融合寻优算法的双馈风力机控制参数分步辨识方法

徐恒山; 李颜汝; 李文昊; 薛飞; 王伟

doi:10.19912/j.0254-0096.tynxb.2022-1964

PDF(2926 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (4) : 247-256. DOI: 10.19912/j.0254-0096.tynxb.2022-1964

融合寻优算法的双馈风力机控制参数分步辨识方法

徐恒山¹, 李颜汝¹, 李文昊¹, 薛飞², 王伟³

作者信息 +

STEPWISE IDENTIFICATION METHOD OF CONTROL PARAMETERS FOR DFIG BASED ON COMPOSITE OPTIMIZATION ALGORITHM

Xu Hengshan¹, Li Yanru¹, Li Wenhao¹, Xue Fei², Wang Wei³

Author information +

文章历史 +

摘要

为获得准确的双馈风力机（DFIG）控制参数以提高电力系统机电/电磁仿真分析和计算的准确性,将长短期记忆（LSTM）神经网络与改进粒子群（IPSO）算法相结合对DFIG的控制参数进行辨识。首先,利用RT-LAB平台通过硬件在环（HIL）实验获得真实DFIG控制器的响应数据集;其次,为避免无关特征干扰LSTM模型的预测结果,利用最大信息系数提取出DFIG中高相关性的观测量特征;在此基础上,为提高算法的寻优速度,利用LSTM初步寻优到DFIG控制参数的初始值与搜索范围;最后,通过IPSO算法精确辨识出DFIG的控制参数,提高了辨识算法的寻优效率和精度。HIL测试结果证实了LSTM-IPSO辨识方法在20%~80%低电压穿越工况下具有良好的适应性,并能有效提高DFIG控制参数的辨识精度。

Abstract

To precisely obtain the control parameters of doubly fed induction generator （DFIG） and improve the accuracy of electromechanical/electromagnetic simulation for the power system, a composite optimization algorithm with combining long short-term memory （LSTM） neutral network and improved particle swarm （IPSO） algorithm is used to identify the control parameters of DFIG. Firstly, the response data of real DFIG controller is obtained by hardware-in-loop （HIL） based on RT-LAB platform. Secondly, the observable quantities that have high relevance of DFIG are extracted through maximum information coefficient to avoid the effect of irrelevant features on the predicting results of LSTM model. On the above basis, in order to improve the optimization speed of the algorithm, LSTM is used to preliminary optimize the initial value and search range of DFIG control parameters. Finally, IPSO algorithm is used to precisely identify the control parameters of DFIG, which improves the searching efficiency and accuracy. The HIL testing results verify that LSTM-IPSO identification method has well adaptability and high identification accuracy to the control parameters under the 20%-80% low voltage ride through （LVRT） conditions.

导出引用

徐恒山, 李颜汝, 李文昊, 薛飞, 王伟. 融合寻优算法的双馈风力机控制参数分步辨识方法[J]. 太阳能学报. 2024, 45(4): 247-256 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1964

Xu Hengshan, Li Yanru, Li Wenhao, Xue Fei, Wang Wei. STEPWISE IDENTIFICATION METHOD OF CONTROL PARAMETERS FOR DFIG BASED ON COMPOSITE OPTIMIZATION ALGORITHM[J]. Acta Energiae Solaris Sinica. 2024, 45(4): 247-256 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1964

中图分类号： TK83

参考文献

[1] 刘明宇, 姚芳, 李志刚, 等. 风电机组功率模型参数辨识及风资源利用率评估[J]. 太阳能学报, 2020, 41(12): 305-315.
LIU M Y, YAO F, LI Z G, et al.Power model parameter identification and wind resource utilization evaluation of wind turbine[J]. Acta energiae solaris sinica,2020, 41(12): 305-315.
[2] 王彤, 邢其鹏, 李鸿恩, 等. 计及虚拟惯量控制的DFIG等效惯量在线评估与响应特性分析[J]. 电力系统保护与控制,2022, 50(11): 52-60.
WANG T, XING Q P, LI H E, et al.Online evaluation and response characteristics analysis of equivalent inertia of a doubly-fed induction generator incorporating virtual inertia control[J]. Power system protection and control, 2022, 50(11): 52-60.
[3] 高明阳. 双馈风电机组参数辨识及风电场动态等值方法研究[D]. 北京: 华北电力大学, 2021.
GAO M Y.Research on parameter identification of doubly fed wind turbine and dynamic equivalent method of wind farm[D]. Beijing: North China Electric Power University, 2021.
[4] 张仰飞, 袁越, 陈小虎, 等. 风力机参数的可辨识分析[J]. 电力系统自动化, 2009, 33(6): 86-89.
ZHANG Y F, YUAN Y, CHEN X H, et al.Analysis on Wind Turbine Parameters Identifiability[J]. Automation of electric power systems, 2009, 33(6): 86-89.
[5] 潘学萍, 鞠平, 徐倩, 等. 双馈风力发电机参数分步辨识及观测量的选择[J]. 中国电机工程学报, 2013, 33(13): 116-126.
PAN X P, JU P, Xu Q, et al.A two-step method for estimating DFIG parameters in a wind turbine and the measurement selection[J]. Proceedings of the CSEE, 2013, 33(13): 116-126.
[6] 王红, 梁俊霞, 胡佳琳. 基于ab坐标系模型的双馈风力发电机参数辨识[J]. 电力系统保护与控制, 2014, 42(20): 81-85.
WANG H, LIANG J X, HU J L.Doubly-fed wind power generator parameter identification based on the ab coordinate model[J]. Power system protection and control, 2014, 42(20): 81-85.
[7] 金宇清, 赵泽, 鞠平, 等. 双馈感应风力发电机的参数辨识分析[J]. 高电压技术, 2011, 37(7): 1700-1705.
JIN Y Q, ZHAO Z, JU P, et al.Analysis on the identification of doubly fed induction generator[J]. High voltage engineering, 2011, 37(7): 1700-1705.
[8] 潘学萍, 鞠平, 温荣超, 等. 解耦辨识双馈风电机组转子侧控制器参数的频域方法[J]. 电力系统自动化, 2015, 39(20): 19-25, 108.
PAN X P, JU P, WEN R C, et al.Decoupling estimation of parameters in rotor side controller of DFIG-based wind turbine by frequency domain method[J]. Automation of electric power systems, 2015, 39(20): 19-25, 108.
[9] 许饶琪, 彭晓涛, 秦世耀, 等. 基于M序列的双馈风机变流器参数辨识方法研究[J]. 电网技术, 2022, 46(2): 578-586.
XU R Q, PENG X T, QIN S Y, et al.Parameter identification of doubly-fed induction generator converter based on M-sequence[J]. Power system technology, 2022, 46(2): 578-586.
[10] 秦继朔, 贾科, 孔繁哲, 等. 基于寻优算法的永磁风机并网逆变器故障穿越控制参数分步辨识[J]. 中国电机工程学报, 2021, 41(S1): 59-69.
QIN J S, JIA K, KONG F Z, et al.Stepwise parameter identification of fault ride-through control parameters of PMSG grid-connected inverter based on optimization algorithm[J]. Proceedings of the CSEE, 2021, 41(S1): 59-69.
[11] 郭强, 王鹤, 聂永辉, 等. 考虑恢复暂态过程的直驱发电系统低电压穿越模型参数解耦辨识方法[J]. 高电压技术, 2021, 47(10): 3430-3440.
GUO Q, WANG H, NIE Y H, et al.Decoupling identification method of low-voltage ride-through model parameters of direct drive power generation system considering recovery transient process[J]. High voltage engineering, 2021, 47(10): 3430-3440.
[12] 沈欣炜, 郑竞宏, 朱守真, 等. 光伏并网逆变器控制参数的dq轴解耦辨识策略[J]. 电力系统自动化, 2014, 38(4): 38-43.
SHEN X W, ZHENG J H, ZHU S Z, et al.A dq axis decoupling parameter identification strategy for grid-connected inverter controller of photovoltaic generation system[J]. Automation of electric power systems, 2014, 38(4): 38-43.
[13] 郭强, 孙华东, 高磊, 等. 计及风电场随机特性的SVG模型参数智能辨识方法研究[J]. 中国电机工程学报, 2020, 40(24): 7950-7958, 8232.
GUO Q, SUN H D, GAO L, et al.Intelligent identification of static var generator model with stochastic characters of wind farm[J]. Proceedings of the CSEE, 2020, 40(24): 7950-7958, 8232.
[14] JIN Y Q, LU C J, JU P, et al.Probabilistic preassessment method of parameter identification accuracy with an application to identify the drive train parameters of DFIG[J]. IEEE transactions on power systems, 2020, 35(3): 1769-1782.
[15] 李辉, 吴优, 谢翔杰, 等. 基于改进PSO的双馈风电机组传动链参数辨识[J]. 太阳能学报, 2021, 42(12): 134-142.
LI H, WU Y, XIE X J, et al.Parameter identification of transmission chain for doubly-fed wind turbine based on improved particle swarm optimization[J]. Acta energiae solaris sinica, 2021, 42(12): 134-142.
[16] PUSKÁS M, ANDRÁS DREXLER D. Parameter identification of a tumor model using artificial neural networks[C]//2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI). Herl'any, Slovakia, 2021: 443-448.
[17] 王志浩, 张新燕, 邱衍江, 等. 双馈风电机组低电压穿越工况下变流器IGBT结温升高的抑制策略研究[J]. 太阳能学报, 2020, 41(10): 259-267.
WANG Z H, ZHANG X Y, QIU Y J, et al.Research on suppression strategy of IGBT junction temperature rise for doubly-fed wind turbine converter under low voltage ride through[J]. Acta energiae solaris sinica, 2020, 41(10): 259-267.
[18] GB/T 36995—2018, 风力发电机组故障电压穿越能力测试规程[S].
GB/T 36995—2018, Wind turbines-test procedure of voltage fault ride through capability[S].
[19] NB/T 31066—2015, 风电机组电气仿真模型建模导则[S].
NB/T 31066—2015, Guidelines for modeling electrical simulation models of wind turbines[S].
[20] 张群, 唐振浩, 王恭,等. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G, et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
[21] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[22] 韩思鹏, 蒋晓艳, 罗意, 等. 遮阴条件下光伏MPPT自适应粒子群算法优化[J]. 太阳能学报, 2022, 43(6): 99-105.
HAN S P, JIANG X Y, LUO Y, et al.Photovoltaic mppt adaptive particle swarm optimization optimization under shading conditions[J]. Acta energiae solaris sinica, 2022, 43(6): 99-105.