基于LSTM神经网络的双馈风机控制参数辨识方法

doi:10.11930/j.issn.1004-9649.202208091

中国电力 ›› 2023, Vol. 56 ›› Issue (6): 31-39.DOI: 10.11930/j.issn.1004-9649.202208091

• 新能源电力系统稳定性分析与控制技术 • 上一篇下一篇

基于LSTM神经网络的双馈风机控制参数辨识方法

薛飞¹, 李宏强¹, 李旭涛¹, 徐恒山²

1. 国网宁夏电力有限公司电力科学研究院，宁夏银川 750001;
2. 三峡大学电气与新能源学院，湖北宜昌 443002

收稿日期:2022-08-25 修回日期:2023-04-27 出版日期:2023-06-28 发布日期:2023-07-04
作者简介:薛飞（1994—），男，硕士，工程师，从事新能源发电与并网、电力电子技术及应用研究，E-mail：tjuxf1010@126.com;徐恒山（1989—），男，通信作者，博士，硕士生导师，从事新能源发电与并网、电力电子技术及应用研究，E-mail：xuhengshan@ctgu.edu.cn
基金资助:
宁夏回族自治区自然科学基金资助项目（2022AAC03612）。

Identification Method for Control Parameters of Doubly-Fed Induction Generator Based on LSTM Neural Network

XUE Fei¹, LI Hongqiang¹, LI Xutao¹, XU Hengshan²

1. Electric Power Research Institute of State Grid Ningxia Electric Power Co., Ltd., Yinchuan 750001, China;
2. College of Electrical Engineering & New Energy, China Three Gorges University, Yichang 443002, China

Received:2022-08-25 Revised:2023-04-27 Online:2023-06-28 Published:2023-07-04
Supported by:
This work is supported by Natural Science Foundation of Ningxia Hui Autonomous Region (No.2022AAC03612).

摘要/Abstract

摘要： 针对暂态工况下难以高精度获取双馈风机（doubly fed induction generator，DFIG）电磁模型控制参数的问题，提出了一种基于长短期记忆（long short-term memory，LSTM）神经网络的DFIG控制参数高精度辨识方法。首先，利用RT-LAB半实物仿真平台测量并获取DFIG控制器硬件在环数据，并在Plecs平台中搭建DFIG模型的辨识模型；然后，采用Person相关系数法提取出高相关性特征并进行神经网络训练；最后，利用提出的LSTM神经网络对DFIG的控制参数进行辨识，并与实测数据进行对比，验证了所提方法的可行性、有效性和实用性。结果表明，相比于传统辨识方法，所提LSTM神经网络参数辨识方法在暂态工况下可有效提高DFIG电磁模型控制参数的辨识精度。

关键词: 双馈风机, 硬件在环, 参数辨识, 长短时记忆网络, Person相关系数法

Abstract: Since it is difficult to obtain highly accurate control parameters of the electromagnetic model of a doubly-fed induction generator (DFIG) under transient conditions, a high precision identification method for the control parameters of DFIG based on long short-term memory (LSTM) neural network was proposed. Firstly, the RT-LAB hardware-in-the-loop (HIL) simulation platform was used to measure and obtain the HIL data of the DFIG controller, and the identification model of DFIG was built in the Plecs platform. Secondly, the Person correlation coefficient method was used to extract highly correlated features and train the neural network. Finally, the proposed LSTM neural network was used to identify the control parameters of DFIG and compare them with the measured data. As a result, the feasibility, effectiveness, and practicability of the proposed method were verified. The results show that compared with the traditional identification methods, the proposed parameter identification method based on LSTM neural network can effectively improve the identification accuracy of the control parameters of the electromagnetic model of DFIGs under transient conditions.

Key words: doubly-fed induction generator, hard-in-the-loop, parameter identification, long short-term memory network, Person correlation coefficient method

薛飞, 李宏强, 李旭涛, 徐恒山. 基于LSTM神经网络的双馈风机控制参数辨识方法[J]. 中国电力, 2023, 56(6): 31-39.

XUE Fei, LI Hongqiang, LI Xutao, XU Hengshan. Identification Method for Control Parameters of Doubly-Fed Induction Generator Based on LSTM Neural Network[J]. Electric Power, 2023, 56(6): 31-39.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202208091

https://www.electricpower.com.cn/CN/Y2023/V56/I6/31

参考文献

[1] 张兴, 孙艳霞, 李丽娜, 等. 风电机组电磁暂态建模及验证[J]. 中国电力, 2020, 53(7): 106–112
ZHANG Xing, SUN Yanxia, LI Lina, et al. Electromagnetic transient modelling and verifying of wind turbine generator[J]. Electric Power, 2020, 53(7): 106–112
[2] 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.
[3] 李振垚, 摆世彬, 方若水, 等. 基于广域测量系统的双馈风力发电机组在线参数辨识方法[J]. 南方电网技术, 2021, 15(5): 89–97
LI Zhenyao, BAI Shibin, FANG Ruoshui, et al. Online parameter identification method of doubly fed induction generator based on wide area measurement system[J]. Southern Power System Technology, 2021, 15(5): 89–97
[4] 陆友文, 崔昊, 陈佳宁, 等. 基于RA-CNN和同步相量的风电场次/超同步振荡参数智能辨识方法[J]. 中国电力, 2023, 56(4): 46–55, 67
LU Youwen, CUI Hao, CHEN Jianing, et al. Intelligent identification method of wind farm sub-synchronous/super-synchronous oscillation parameters based on RA-CNN and synchrophasor[J]. Electric Power, 2023, 56(4): 46–55, 67
[5] 张辉, 蒲天骄, 王刚, 等. 基于实测频率轨迹的机组调速器参数辨识[J]. 电力系统保护与控制, 2014, 42(1): 24–33
ZHANG Hui, PU Tianjiao, WANG Gang, et al. Governor parameter identification of generation system based on measured frequency curve[J]. Power System Protection and Control, 2014, 42(1): 24–33
[6] 乔腾, 张益铭, 曹一家, 等. 基于概率可靠性评估的永磁直驱风机低电压穿越控制模型参数辨识[J]. 中国电力, 2021, 54(12): 102–111
QIAO Teng, ZHANG Yiming, CAO Yijia, et al. Parameter identification of low voltage ride-through control model for permanent magnet direct-drive wind turbine based on probabilistic reliability assessment[J]. Electric Power, 2021, 54(12): 102–111
[7] GAUTAM D, VITTAL V, HARBOUR T. Impact of increased penetration of DFIG-based wind turbine generators on transient and small signal stability of power systems[J]. IEEE Transactions on Power Systems, 2009, 24(3): 1426–1434.
[8] 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 Yangfei, YUAN Yue, CHEN Xiaohu, et al. Analysis on wind turbine parameters identifiability[J]. Automation of Electric Power Systems, 2009, 33(6): 86–89
[9] 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 Xinwei, ZHENG Jinghong, ZHU Shouzhen, 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
[10] 孙黎霞, 林雪, 金宇清, 等. 基于粒子群优化算法的并网光伏发电单元建模[J]. 电网技术, 2015, 39(5): 1213–1218
SUN Lixia, LIN Xue, JIN Yuqing, et al. Modeling of grid-connected photovoltaic generation unit based on particle swarm optimization algorithm[J]. Power System Technology, 2015, 39(5): 1213–1218
[11] 金宇清, 鞠平, 潘学萍, 等. 光伏逆变器控制参数的分步辨识方法[J]. 电网技术, 2015, 39(3): 594–600
JIN Yuqing, JU Ping, PAN Xueping, et al. A stepwise method to identify controller parameters of photovoltaic inverter[J]. Power System Technology, 2015, 39(3): 594–600
[12] 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 Xueping, JU Ping, WEN Rongchao, 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
[13] 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 Raoqi, PENG Xiaotao, QIN Shiyao, et al. Parameter identification of doubly-fed induction generator converter based on M-sequence[J]. Power System Technology, 2022, 46(2): 578–586
[14] 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(增刊1): 59–69
QIN Jishuo, JIA Ke, KONG Fanzhe, 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
[15] 郭建军, 韩钤钰, 董佳琦, 等. 基于SSA-PSO-LSTM模型的羊舍相对湿度预测技术[J]. 农业机械学报, 2022, 53(9): 365–373, 398
GUO Jianjun, HAN Qianyu, DONG Jiaqi, et al. Prediction of sheep house humidity based on SSA PSO LSTM model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(9): 365–373, 398
[16] 付敏, 盖凯凯, 林悦铭. 带滤波电路的双馈风力发电系统网侧控制策略[J]. 控制工程, 2017, 24(2): 396–401
FU Min, GAI Kaikai, LIN Yueming. Research on the control strategy of grid side of doubly-fed wind power system with filter circuit[J]. Control Engineering of China, 2017, 24(2): 396–401
[17] GÜNTHER K, SOURKOUNIS C. Investigation of virtual synchronous machine control for the grid-side converter of wind turbines with permanently excited synchronous generator[C]//IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society. Lisbon, Portugal. IEEE, 2019: 2395–2401.
[18] 李温鹏, 周平. 高炉铁水质量鲁棒正则化随机权神经网络建模[J]. 自动化学报, 2020, 46(4): 721–733
LI Wenpeng, ZHOU Ping. Robust regularized RVFLNs modeling of molten iron quality in blast furnace ironmaking[J]. Acta Automatica Sinica, 2020, 46(4): 721–733
[19] 陈世群, 高伟, 陈孝琪, 等. 一种基于极限学习机和皮尔逊相关系数的光伏阵列故障快速诊断方法[J]. 电气技术, 2021, 22(10): 57–64
CHEN Shiqun, GAO Wei, CHEN Xiaoqi, et al. A fast fault diagnosis method for photovoltaic array via extreme learning machine and Pearson’s correlation coefficient[J]. Electrical Engineering, 2021, 22(10): 57–64
[20] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735–1780.

基于LSTM神经网络的双馈风机控制参数辨识方法

Identification Method for Control Parameters of Doubly-Fed Induction Generator Based on LSTM Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	夏天, 刘代飞, 岳家辉, 陈来恩, 李亦梁. 基于蜣螂算法优化卡尔曼滤波的锂离子电池模型参数辨识[J]. 中国电力, 2025, 58(1): 196-204.
[2]	李丹, 秦世耀, 李少林, 贺敬. 基于混沌粒子群的双馈风电机组LVRT实测建模及暂态参数辨识[J]. 中国电力, 2024, 57(8): 75-84.
[3]	马宏忠, 宣文婧, 朱沐雨, 陈悦林. 基于LWOA-LSTM的大容量锂电池SOC估计[J]. 中国电力, 2024, 57(6): 37-44.
[4]	陆友文, 崔昊, 陈佳宁, 彭祥佳, 冯双, 刘栋. 基于RA-CNN和同步相量的风电场次/超同步振荡参数智能辨识方法[J]. 中国电力, 2023, 56(4): 46-55,67.
[5]	张宏杰, 陈贵凤, 闫宏伟, 杨晓龙, 侯天仁, 张伟. 基于SMOTE与Bayes优化的LSTM网络变压器故障诊断[J]. 中国电力, 2023, 56(10): 164-170.
[6]	吴林林, 程浩, 刘京波, 杜东冶, 龚超, 郭春义. 静止无功发生器对双馈风电场高频振荡的影响[J]. 中国电力, 2022, 55(9): 163-173,182.
[7]	孙素娟, 霍乾涛, 孙立鑫, 过亮, 王瑞, 孔祥梅. 考虑整机转矩控制的双馈风机轴系扭振机理分析及抑制策略[J]. 中国电力, 2022, 55(5): 39-46.
[8]	乔腾, 张益铭, 曹一家, 王力, 袁清. 基于概率可靠性评估的永磁直驱风机低电压穿越控制模型参数辨识[J]. 中国电力, 2021, 54(12): 102-111.
[9]	黄潇潇, 杨韬, 郑骁麟, 郭凌旭, 林济铿. 基于PMU量测信息的短线路同杆并架双回线参数辨识[J]. 中国电力, 2020, 53(7): 141-148.
[10]	张兴, 孙艳霞, 李丽娜, 高彩云, 马俊华, 高丽萍, 刘可可, 何国庆, 李光辉. 风电机组电磁暂态建模及验证[J]. 中国电力, 2020, 53(7): 106-112.
[11]	于国强, 崔晓波, 史毅越, 汤可怡, 张天海. 基于改进群优化算法的深度调峰机组一次调频建模[J]. 中国电力, 2020, 53(6): 147-152.
[12]	张伟骏, 陈文龙, 黄霆, 苏清梅, 林芳, 林济铿. 基于轨迹灵敏度的同步发电机参数辨识[J]. 中国电力, 2019, 52(9): 102-109.
[13]	王旭东, 王高猛, 林济铿, 康宁, 丁一, 刘辉. 基于AMI量测信息的低压配电网线路参数辨识方法[J]. 中国电力, 2019, 52(5): 63-69.
[14]	王刚，梁正玉，李存文，杨涛. 大数据分析在汽轮机调节门特性参数辨识及优化中的应用[J]. 中国电力, 2016, 49(6): 15-19.
[15]	宁剑，王毅，邹德虎，罗玉春. 状态估计智能分析功能设计与应用[J]. 中国电力, 2015, 48(2): 85-89.

模态框（Modal）标题

基于LSTM神经网络的双馈风机控制参数辨识方法

Identification Method for Control Parameters of Doubly-Fed Induction Generator Based on LSTM Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics