为了获取开关磁阻电机(SRM)的精确模型,提出了一种基于径向基函数(RBF)神经网络对SRM进行建模的方法,主要包括离线建模和在线建模两部分。离线建模通过实验测量得到SRM的磁链特性曲线,并利用该数据训练RBF神经网络,实现SRM磁链的离线建模;在线建模是指当SRM的运行状态发生变化时,离线模型的估计磁链与实际磁链会产生误差,通过对神经网络的输出权值进行在线调节,实现具有在线动态调节功能的SRM在线模型。为了验证该方法的可行性,针对一台12/8结构的SRM样机进行仿真和实验,结果表明SRM的离线模型和在线模型在仿真和实验条件下均能正确地估计SRM的磁链特性,而且在线模型的估计精度高于离线模型,验证了本文的研究方法合理有效。
To obtain the accurate switched reluctance motor(SRM) model, the offline and online modeling schemes based on radial basis fuction (RBF) neural network are investigated in this paper. Firstly, an offline modeling scheme is studied. The flux linkage characteristics are obtained from experiment and used as a training data set, based on which an RBF neural network is trained to obtain the offline SRM model. Secondly, an online modeling method is proposed. When the operating conditions of the SRM changes, the offline model is not able to approximate the real-time SRM characteristics accurately. Based on the approximation error, an online modeling scheme is applied to improve the model accuracy by regulating the values of the RBF weights online. To verify the feasibility of this method, both the offline and online modeling schemes are tested in simulations and experiments using a 12/8 SRM. The results show that both the offline and online models can estimate the flux linkage characteristics correctly and the online model is more accurate than the offline model. Simulation and experimental results have verified the effectiveness and advantages of this modeling methods.
[1] Wang H H. Speed modulation control technique of switched reluctance motor. Beijing: China Machine Press, 1995. (in Chinese) 王宏华. 开关型磁阻电动机调速控制技术. 北京: 机械工业出版社, 1995.
[2] Wu J H. Design and application of switched reluctance motor. Beijing: China Machine Press, 2000. (in Chinese) 吴建华. 开关磁阻电机设计与应用. 北京: 机械工业出版社, 2000.
[3] Krishnan R, Arumugan R, Lindsay J F. Design procedure for switched reluctance motors. IEEE Transactions on Industry Applications, 1988, 24(3): 456-461.
[4] Ding W, Liang D L. Nonlinear mathematic model and finite element analysis for a 12/8 pole dual-channel switched reluctance machine. Electric Machines and Control, 2009, 13(2): 190-196. (in Chinese) 丁文, 梁得亮. 12/8极双通道开关磁阻电机非线性数学模型与有限元分析. 电机与控制学报, 2009, 13(2): 190-196.
[5] Xie D X, Yan X K, Zhang Y H, et al. Three dimensional finite element analysis of winding magnetic flux linkage in rotary electric machines. Proceedings of the CSEE, 2006, 26(21): 143-148. (in Chinese) 谢德馨, 阎秀恪, 张奕黄, 等. 旋转电机绕组磁链的三维有限元分析. 中国电机工程学报, 2006, 26(21): 143-148.
[6] Xue X D, Cheng K W E, Ho S L. Simulation of swished reluctance motor drives using two dimensional bicubie spline. IEEE Transactions on Energy Conversion, 2002, 17(4): 471-477.
[7] Lin Z Y, Reay D S, Williams B W, et al. Online modeling for switched reluctance motors using B-spline neural networks. IEEE Transactions on Industrial Electronics, 2007, 54(6): 3317-3322.
[8] Rajandran R V, Ramasamy G, Sahoo N C. Flux linkage model optimization using binary coded genetic algorithm for switched reluctance motor. IEEE PEDS. 2005: 898-902.
[9] Cheok A D, Ertugrul N. Use of fuzzy logical for modeling, estimation and prediction in switched reluctance motor drives. IEEE Transactions on Industrial Electronics, 1999, 46(6): 1207-1224.
[10] Mese E, Torry D A. An approach for sensorless position estimation for switched reluctance motor using artificial neural networks. IEEE Transactions on Power Electro-nics, 2002, 17(1): 66-75.
[11] Ding W, Liang D L. Modeling and simulation of switched reluctance motor based on RBFN-AFS. Transactions of China Electrotechnical Society, 2009, 24(9): 44-52. (in Chinese) 丁文, 梁得亮. 基于RBFN-AFS的开关磁阻电机非线性模型与动态仿真. 电工技术学报, 2009, 24(9): 44-52.
[12] Lu M J, Guo Q. RBFNN and rapid realization by DSP. Electronic Measurement Technology, 2008, 31(1): 153-155. (in Chinese) 吕孟军, 郭琪. RBF神经网络算法及在定点DSP上的快速实现. 电子测量技术, 2008, 31(1): 153-155.
[13] Xia C L, Qi W Y, Yang R, et al. Identification and model reference adaptive control for ultrasonic motor based on RBF neural network. Proceedings of the CSEE, 2004, 24(7): 117-121. (in Chinese) 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): 117-121.
[14] Jiang C S, Wang C Q, Wei H K, et al. Automatic control and application. Beijing: Science Press, 2007. (in Chinese) 姜长生, 王从庆, 魏海坤, 等. 智能控制与应用. 北京: 科学出版社, 2007.
[15] Cao J Y, Zhou Z D, Chen Y P, et al. Methods of characteristic measurement and model parameter identification for switched reluctance motors. Transactions of China Electrotechnical Society, 2004, 19(11): 25-30. (in Chinese) 曹家勇, 周祖德, 陈幼平, 等. 开关磁阻电动机特性检测与参数辨识方法研究. 电工技术学报, 2004, 19(11): 25-30.
[16] Cheng W S. Automatic control theory, method and application. Beijing: Tsinghua University Press, 2009. (in Chinese) 程武山. 智能控制理论, 方法与应用. 北京: 清华大学出版社, 2009.
CJA