基于Hammerstein模型的风力发电系统建模与辨识

doi:10.16182/j.issn1004731x.joss.22-0246

系统仿真学报 ›› 2023, Vol. 35 ›› Issue (7): 1517-1525.doi: 10.16182/j.issn1004731x.joss.22-0246

基于Hammerstein模型的风力发电系统建模与辨识

李峰(), 郑天, 宋伟

江苏理工学院电气信息工程学院，江苏常州 213001

收稿日期:2022-03-22 修回日期:2023-01-31 出版日期:2023-07-29 发布日期:2023-07-19
作者简介:李峰(1987-)，男，副教授，博士，研究方向为数据驱动的复杂非线性动态模型化。E-mail：lifeng@jsut.edu.cn
基金资助:
国家自然科学基金(62003151);常州市科技计划(CJ20220065);江苏高校“青蓝工程”

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

Feng Li(), Tian Zheng, Wei Song

College of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou 213001, China

Received:2022-03-22 Revised:2023-01-31 Online:2023-07-29 Published:2023-07-19

摘要/Abstract

摘要：

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。

关键词: 风力发电系统, Hammerstein模型, 组合式信号, 两阶段辨识

Abstract:

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.

Key words: wind power generation system, Hammerstein model, combined signal, two-stage identification

中图分类号:

TP11

李峰, 郑天, 宋伟. 基于Hammerstein模型的风力发电系统建模与辨识[J]. 系统仿真学报, 2023, 35(7): 1517-1525.

Feng Li, Tian Zheng, Wei Song. Modeling and Identification of Wind Power Generation System Based on Hammerstein Model[J]. Journal of System Simulation, 2023, 35(7): 1517-1525.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

图9

参考文献 22

1	Wiser R, Rand J, Seel J, et al. Expert Elicitation Survey Predicts 37% to 49% Declines in Wind Energy Costs by 2050[J]. Nature Energy, 2021, 6(5): 555-565.
2	Li Jie, Liu Chao, Zhang Pengfei, et al. Difference Between Grid Connections of Large-scale Wind Power and Conventional Synchronous Generation[J]. Global Energy Interconnection, 2020, 3(5): 486-493.
3	Ahmad T, Zhang Hongcai, Yan Biao. A Review on Renewable Energy and Electricity Requirement Forecasting Models for Smart Grid and Buildings[J]. Sustainable Cities and Society, 2020, 55: 102052.
4	杨茂, 许传宇, 王凯旋. 基于切换输出机制的超短期风电功率预测[J]. 高电压技术, 2022, 48(2): 420-429.
	Yang Mao, Xu Chuanyu, Wang Kaixuan. Ultra-short-term Wind Power Forecasting Based on Switching Output Mechanism[J]. High Voltage Engineering, 2022, 48(2): 420-429.
5	Zhang Gang, Liu Hongchi, Zhang Jiangbin, et al. Wind Power Prediction Based on Variational Mode Decomposition Multi-frequency Combinations[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7(2): 281-288.
6	Yuan Xiaohui, Tan Qingxiong, Lei Xiaohui, et al. Wind Power Prediction Using Hybrid Autoregressive Fractionally Integrated Moving Average and Least Square Support Vector Machine[J]. Energy, 2017, 129: 122-137.
7	Jonata C de Albuquerque, Ronaldo R B de Aquino, Otoni Nóbrega Neto, et al. Power Curve Modelling for Wind Turbine Using Artificial Intelligence Tools and Pre-established Inference Criteria[J]. Journal of Modern Power Systems and Clean Energy, 2021, 9(3): 526-533.
8	王子赟, 纪志成. 基于滤波极大似然随机梯度的弃风电量预测[J]. 系统仿真学报, 2017, 29(3): 589-594.
	Wang Ziyun, Ji Zhicheng. Filtering Based Maximum Likelihood Stochastic Gradient Prediction on Wind Power Curtailment[J]. Journal of System Simulation, 2017, 29(3): 589-594.
9	Quachio R, Garcia C. MPC Relevant Identification Method for Hammerstein and Wiener Models[J]. Journal of Process Control, 2019, 80: 78-88.
10	Li Junhong, Zheng Weixing, Gu Juping, et al. A Recursive Identification Algorithm for Wiener Nonlinear Systems With Linear State-space Subsystem[J]. Circuits Systems and Signal Processing, 2018, 37(6): 2374-2393.
11	Ase H, Katayama T. A Subspace-based Identification of Wiener-hammerstein Benchmark Model[J]. Control Engineering Practice, 2015, 44: 126-137.
12	Jalaleddini K, Kearney R E. Subspace Identification of SISO Hammerstein Systems: Application to Stretch Reflex Identification[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(10): 2725-2734.
13	Filipovic V. Recursive Identification of Block-oriented Nonlinear Systems in the Presence of Outliers[J]. Journal of Process Control, 2019, 78: 1-12.
14	李峰, 罗印升, 李博, 等. 基于组合式信号源的Hammerstein-Wiener模型辨识方法[J]. 控制与决策, 2022, 37(11): 2959-2967.
	Li Feng, Luo Yinsheng, Li Bo, et al. Identification Method of the Hammerstein-wiener Model Based on Combined Signal Sources[J]. Control and Decision, 2022, 37(11): 2959-2967.
15	Rahmani M R, Farrokhi M. Identification of Neuro-fractional Hammerstein Systems: A Hybrid Frequency-/time-domain Approach[J]. Soft Computing, 2018, 22(24): 8097-8106.
16	Li Feng, Zhu Xinjian, He Naibao, et al. Parameter Learning for the Nonlinear System Described by Hammerstein Model with Output Disturbance[J]. Asian Journal of Control, 2023, 25(2): 886-898.
17	Li Feng, Jia Li. Correlation Analysis-based Error Compensation Recursive Least-square Identification Method for the Hammerstein Model[J]. Journal of Statistical Computation and Simulation, 2018, 88(1): 56-74.
18	邹同华, 高云鹏, 伊慧娟, 等. 基于Thompson tau-四分位和多点插值的风电功率异常数据处理[J]. 电力系统自动化, 2020, 44(15): 156-162.
	Zou Tonghua, Gao Yunpeng, Yi Huijuan, et al. Processing of Wind Power Abnormal Data Based on Thompson Tau-quartile and Multi-point Interpolation[J]. Automation of Electric Power Systems, 2020, 44(15): 156-162.
19	Shen Xiaojun, Fu Xuejiao, Zhou Chongcheng. A Combined Algorithm for Cleaning Abnormal Data of Wind Turbine Power Curve Based on Change Point Grouping Algorithm and Quartile Algorithm[J]. IEEE Transactions on Sustainable Energy, 2019, 10(1): 46-54.
20	Li Feng, Jia Li, Peng Daogang, et al. Neuro-fuzzy Based Identification Method for Hammerstein Output Error Model with Colored Noise[J]. Neurocomputing, 2017, 244: 90-101.
21	Li Feng, Jia Li, Peng Daogang. Identification Method of Neuro-fuzzy-based Hammerstein Model with Coloured Noise[J]. IET Control Theory & Applications, 2017, 11(17): 3026-3037.
22	Wang Dongqing, Ding Feng. Extended Stochastic Gradient Identification Algorithms for Hammerstein-wiener ARMAX Systems[J]. Computers & Mathematics With Applications, 2008, 56(12): 3157-3164.

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

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 22

相关文章 1

编辑推荐

Metrics

本文评价