基于RBF神经网络的直驱风力发电系统反推控制

摘要/Abstract

摘要： 考虑风力发电系统的高度非线性及不确定性,提出永磁直驱式风力发电系统反推控制策略,实现最大风能跟踪。利用RBF神经网络的学习和估计能力,设计未知扰动观测器,在逼近系统未知部分的基础上优化控制器设计。仿真结果表明,所用方法提高了系统转速跟踪能力,提高了风能捕获效率。

关键词: 风力发电系统, 非线性, 最大功率捕获, 径向基函数神经网络, 反推控制

Abstract: Considering the high nonlinearity and uncertainty of wind power generation system, a reverse thrust control strategy for permanent magnet direct drive wind power generation system was proposed to achieve maximum wind energy tracking. Using the learning and estimation ability of the RBF neural network, an unknown disturbance observer was designed, and the controller design was optimized on the basis of approximating the unknown part of the system. The simulation results show that the method used improves the speed tracking ability of the system and improves the efficiency of wind energy capture.

Key words: wind power generation system, nonlinear, maximum power capture, radial basis function(RBF) neural network, backstepping control

中图分类号:

TM351

周尔卓, 沈艳霞. 基于RBF神经网络的直驱风力发电系统反推控制[J]. 微特电机, 2022, 50(6): 41-45.

ZHOU Erzhuo, SHEN Yanxia. Backstepping Control of Direct-driven Wind Power Generation System Based on RBF Neural Network[J]. Small & Special Electrical Machines, 2022, 50(6): 41-45.

参考文献

[1] 李晖,刘栋,姚丹阳.面向碳达峰碳中和目标的我国电力系统发展研判[J].中国电机工程学报,2021,41(18):6245-6259.
[2] 朱蓉,王阳,向洋,等.中国风能资源气候特征和开发潜力研究[J].太阳能学报,2021,42(6):409-418.
[3] SONG Y, LIANG L, TAN M.Neuroadaptive power tracking control of wind farms under uncertain power demands[J].IEEE Transactions on Industrial Electronics,2017(9):7071-7078.
[4] BO L,TANG W,XIAHOU K,et al.Development of novel robust regulator for maximum wind energy extraction based upon perturbation and observation[J].Energies,2017,10(4):569.
[5] MOURABIT Y E,DEROUICH A,GHZIZAL A E,et al.Nonlinear backstepping control for PMSG wind turbine used on the real wind profile of the Dakhla cm orocco city[J].International Transactions on Electrical Energy Systems,2020(4):1-6.
[6] WANG Y, WANG X, XU X. Backstepping control of primary permanent magnet linear synchronous motor based on adaptive RBF observer[C]//2021 IEEE International Conference on Power Electronics,Computer Applications (ICPECA),2021, 957-961.
[7] LIN C H, LIN M K, WU R C.Integral backstepping control for a permanent magnet synchronous motor using adaptive recurrent neural network uncertainty observer[J].Advanced Science,Engineering and Medicine,2012,4(5):442-447.
[8] 吴定会,杨德亮,肖仁.基于LPV观测器的永磁同步电机反推控制[J].测控技术,2019,38(8):113-118.
[9] 张开明,史宏俊,郭涛.采用滑模自适应控制的永磁同步风力发电系统最大功率控制[J].电力系统及其自动化学报,2019,31(7):143-150.
[10] 王金铭,卢奭瑄,何新,等.大型风力发电机风能利用系数参数拟合的研究[J].太阳能学报,2012,33(2):221-225.
[11] CECATI C, KOLBUSZ J,ROZYCKI P, et al.A novel RBF training algorithm for short-term electric load forecasting and comparative studies[J]. IEEE Transactions on Industrial Electronics,2015,62(10),6519-6529.
[12] 付东学,赵希梅.基于径向基函数神经网络的永磁直线同步电机反推终端滑模控制[J].电工技术学报,2020,35(12):2545-2553.

[1]	朱德明, 张军, 白晨光. 基于卡尔曼滤波器的永磁同步电机自抗扰控制[J]. 微特电机, 2022, 50(5): 62-67.
[2]	刘爱民, 刘权, 娄家川, 于秀孺. 基于天牛须算法的新型开关磁阻电机优化研究[J]. 微特电机, 2022, 50(4): 1-6.
[3]	苗雨, 赵希梅. 基于智能分数阶互补滑模的PMLSM直接推力控制[J]. 微特电机, 2022, 50(4): 46-51.
[4]	曾子元,李云桓. 基于扩张状态观测器的四旋翼无人机飞行控制系统研究[J]. 微特电机, 2022, 50(1): 41-44.
[5]	王腾飞, 李海江. 大功率直驱风力发电机轴承应力场有限元计算[J]. 微特电机, 2021, 49(9): 24-27.
[6]	白晨光, 魏晓静, 邱鑫, 杨建飞, 葛浩锐, 金振, 张永民. 永磁同步电机非线性自抗扰复合型控制策略研究[J]. 微特电机, 2021, 49(4): 46-50.
[7]	李梦茹, 冬雷, 冉茂莹, 于坤洋. 开关磁阻电机无位置传感器控制方法综述[J]. 微特电机, 2021, 49(1): 51-54.
[8]	田雨, 康尔良. 永磁同步电机神经网络速度控制器设计[J]. 微特电机, 2020, 48(6): 49-52.
[9]	娄佩宾, 黄茹楠. 基于非线性干扰观测器的PMSM自适应反演滑模控制[J]. 微特电机, 2020, 48(5): 32-35.
[10]	雷学国,蒋学程. 表贴式PMSM转子初始位置非线性估计[J]. 微特电机, 2019, 47(3): 15-17.
[11]	. 考虑驱动器参数的混合式步进电动机精细化模型[J]. 微特电机, 2019, 47(12): 1-7.
[12]	杨洋. 基于积分鲁棒的电液伺服系统渐进控制[J]. 微特电机, 2019, 47(1): 78-81.
[13]	王宝军,王家军. 永磁同步电动机的速度指定位置跟踪控制[J]. 微特电机, 2018, 46(6): 67-73.
[14]	何彪, 张琪, 陈世军, 黄苏融. 逆变器供电永磁同步电机铁耗和永磁体损耗分析[J]. 微特电机, 2018, 46(5): 35-38.
[15]	彭妍洁, 王海涛, 陈玉峰, 徐明. 永磁同步电机的积分反推-滑模转角控制[J]. 微特电机, 2018, 46(5): 58-61.