摘要
针对风电机组复杂的非线性动态特性阻碍了面向模型预测控制的机组建模,以及现有非线性和局部线性建模方法在模型复杂度和精度方面存在局限性等问题,提出了一种风电机组全局线性建模方法。基于Koopman算子理论和深度学习技术,设计了状态空间映射神经网络;建立了该网络的训练策略,其特点在于包含一个基于Frobenius范数的正则化项,用以提升所得模型的长期预测精度;通过数据驱动的方式训练所提网络,从而建立起风电机组的高维全局线性动态模型。仿真验证结果表明:所提方法下,风轮转速和桨距角的预测误差分别为0.869%和0.026%,远低于3种对比方法;与局部线性动态模型相比,基于所建高维全局线性动态模型的风电场模型预测控制策略使机组风轮转速跟踪误差和越限程度分别降低了92.58%和95.85%。研究结果可为面向模型预测控制的风电机组动态建模提供理论参考。
To address the challenges posed by the complex nonlinear dynamics of wind turbines in model predictive control(MPC)-oriented modeling,as well as the limitations of existing nonlinear and local linear modeling methods in terms of model complexity and accuracy,a global linear modeling method for wind turbines is proposed.Based on Koopman operator theory and deep learning techniques,a state-space mapping neural network is designed.A training strategy incorporating a Frobenius norm-based regularization term is developed to enhance the long-term prediction accuracy of the established model.Through data-driven training of the proposed network,a high-dimensional global linear dynamic model of the wind turbine is established.Simulation results demonstrate that the prediction errors for rotor speed and pitch angle are 0.869%and 0.026%,respectively,which are significantly lower than those of the three comparative methods.Compared with the local linear dynamic model,the wind farm MPC strategy based on the established high-dimensional global linear dynamic model reduces the rotor speed tracking error and overshoot by 92.58%and 95.85%,respectively.The findings provide a theoretical reference for MPC-oriented dynamic modeling of wind turbines.
作者
田润泽
寇鹏
武义琨
张智豪
张远航
王若涛
郝守礼
梁得亮
TIAN Runze;KOU Peng;WU Yikun;ZHANG Zhihao;ZHANG Yuanhang;WANG Ruotao;HAO Shouli;LIANG Deliang(School of Electrical Engineering,Xi’an Jiaotong University,Xi’an 710049,China;Shaanxi Key Laboratory of Smart Grid,Xi’an Jiaotong University,Xi’an 710049,China;State Key Laboratory of Electrical Insulation and Power Equipment,Xi’an Jiaotong University,Xi’an 710049,China;Northern Branch,Beijing Jingneng International Holding Co.,Ltd.,Hohhot 010000,China)
出处
《西安交通大学学报》
北大核心
2026年第2期183-194,共12页
Journal of Xi'an Jiaotong University
基金
国家自然科学基金资助项目(52077165)。
