Abstract:The high saturation of magnetic circuit and the doubly salient structure of switched reluctance motor (SRM) make the flux linkage a nonlinear function of rotor position and phase current. In this paper, the pi-sigma fuzzy neural network, which has the merit of T-S type fuzzy logic and neural network, is adopted to develop the nonlinear model of SRM and an adaptive learning rate training algorithm with momentum is applied. Relatively high precision model of SRM is implemented. It has simple structure, less training epoch and fast online calculation. The sampled phase current and rotor position are non-equally spaced. Thus a reasonable distribution of measured data is reached. The precision and generalization ability of the model are improved. Meanwhile the number of measured data is reduced. Compared with the measured data and generalization validate data, the output data of the model are in good agreement with those data. This proves that the precision of the model developed in this paper is relatively high. The model has the merits of relatively strong generalization ability, simple structure and fast calculation.
修杰, 夏长亮, 王世宇. 开关磁阻电机的Pi-sigma模糊神经网络建模[J]. 电工技术学报, 2009, 24(8): 46-51.
Xiu Jie, Xia Changliang, Wang Shiyu. Modeling of Switched Reluctance Motor Based on Pi-Sigma Fuzzy Neural Network. Transactions of China Electrotechnical Society, 2009, 24(8): 46-51.
[1] Lawrenson P T, et al. Variable-speed switched reluctance motors[J]. IEE Proceedings, 1980, 127(B) (4): 253-265. [2] Corda J. Linear analysis of switched reluctance motor[C]. ICEM, Lausanne, 1984, 1: 281-284. [3] Giuseppe S Buja, Mm’a I Valla. Control character- istics of the SRM drives, part II: operation in the saturated region[J]. IEEE Transactions on Industrial Electronics, 1994, 41(3): 316-325. [4] Torrey D A, Lang J H. Modeling a nonlinear variable-reluctance motor drive[J]. IEE Proceedings of Electric Power Applications, 1990, 137(5): 314-326. [5] Mecrow B C, Weiner C, Clothier A C. The modeling of switched reluctance machines with magnetically coupled windings[C]. IEEE Industry Applications Conference, Rome, 2000, 1: 79-86. [6] Roux C, Morcos M M. A simple model for switched reluctance motors[J]. IEEE Power Engineering Review, 2000, 20(10): 49-52. [7] Salmasi F R, Fahimi B. Modeling switched-reluctance Machines by decomposition of double magnetic saliencies[J]. IEEE Transactions on Magnetics, 2004, 40(3): 1556-1561. [8] Moson I, Iwan K, Nieznanski J. Circuit-oriented model of the switched reluctance motor for drive systems simulation[C]. IEEE 28th Annual Conference of the Industrial Electronics Society, Sevilla, 2002, 1: 497-501. [9] Moallem M, Ong C M. Prediction the steady-state performance of a switched reluctance machine[J]. IEEE Transactions on Industry Applications, 1992, 27(6): 1087-1094. [10] Radun A. Analytically computing the flux linked by a switched reluctance motor phase when the stator and rotor poles overlap[J]. IEEE Transactions on Magnetics, 2000, 36(4):1996-2003. [11] Hossain S A, Husain I. Modeling simulation and control of switched reluctance motor drives[C]. The 29th Annual Conference of the IEEE Industrial Electronics Society, Roanoke, 2003, 3: 2447-2452. [12] Michaelides A M, Pollock C. Modeling and design of switched reluctance motors with two phases simultaneously excited[J]. IEE Proceedings of Electrical and Power Application, 1996, 143(5): 361-370. [13] Radimov N, Ben Hail N, Rabinaovici R. Simple model of switched reluctance machine based on only aligned and unaligned position data[J]. IEEE Transactions on Magnetics, 2004, 40(3): 1562-1572. [14] Elmas C, et al. Modeling of a nonlinear switched reluctance drive based on artificial neural networks[C]. IEE Power Electronics and Variable Speed Drives, London, 1994, 399:7-12. [15] 纪良文, 蒋静坪, 何峰. 基于径向基函数神经网络的开关磁阻电机建模[J]. 电工技术学报, 2001, 16(4): 7-11. [16] 李大芃, 王守臣, 诸静. 开关磁阻电机的模糊神经网络模型[J]. 中国电机工程学报, 2000, 20(1): 11-14. [17] 蒋全, 周鹗. 利用正弦交流电源测量基本磁化曲线的方法[J]. 微特电机, 1989, 5: 1-5.