基于Hammerstein模型的风力发电系统建模与辨识

Modeling and Identification of Wind Power Generation System Based on Hammerstein Model

为建立风力发电系统的高精度模型,研究了一种基于Hammerstein模型的风力发电系统的建模与辨识方法。使用3σ准则对异常数据进行剔除,利用剔除后的数据训练风力发电系统的标称模型。利用Hammerstein模型建立风力发电系统的数据驱动模型,并将可分离信号和实际风速构成的组合式信号作为Hammerstein模型输入,可分离信号经过标称模型的输出和实际功率作为Hammerstein模型输出,基于组合式信号的输入和输出数据,利用相关分析法和带遗忘因子的递推增广随机梯度方法分别辨识Hammerstein模型中静态非线性子系统和动态线性子系统的参数。采用实际风速数据进行仿真实验,提出的方法与增广随机梯度方法的平均绝对百分比误差分别为4.99%和14.73%,与增广随机梯度方法相比,提出方法的平均绝对百分比误差减少了9.74%。仿真结果表明,提出的方法能够有效辨识Hammerstein模型风力发电系统,具有较好的预测性能。

A modeling and identification method of wind power generation system based on Hammerstein model is studied to establish high-precision model of wind power generation system.Firstly,3σ criterion is used to propose the abnormal data,and the eliminated data is used to train the nominal model of the wind power generation system.Furthermore,the Hammerstein model is used to establish the data-driven model of wind power generation system,and the combined signal composed of separable signal and actual wind speed is used as the input of the Hammerstein model.The output of the separable signal through the nominal model and the actual power are used as the output of the Hammerstein model.Based on the input and output data of the combined signal,the parameters of static nonlinear subsystem and dynamic linear subsystem in the Hammerstein model are identified by correlation analysis and recursive extended stochastic gradient method.Simulation experiments with actual wind speed data show that the mean absolute percentage errors of the proposed method and the augmented stochastic gradient method are 4.99% and 14.73%,respectively.Compared with the extended stochastic gradient method,the average absolute percentage error of the proposed method is reduced by 9.74%.The simulation results show that the proposed method can effectively identify the Hammerstein model wind power generation system and has good prediction performance.