针对风电场多分支结构引起的辨识精度和测点数量存在互斥性的问题,提出一种基于双决策思想的风电场集电线路故障辨识方法,用于辨识风电场故障分支及其故障类型。考虑风电场独特的树状多分支结构划分故障集电线路,上层决策用于确定风电场发生故障的集电线路,下层决策进一步实现故障分支辨识和故障分类。上层决策基于能量相似度思想辨识故障集电线路,建立故障决策矩阵,缩小故障范围,无需人工设置阈值。下层决策基于时频响应特征融合辨识风电场故障支路及类型,基于集电线路双端测点各相特征状态矩阵建立故障特征融合矩阵,减少测点需求。该方法仅需风电场少量测点信息,即可实现风电场多分支结构故障辨识,兼顾故障电阻、起始角度、故障位置和噪声的影响。
Abstract
A fault identification method for wind farm collecting lines based on the dual decision idea is proposed to address the issue of trade-off between identification accuracy and the mamberof measurement points caused by the multi branch structure of wind farms. This method is used to identify wind farm fault branches and their types in wind farms. Consider the unique tree like multi branch structure of wind farms for dividing fault collection lines. The upper-level decision is used to determine the collection line where the wind farm fails, while the lower level decision further facilitates fault branch identification and fault classification. The upper level decision-making is based on the concept of energy similarity to identify faulty collector lines, establish a fault decision matrix, narrow down the fault range, and does require manual threshold setting. The lower level decision-making is based on time-frequency response feature fusion to identify the fault branches and types in wind farms. A fault feature fusion matrix is established based on the characteristic state matrix of each phase at the dual end measurement points of the collection line to reduce the need for measurement points. This method only requires a small amount of measurement point data in the wind farm to achieve fault identification of multi branch structures in the wind farm, taking into account the effects of fault resistance, starting angle, fault location, and noise.
关键词
风电场 /
卷积神经网络 /
短路电流 /
故障选线 /
故障分类
Key words
wind farms /
convolutional neural networks /
short circuit current /
fault identification /
fault classification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 薛翼程, 张哲任, 徐政. 适用于短路故障分析的风电场动态等值建模方法[J]. 太阳能学报, 2022, 43(5): 327-335.
XUE Y C, ZHANG Z R, XU Z.Dynamic equivalent model of wind farm for short-circuit faults analysis[J]. Acta energiae solaris sinica, 2022, 43(5): 327-335.
[2] 朱永利, 丁嘉, 潘新朋. 基于零序分量的风电场集电线不对称接地故障定位[J]. 电力系统保护与控制, 2023, 51(3): 56-67.
ZHU Y L, DING J, PAN X P.Zero-sequence component-based fault localization for asymmetric phase-to-ground faults of collecting lines in wind farms[J]. Power system protection and control, 2023, 51(3): 56-67.
[3] 王晓东, 王永浩, 刘颖明, 等. 海上风电场集电多分支线路故障区段定位方法[J]. 太阳能学报, 2023, 44(1): 163-170.
WANG X D, WANG Y H, LIU Y M, et al.Fault branch location for multi-branch collection lines of offshore wind farm[J]. Acta energiae solaris sinica, 2023, 44(1): 163-170.
[4] 邓丰, 梅龙军, 唐欣, 等. 基于时频域行波全景波形的配电网故障选线方法[J]. 电工技术学报, 2021, 36(13): 2861-2870.
DENG F, MEI L J, TANG X, et al.Faulty line selection method of distribution network based on time-frequency traveling wave panoramic waveform[J]. Transactions of China Electrotechnical Society, 2021, 36(13): 2861-2870.
[5] 刘晓琴, 王大志, 江雪晨, 等. 利用行波到达时差关系的配电网故障定位算法[J]. 中国电机工程学报, 2017, 37(14): 4109-4115.
LIU X Q, WANG D Z, JIANG X C, et al.Fault location algorithm for distribution power network based on relationship in time difference of arrival of traveling wave[J]. Proceedings of the CSEE, 2017, 37(14): 4109-4115.
[6] 张科, 孙立志, 朱永利, 等. 基于矢量偏离度的风电场集电线路故障定位方法[J]. 电力系统自动化, 2019, 43(10): 127-133.
ZHANG K, SUN L Z, ZHU Y L, et al.Fault location method of wind farm collection line based on vector deviation degree[J]. Automation of electric power systems, 2019, 43(10): 127-133.
[7] 王宾, 任萱. 中性点经小电阻接地风电场集电线路单相接地故障测距研究[J]. 中国电机工程学报, 2021, 41(6): 2136-2143, 20.
WANG B, REN X.Single-line-to-ground fault location in wind farm collection line with neutral point grounding with resistor[J]. Proceedings of the CSEE, 2021, 41(6): 2136-2143, 20.
[8] 丁嘉, 朱永利. 图学习与零序分量相结合的风电场集电线单相接地故障定位[J]. 电工技术学报, 2023, 38(17): 4701-4714.
DING J, ZHU Y L.A fault localization scheme for single-phase-to-ground faults on collecting lines in wind farms combining graph learning and zero-sequence components[J]. Transactions of China Electrotechnical Society, 2023, 38(17): 4701-4714.
[9] 田鹏飞, 于游, 董明, 等. 基于CNN-SVM的高压输电线路故障识别方法[J]. 电力系统保护与控制, 2022, 50(13): 119-125.
TIAN P, YU Y, DONG M, et al.A CNN-SVM-based fault identification method for high-voltage transmission lines[J]. Power system protection and control, 2022, 50(13): 119-125.
[10] 徐舒玮, 邱才明, 张东霞, 等. 基于深度学习的输电线路故障类型辨识[J]. 中国电机工程学报, 2019, 39(1): 65-74.
XU S W, QIU C M, ZHANG D X, et al.A deep learning approach for fault type identification of transmission line[J]. Proceedings of the CSEE, 2019, 39(1): 65-74.
[11] WANG X D, GAO X, LIU Y M, et al.Stockwell-transform and random-forest based double-terminal fault diagnosis method for offshore wind farm transmission line[J]. IET renewable power generation, 2021, 15(11): 2368-2382.
[12] 彭华, 朱永利. 基于apFFT频谱校正和XGBoost的风电场集电线路单相接地故障测距[J]. 电工技术学报, 2020, 35(23): 4931-4939.
PENG H, ZHU Y L.Single phase grounding fault location for power lines of wind farm based on apFFT spectrum correction and XGBoost algorithm[J]. Transactions of China Electrotechnical Society, 2020, 35(23): 4931-4939.
[13] 李宇, 杨柳林. 基于卷积神经网络的配电网单相接地故障识别[J]. 电气工程学报, 2020, 15(3): 22-30.
LI Y, YANG L L.Identification of single-phase-to-earth fault in distribution network based on convolutional neural network[J]. Journal of electrical engineering, 2020, 15(3): 22-30.
基金
辽宁省揭榜挂帅科技攻关专项（2021JH1/10400009）
PDF(4787 KB)
