龚礼,张梦瑶,赵鑫鑫,罗浩,张道源,焦绪国
GONG Li,ZHANG Mengyao,ZHAO Xinxin,LUO Hao,ZHANG Daoyuan,JIAO Xuguo

• 1:青岛理工大学信息与控制工程学院

摘要(Abstract)：

针对传统OTC（最优转矩控制）算法转速调节较慢导致风能捕获效率降低的问题，提出了一种基于DDPG（深度确定性策略梯度）和ICC（惯性补偿控制）的风电机组新型OTC算法。基于DDPG算法，根据风轮转速与风速实时在线更新增益系数；为进一步提升转速跟踪动态，结合ICC原理添加了惯性补偿项；为克服补偿项中对气动转矩传感器或机理建模的依赖，采用BLS（宽度学习系统）估计气动转矩。采用Open FAST进行仿真验证，结果表明所提方法能够有效提升风轮转速跟踪动态，从而提高风能捕获效率。
Conventional optimal torque control(OTC) strategies suffer from slow rotor speed regulation, which limits wind energy capture efficiency. To address this issue, a novel OTC strategy for wind turbines based on deep deterministic policy gradient(DDPG) and inertial compensation control(ICC) is proposed. Using the DDPG algorithm, the gain coefficient is updated online in real time according to wind speed and rotor speed. To further enhance rotor speed tracking dynamics, an inertial compensation term is introduced based on the ICC principle. To eliminate the dependence of the compensation term on aerodynamic torque sensors or mechanism-based modeling, a broad learning system(BLS) is employed to estimate the aerodynamic torque. Simulations conducted on the OpenFAST demonstrate that the proposed method significantly improves rotor speed tracking dynamics, thereby enhancing wind energy capture efficiency.

关键词(KeyWords)： 最优转矩控制;动态性能提升;深度确定性策略梯度;惯性补偿控制;宽度学习系统
optimal torque control;dynamic performance improvement;deep deterministic policy gradient;inertial compensation control;broad learning system

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金（62203249）;; 山东省自然科学基金（ZR2025MS1100、ZR2021QF115）

作者(Author): 龚礼,张梦瑶,赵鑫鑫,罗浩,张道源,焦绪国
GONG Li,ZHANG Mengyao,ZHAO Xinxin,LUO Hao,ZHANG Daoyuan,JIAO Xuguo

DOI: 10.19585/j.zjdl.202608008

参考文献(References)：

• [1]黄学勤，杨鹏举，赵耀，等.考虑多维气象数据与时间影响的风电功率区间预测[J].浙江电力，2026,45(1):66-77.Huang Xueqin,Yang Pengju,Zhao Yao,et al.Wind power interval forecasting based on multidimensional meteorological data and temporal effects[J]. Zhejiang Electric Power,2026,45(1):66-77.
• [2]郑衍森，苏黄盛，梁业盈，等.风力发电用储能电池技术的发展现状及展望[J].电力电容器与无功补偿，2025,46(4):1-12.Zheng Yansen,Su Huangsheng,Liang Yeying,et al. Development status and prospects of energy storage batteries for wind power generation[J]. Power Capacitor&Reactive Power Compensation,2025,46(4):1-12.
• [3]赵清华，李明，李晓龙，等.构网型与跟网型储能在弱电网中的暂态响应特性及并网性能研究[J].高压电器，2025,61(11):22-33.Zhao Qinghua,Li Ming,Li Xiaolong,et al.Study on transient response characteristics and grid-connection performance of grid-forming and grid-following energy storage in weak grids[J].High Voltage Apparatus,2025,61(11):22-33.
• [4]杨康，谢丽军，熊浩，等.考虑风-储频率响应的智能电网频率特征分析[J].电测与仪表，2024,61(11):165-173.Yang Kang,Xie Lijun,Xiong Hao,et al.Analysis of frequency characteristics of smart grid considering windpower-energy storage frequency response[J].Electrical Measurement&Instrumentation,2024,61(11):165-173.
• [5]张文博，邢海军，聂立君，等.考虑高渗透率可再生能源的新型电力系统可靠性评估综述[J].电测与仪表，2025,62(9):51-61.Zhang Wenbo,Xing Haijun,Nie Lijun,et al.Review of the novel power system reliability assessment with high penetration renewable energy[J]. Electrical Measurement&Instrumentation,2025,62(9):51-61.
• [6]夏冰清，傅栩杰，杨文斌，等.直驱式永磁同步风力发电系统的组合控制策略[J].浙江电力，2024,43(11):57-64.Xia Bingqing,Fu Xujie,Yang Wenbin,et al.An integrated control strategy for D-PMSG wind power generation systems[J].Zhejiang Electric Power,2024,43(11):57-64.
• [7]郭思远，景志滨，李洪波，等.基于单虚拟惯量系数的双馈风机构网控制策略[J].智慧电力，2025,53(5):24-30.Guo Siyuan,Jing Zhibin,Li Hongbo,et al. Grid-forming control strategy for doubly-fed wind turbines based on a single virtual inertia coefficient[J].Smart Power,2025,53(5):24-30.
• [8]郭磊，唐应才.基于励磁电流控制的DESG风电机组MPPT控制[J].电力电子技术，2024,58(4):76-79.Guo Lei,Tang Yingcai.MPPT control of DESG wind turbine based on excitation current control[J]. Power Electronics,2024,58(4):76-79.
• [9]王文文，刘向杰，孔小兵.风力发电控制系统的实时非线性经济模型预测控制[J].系统仿真学报，2025,37(3):679-690.Wang Wenwen,Liu Xiangjie,Kong Xiaobing. Real-time nonlinear economic model predictive control of wind energy conversion system[J].Journal of System Simulation,2025,37(3):679-690.
• [10]Zhou L J,Yin M H,Sun X K,et al.Maximum power point tracking control of wind turbines based on equivalent sinusoidal wind[J].Electric Power Systems Research,2023,223:109534.
• [11]周连俊，李群，殷明慧，等.面向风电机组最大功率点跟踪的转矩曲线增益动态优化[J].电工技术学报，2023,38(13):3447-3458.Zhou Lianjun,Li Qun,Yin Minghui,et al. Torque curve gain dynamic optimization for maximum power point tracking of wind turbines[J].Transactions of China Electrotechnical Society,2023,38(13):3447-3458.
• [12]Johnson K E,Pao L Y,Balas M J,et al. Control of variable-speed wind turbines:standard and adaptive techniques for maximizing energy capture[J]. IEEE Control Systems Magazine,2006,26(3):70-81.
• [13]周连俊，殷明慧，杨炯明，等.考虑变化湍流风速条件的风电机组改进自适应转矩控制[J].电力系统自动化，2021,45(1):184-191.Zhou Lianjun,Yin Minghui,Yang Jiongming,et al. Improved adaptive torque control for wind turbine considering varying turbulence conditions[J].Automation of Electric Power Systems,2021,45(1):184-191.
• [14]张小莲，郝思鹏，翟晶晶，等.限定寻优区间的风力机最大功率点跟踪控制[J].可再生能源，2016,34(3):381-388.Zhang Xiaolian,Hao Sipeng,Zhai Jingjing,et al. An improved maximum power point tracking control for wind power system by specifying optimal searching range[J].Renewable Energy Resources,2016,34(3):381-388.
• [15]Johnson K E,Fingersh L J,Balas M J,et al.Methods for increasing region 2 power capture on a variable-speed wind turbine[J]. Journal of Solar Energy Engineering,2004,126(4):1092-1100.
• [16]Kim K H,Van T L,Lee D C,et al. Maximum output power tracking control in variable-speed wind turbine systems considering rotor inertial power[J]. IEEE Transactions on Industrial Electronics,2013,60(8):3207-3217.
• [17]Kong X B,Wang W W,Liu X J,et al.Offshore wind turbines real-time control using convex nonlinear economic MPC scheme[J].Ocean Engineering,2024,297:116988.
• [18]Mérida J,Aguilar L T,Dávila J.Analysis and synthesis of sliding mode control for large scale variable speed wind turbine for power optimization[J]. Renewable Energy,2014,71:715-728.
• [19]宋煜浩，魏韡，黄少伟，等.风储联合电站实时自调度的高效深度确定性策略梯度算法[J].电工技术学报，2022,37(23):5987-5999.Song Yuhao,Wei Wei,Huang Shaowei,et al. Efficient deep deterministic policy gradient algorithm for real-time self-dispatch of wind-storage power plant[J].Transactions of China Electrotechnical Society,2022,37(23):5987-5999.
• [20]Chen P,Han D Z.Reward adaptive wind power tracking control based on deep deterministic policy gradient[J].Applied Energy,2023,348:121519.
• [21]陈载宇，李阳，殷明慧，等.基于参考输入优化的变速风电机组最大化风能捕获方法[J].控制理论与应用，2022,39(7):1219-1228.Chen Zaiyu,Li Yang,Yin Minghui,et al.Maximizing wind energy extraction for variable-speed wind turbines based on the optimization of reference input[J].Control Theory&Applications,2022,39(7):1219-1228.
• [22]Jiao X G,Yang Q M,Xu B.Hybrid intelligent feedforwardfeedback pitch control for VSWT with predicted wind speed[J]. IEEE Transactions on Energy Conversion,2021,36(4):2770-2781.
• [23]Jiao X G,Zhang D Y,Zhang Z Y,et al.A hybrid deep and broad learning architecture for wind power forecasting based on spatial-temporal feature selection[J]. IEEE Transactions on Instrumentation and Measurement,2025,74:2510416.
• [24]Guo L S,Yin M H,Cai C X,et al. Optimal decreased torque gain control for maximizing wind energy extraction under varying wind speed[J]. Journal of Modern Power Systems and Clean Energy,2023,11(3):853-862.
• [25]Zhang G Z,Hu W H,Cao D,et al.Coordinated active and reactive power dynamic dispatch strategy for wind farms to minimize levelized production cost considering system uncertainty:a soft actor-critic approach[J].Renewable Energy,2023,218:119335.
• [26]Gong X R,Zhang T,Philip Chen C L,et al.Research review for broad learning system:algorithms,theory,and applications[J].IEEE Transactions on Cybernetics,2022,52(9):8922-8950.
• [27]Philip Chen C L,Liu Z L,Feng S.Universal approximation capability of broad learning system and its structural variations[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(4):1191-1204.
• [28]Zhou X,Pang C X,Zeng X H,et al.A short-term power prediction method based on temporal convolutional network in virtual power plant photovoltaic system[J].IEEE Transactions on Instrumentation and Measurement,2023,72:9003810.
• [29]Mazare M,Taghizadeh M. Uncertainty estimator-based dual layer adaptive fault-tolerant control for wind turbines[J].Renewable Energy,2022,188:545-560.
• [30]Jin H Z,Wang M X,Xiang H Y,et al.A PSO-RBF prediction method on flow corrosion of heat exchanger using the industrial operations data[J].Process Safety and Environmental Protection,2024,183:11-23.
• [31]Yin S,Liu H.Wind power prediction based on outlier correction, ensemble reinforcement learning,and residual correction[J].Energy,2022,250:123857.
• [32]Khazaei S,Ehsan M,Soleymani S,et al.A high-accuracy hybrid method for short-term wind power forecasting[J].Energy,2022,238:122020.