基于物理神经网络的风电机组转矩-桨距角协同控制策略

米阳; 杨熙; 韩云昊; 李春煦; 袁明瀚; 郑晓亮

doi:10.19912/j.0254-0096.tynxb.2025-0173

PDF(1765 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (6) : 403-414. DOI: 10.19912/j.0254-0096.tynxb.2025-0173

基于物理神经网络的风电机组转矩-桨距角协同控制策略

米阳¹, 杨熙¹, 韩云昊¹, 李春煦¹, 袁明瀚², 郑晓亮³

作者信息 +

COLLABORATIVE CONTROL STRATEGY OF TORQUE-PITCH ANGLE OF WIND TURBINES BASED ON PHYSICS-INFORMED NEURAL NETWORKS

Mi Yang¹, Yang Xi¹, Han Yunhao¹, Li Chunxu¹, Yuan Minghan², Zheng Xiaoliang³

Author information +

文章历史 +

摘要

针对低风速下传统最大功率点追踪控制风能利用效率低和中高风速下传统比例积分（PI）桨距角控制器功率输出不稳定问题,提出基于物理信息神经网络和模型预测的全风速协同优化控制策略来提升风力机功率输出效率与稳定性。通过引入物理信息神经网络模型准确刻画风力机的动态特性并结合随机权重改变算法实现神经网络在线训练,进而设计以转矩和桨距角为目标的单一模型预测控制,同时基于动态设置成本函数实现低风速下的最大功率追踪与中高风速下的平稳功率输出。最后实验验证显示,所设计的全风速协同优化控制可有效改善风力机的动态响应性能,优化控制系统的实时性和风能利用效率。

Abstract

Under low wind speed conditions, conventional maximum power point tracking （MPPT） control strategies fail to effectively account for the dynamic influence of the pitch angle, leading to reduced wind energy utilization efficiency. Under medium and high wind speed conditions, traditional PI-based pitch angle controllers struggle to maintain stable power output. To address these challenges, this paper proposes a collaborative optimization strategy that integrates Physics-Informed Neural Networks （PINNs） with Model Predictive Control （MPC）. The PINN model accurately captures the dynamic characteristics of wind turbines, while an online training mechanism based on a stochastic weight adjustment algorithm enhances adaptability. A unified MPC strategy is developed, considering both torque and pitch angle as control variables. By dynamically adjusting the cost function, the proposed approach achieves maximum power tracking under low wind speed conditions and ensures stable power output under medium and high wind speed conditions. Experimental results validate that the proposed method significantly improves the dynamic response of the wind turbines, enhances real-time control performance, and increases wind energy utilization efficiency.

导出引用

米阳, 杨熙, 韩云昊, 李春煦, 袁明瀚, 郑晓亮. 基于物理神经网络的风电机组转矩-桨距角协同控制策略[J]. 太阳能学报. 2026, 47(6): 403-414 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0173

Mi Yang, Yang Xi, Han Yunhao, Li Chunxu, Yuan Minghan, Zheng Xiaoliang. COLLABORATIVE CONTROL STRATEGY OF TORQUE-PITCH ANGLE OF WIND TURBINES BASED ON PHYSICS-INFORMED NEURAL NETWORKS[J]. Acta Energiae Solaris Sinica. 2026, 47(6): 403-414 https://doi.org/10.19912/j.0254-0096.tynxb.2025-0173

中图分类号： TM614

参考文献

[1] 贺益康, 胡家兵. 双馈异步风力发电机并网运行中的几个热点问题[J]. 中国电机工程学报, 2012, 32(27): 1-15.
HE Y K, HU J B.Several hot-spot issues associated with the grid-connected operations of wind-turbine driven doubly fed induction generators[J]. Proceedings of the CSEE, 2012, 32(27): 1-15.
[2] YANG B, LIU B Q, ZHOU H Y, et al.A critical survey of technologies of large offshore wind farm integration: summary, advances, and perspectives[J]. Protection and control of modern power systems, 2022, 7(1): 1-32
[3] 吴璇, 赵文彬, 朱瑞. 鼠笼异步式风力机的新型控制方法研究[J]. 电力系统保护与控制, 2023, 51(18): 43-51.
WU X, ZHAO W B, ZHU R.A novel control method of a squirrel cage asynchronous generator for a wind turbine[J]. Power system protection and control, 2023, 51(18): 43-51.
[4] 陈毅东, 杨育林, 王立乔, 等. 风力发电最大功率点跟踪技术及仿真分析[J]. 高电压技术, 2010, 36(5): 1322-1326.
CHEN Y D, YANG Y L, WANG L Q, et al.Maximum power point tracking technology and simulation analysis for wind power generation[J]. High voltage engineering, 2010, 36(5): 1322-1326.
[5] ASGHAR A B, LIU X D.Adaptive neuro-fuzzy algorithm to estimate effective wind speed and optimal rotor speed for variable-speed wind turbine[J]. Neurocomputing, 2018, 272: 495-504.
[6] 李娟, 张克兆, 李生权, 等. 最佳叶尖速比的最大功率自抗扰跟踪控制[J]. 电机与控制学报, 2015, 19(12): 94-100, 106.
LI J, ZHANG K Z, LI S Q, et al.Maximum power point tracking control with active disturbance rejection controller based on the best tip speed ratio[J]. Electric machines and control, 2015, 19(12): 94-100, 106.
[7] SABZEVARI S, KARIMPOUR A, MONFARED M, et al.MPPT control of wind turbines by direct adaptive fuzzy-PI controller and using ANN-PSO wind speed estimator[J]. Journal of renewable and sustainable energy, 2017, 9: 013302.
[8] 李佳俊, 娄尧林, 应京良, 等. 基于直接转速控制的风电机组最大功率点跟踪策略研究[J]. 太阳能学报, 2024, 45(10): 607-615.
LI J J, LOU Y L, YING J L, et al.Research on maximum power point tracking strategy of wind turbine based on direct speed control[J]. Acta energiae solaris sinica, 2024, 45(10): 607-615.
[9] 朱连成, 肖阳, 苏晓英, 等. 双定子无刷双馈风力发电机无速度传感器反步法直接功率控制[J]. 太阳能学报, 2024, 45(4): 206-213.
ZHU L C, XIAO Y, SU X Y, et al.Sensorless back-stepping direct power control of dual-stator brushless doubly-fed wind power generator[J]. Acta energiae solaris sinica, 2024, 45(4): 206-213.
[10] KHAN M J, MATHEW L.Comparative study of optimization techniques for renewable energy system[J]. Archives of computational methods in engineering, 2020, 27(2): 351-360.
[11] 刘吉臻, 孟洪民, 胡阳. 采用梯度估计的风力发电系统最优转矩最大功率点追踪效率优化[J]. 中国电机工程学报, 2015, 35(10): 2367-2374.
LIU J Z, MENG H M, HU Y.Efficiency optimization of optimum torque maximum power point tracking based on gradient approximation for wind turbine generator system[J]. Proceedings of the CSEE, 2015, 35(10): 2367-2374.
[12] MOUSA H H H, YOUSSEF A R, MOHAMED E E M. State of the art perturb and observe MPPT algorithms based wind energy conversion systems: a technology review[J]. International journal of electrical power & energy systems, 2021, 126: 106598.
[13] UDDIN M N, AMIN I K.Adaptive step size based hill-climb search algorithm for MPPT control of DFIG-WECS with reduced power fluctuation and improved tracking performance[J]. Electric power components and systems, 2018, 46(19/20): 2203-2214.
[14] CORTES-VEGA D, ORNELAS-TELLEZ F, ANZUREZ-MARIN J.Comparative analysis of MPPT techniques and optimal control for a PMSG-based WECS[C]//2019 IEEE 4th Colombian Conference on Automatic Control (CCAC). Medellin, Colombia, 2019: 1-6.
[15] 曹娜, 苏亚妮, 于群. 运行参数变化时双馈风电机组振荡机理及特性研究[J]. 太阳能学报, 2024, 45(3): 54-64.
CAO N, SU Y N, YU Q.Study on oscillation mechanism and features of doubly-fed wind turbines with operating parameters changings[J]. Acta energiae solaris sinica, 2024, 45(3): 54-64.
[16] 宋卓彦, 王锡凡, 滕予非, 等. 变速恒频风力发电机组控制技术综述[J]. 电力系统自动化, 2010, 34(10): 8-17.
SONG Z Y, WANG X F, TENG Y F, et al.Overview of control technologies for variable-speed constant-frequency wind turbines[J]. Automation of electric power systems, 2010, 34(10): 8-17.
[17] 赵瑜, 周玮, 于芃, 等. 风电有功波动功率调节控制研究[J]. 中国电机工程学报, 2013, 33(13): 85-91.
ZHAO Y, ZHOU W, YU P, et al.Study on regulation and control of active wind power fluctuations[J]. Proceedings of the CSEE, 2013, 33(13): 85-91.
[18] 孙欣宇, 向东, 丁伟, 等. 基于麻雀搜索算法的风电机组独立变桨控制研究[J]. 太阳能学报, 2023, 44(10): 266-274.
SUN X Y, XIANG D, DING W, et al.Research on individual pitch control of wind turbine based on sparrow search algorithm[J]. Acta energiae solaris sinica, 2023, 44(10): 266-274.
[19] 金石, 张凤阁, 朱连成. 无刷双馈风力发电机的变速恒频最大功率跟踪[J]. 太阳能学报, 2014, 35(11): 2279-2286.
JIN S, ZHANG F G, ZHU L C.VSCF maximal power tracking for brushless doubly fed wind power generator[J]. Acta energiae solaris sinica, 2014, 35(11): 2279-2286.
[20] 李和明, 张祥宇, 王毅, 等. 基于功率跟踪优化的双馈风力发电机组虚拟惯性控制技术[J]. 中国电机工程学报, 2012, 32(7): 32-39, 188.
LI H M, ZHANG X Y, WANG Y, et al.Virtual inertia control of DFIG-based wind turbines based on the optimal power tracking[J]. Proceedings of the CSEE, 2012, 32(7): 32-39, 188.
[21] AFSHARIAN S, KARIMPOUR A.Wind turbine power tracking using multiple model predictive control[C]//2013 21st Iranian Conference on Electrical Engineering(ICEE). Mashhad, Iran, 2013: 1-6.
[22] 韩兵, 周腊吾, 陈浩, 等. 大型风电机组激光雷达辅助模型预测控制方法[J]. 中国电机工程学报, 2016, 36(18): 5062-5069.
HAN B, ZHOU (L /X)W, CHEN H, et al. Approach to model predictive control of large wind turbine using light detection and ranging measurements[J]. Proceedings of the CSEE, 2016, 36(18): 5062-5069.
[23] 田德, 周臣凯, 唐世泽, 等. 基于自适应模型预测控制的大型风电机组MPPT方法[J]. 太阳能学报, 2023, 44(6): 501-508.
TIAN D, ZHOU C K, TANG S Z, et al.MPPT method for large wind turbines based on adaptive model predictive control[J]. Acta energiae solaris sinica, 2023, 44(6): 501-508.
[24] 苏向敬, 山衍浩, 周汶鑫, 等. 基于GRU和注意力机制的海上风力机齿轮箱状态监测[J]. 电力系统保护与控制, 2021, 49(24): 141-149.
SU X J, SHAN Y H, ZHOU W X, et al.GRU and attention mechanism-based condition monitoring of an offshore wind turbine gearbox[J]. Power system protection and control, 2021, 49(24): 141-149.
[25] 张橙, 李雪, 叶茂, 等. 物理信息神经网络在两相流中的应用[J]. 化工学报, 2024, 75(11): 3835-3856.
ZHANG C, LI X, YE M, et al.Application of physics-informed neural network in two-phase flow[J]. CIESC journal, 2024, 75(11): 3835-3856.
[26] 杜轲, 齐婧, 高嘉伟, 等. 基于物理信息神经网络(PINN)方法的结构动力响应分析[J/OL]. 工程力学, 1-12[2025-01-02]. http://hp.kns.cnki.net.shiep.vpn358.com/kcms/detail/11.2595.o3.20240822.1525.006.html.
DU K, QI J, GAO J W, et al. Structural dynamic response analysis based on physical information neural network method [J/OL]. Engineering mechanics, 1-12 [2025-01-02]. http://hp.kns.cnki.net.shiep.vpn358.com/kcms/detail/11.2595.o3.20240822.1525.006.html.
[27] 向超群, 尹雪瑶, 伍珣, 等. 基于物理信息神经网络的牵引变流器直流支撑电容参数辨识方法[J]. 电工技术学报, 2024, 39(15): 4654-4667.
XIANG C Q, YIN X Y, WU X, et al.Parameter identification of DC-link capacitor in traction converter based on physical information neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(15): 4654-4667.
[28] WILLIAMS G, WAGENER N, GOLDFAIN B, et al.Information theoretic MPC for model-based reinforcement learning[C]//2017 IEEE International Conference on Robotics and Automation (ICRA). Singapore, 2017: 1714-1721.
[29] SHI G Y, SHI X C, O’CONNELL M, et al. Neural lander: stable drone landing control using learned dynamics[C]//2019 International Conference on Robotics and Automation (ICRA). Montreal, QC, Canada, 2019: 9784-9790.