Abstract：Owing to the stochastic nature of wind speed,time-variable of parameters,system lagging and system nonlinearities the power generated by wind turbines appears to instable change. To improve the dynamic performance in the operation region of constant power output,a sliding mode variable structure controller using RBF neural network is proposed based on analyses of the features of wind turbine generator system. The initial centers through a FCM algorithm and the weights of network is obtained through recursive least squares(RLS) in off-line training. The sliding mode error is introduced in the adaptive law to improve the performance of the systems. The strategy mentioned above has such advantages as strong ability of rejecting chattering,well robust to the variation of parameter and fast response. Coupled with neural network control it also effectively reduces the chattering of only using a sliding mode variable structure control system. The simulink model of variable pitch system is built with Matlab/Simulink and simulation results also were compared. The results show that the controller has strong adaptability,good robustness and dynamic performance.
秦斌，周浩，杜康，王欣. 基于RBF网络的风电机组变桨距滑模控制[J]. 电工技术学报, 2013, 28(5): 37-41.
Qin Bin,Zhou Hao,Du Kang,Wang Xin. Sliding Mode Control of Pitch Angle Based on RBF Neural-Network. Transactions of China Electrotechnical Society, 2013, 28(5): 37-41.
[1] 叶杭冶. 风力发电机组的控制技术[M]. 2版. 北京: 机械工业出版社, 2007. [2] 郭金东, 赵栋利, 林资旭, 等. 兆瓦级变速恒频风力发电机组控制系统[J]. 中国电机工程学报, 2007, 27(6): 1-6. Guo Jindong, Zhao Dongli, Lin Zixu, et al. Research of the megawatt level variable speed constant frequency wind power unit control system[J]. Proceedings of the CSEE, 2007, 27(6): 1-6. [3] 廖勇, 何金波, 姚骏, 等. 基于变桨距和转矩动态控制的直驱永磁同步风力发电机功率平滑控制[J]. 中国电机工程学报, 2009, 29(18): 71-77. Liao Yong, He Jinbo, Yao Jun, et al. Power smoothing control strategy of direct-driven permanent magnet synchronous generator of wind turbines with pitch angle control and torque dynamic control[J]. Proceedings of the CSEE, 2009, 29(18): 71-77. [4] Kusiak A, Li W, Song Z. Dynamic control of wind turbines[J]. Renewable Energy, 2010, 35(2): 456-463. [5] Anca Hansen, Florin Iov, Poul Sorensen, et al. Overall control strategy of variable speed doubly-fed induction generator wind turbine[C]. Nordic Wind Power Conference, Gotebog, Sweden, 2004. [6] 张新房, 徐大平. 风力发电机组的变论域自适应模糊控制[J]. 控制工程, 2003, 10(4): 342-345. Zhang Xinfang, Xu Daping. Adaptive fuzzy control based on variable universe of wind turbines[J]. Control Engineering of China, 2003, 10(4): 342-345. [7] A Tapia, J X Ostolaza. Modeling and control of a wind turbine driven doubly-fed induction generator[J]. IEEE Transactions on Energy Conversion, 2003, 18(2): 194-200. [8] 张雷. 滑模变结构控制在风力发电机组变桨控制中的应用[J]. 电气应用, 2009, 28(4): 78-81. Zhang Lei. Application of sliding mode control in pitch angle control of wind power system[J]. Electrotechnical Application, 2009, 28(4): 78-81. [9] 胡剑波, 庄开宇. 高级变结构控制理论与应用[M]. 西安: 西北工业大学出版社, 2008. [10] Kanellos F D, Hatziargyriou N D. A new control scheme for variable speed wind turbines using neural networks[C]. Power Engineering Society Winter Meeting, New York, USA, 2002, 1: 360-365. [11] 秦斌, 吴敏, 王欣. 模糊神经网络模型混沌混合优化学习算法及应用[J]. 控制与决策, 2005, 20(3): 261-265. Qin Bin, Wu Min, Wang Xin. Hybrid chaos optimization algorithm for fuzzy neural network model and its applications[J]. Control and Decision, 2005, 20(3): 261-265. [12] Young Woon Woo, Doo Heon Song, et al. FCM-based RBF network in identifying concrete slab surface cracks[J]. IEEE Intelligent Systems Design and Applications, 2008, 1(1): 664 -669. [13] 秦斌, 吴敏, 王欣, 等. 基于模糊神经网络的多变量解耦控制[J]. 小型微型计算机系统, 2002, 23(5): 561-564. Qin Bin, Wu Min, Wang Xin, et al. Multivariable decoupling control based on fuzzy neural networks[J]. Mini-Micro System, 2002, 23(5): 561-564.
2013, Vol. 28 
