Foundation[M].Pearson Education,1999.
[28 降人厚.智能控制理论和方法[M].西安:西安电子科技大学出版社,1999.
[29]从爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术大学出版社,1998.
[30]侯祥林,胡英,李永强等.多层人人工神经网络合理结构的确定方法[J].东北大学学报(自然科学版),2003,01:35-38.
[31]郭晶,周激流,张晔等.人脸识别系统中的BP网分类方法[J].四川大学学报(自然科学版),1999,6:518-522.
[32]伍春香,刘琳.三层BP网隐层节点数确定方法的研究[J].武汉测绘科技大学学报,1999,24(2):177-179.
[33]陈桂明,张明照,戚红雨等.应用MATLAB建模与仿真[M],北京:科学出版社,2001.
[34]范影乐,杨胜天,李轶等.MATLAB仿真应用详解[M],北京:人们邮电出版社,2001.
[35]陈新,郑洪涛,蒋静坪.基于MATLAB的开关磁阻电动机非线性动态模型仿真[J].电气传动,2002(6):55-57.
[36]田茂昕,马志源,詹琼华.基于MATLAB的开关磁阻发电机数字仿真[J].中小型电机,2001,28(2):13-18.
[37]梁正学.基于Matlab的SR电机稳态运行仿真分析[J].自动化设计与应用,测试技术与自动化卷,2004.3.23-24
[38]Chong-Chul,Kim Jin Hur,Dong-Seok Hyun.Simulation of a Switched Reluctance Motors Using Matlab/M-file[C]。 IECON02 Industrial Electronics Society,IEEE 2002 28th Annual Conference,2002,Nov,5:1066-1071.
[39]D A Torrey,X M Niu,E J Unkauf.Analytical modelling of variable-reluctance machine magnetisation characteristics[J].IEE Proceedings -Electric Power Applications,Vol,142,Nol,January 1995:14-22.
[40]H Le-Huy,P Brunelle.Design and Implementation of a Switched Reluctance Motor Genetic Model for Simulink SimPowerSystems[J].Electrimacs2005,Conference.
[41]F Soares,P J Costas Brance.Simulation of a 6/4 Switched Reluctance Motor Based on Matlab/Simulink Environment.IEEE.Transactions on Aerospace and Electronic Systems Vol,No3,July 2001:989-1009.
[42]魏静韬.SRD动态模型仿真及控制方案的研究[D].硕士论文,大庆石油学院,2005.
[43]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.