1.School of Electric power, Shenyang Institute of Engineering, Shenyang 110136, China
2.School of Renewable Energy, Shenyang Institute of Engineering, Shenyang 110136, China
3.School of Energy and Power, Shenyang Institute of Engineering, Shenyang 110136, China
4.Liaoning Branch, Huaneng New Energy Company Limited, Shenyang 110002, China
Show less
文章历史+
Received
Accepted
Published
2024-10-17
2024-11-23
Issue Date
2025-10-30
PDF (1053K)
摘要
基于风电场复杂运行环境和多分支混合集电线路的单相接地故障定位需求,提出一种基于卷积神经网络(convolutional neural network,CNN)和长短期记忆网络(long short term memory networks,LSTM)混合模型(CNN-LSTM)的单相接地故障定位策略。采集故障时零序电流,构建风电场单相接地故障数据集,将CNN-LSTM混合模型改进为适合故障测距的预测模型,将该模型应用于在线故障定位。研究结果表明:与CNN和反向传播神经网络(backpropagation neural network,BP)相比,CNN-LSTM混合模型方法定位准确率更高,在不同故障距离和故障电阻情况下均可使用。研究结论为风电场集电线路接地故障定位提供参考。
Abstract
Based on the complex operating environment of wind farms and the single-phase grounding fault location requirements of multi-branch hybrid collector lines, a single-phase grounding fault location strategy based on convolutional neural network (CNN) and long short term memory networks (LSTM) hybrid model (CNN-LSTM) is proposed. The zero-sequence current is collected when the fault occurs, and the single-phase grounding fault data set of the wind farm is constructed. The CNN-LSTM hybrid model is improved into a prediction model suitable for fault location, and the model is applied to online fault location. The results show that compared with CNN and backpropagation neural network (BP), the CNN-LSTM hybrid model method has higher positioning accuracy and can be used in different fault distances and fault resistances. The research conclusions provide a reference for the grounding fault location of wind farm collector lines.
PENGHua, ZHUYongli.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.
WANGBin, RENXuan.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):2136-2144.
ZHAIYujia, ZHANGKai, ZHUYongli,et al.Single-line-to-ground fault location method for wind farm collection line based on segmented impedance matching [J].Smart Power,2020, 48(12):26-32.
PENGHua, WANGWenchao, ZHUYongli,et al.An intelligent single-phase grounding fault location for a wind farm collection line based on an LSTM neural network[J].Power System Protection and Control,2021,49(16):60-66.
DENGFeng, SHIHongfei, FENGSixu,et al.Single-ended traveling wave location method for distribution network based on CNN-LSTM panoramic fault feature mining[J].Proceedings of the CSEE,2019,43():114-126.
[15]
GUOM F, GAOJ H, SHAOX,et al.Location of single-line-to-ground fault using 1-D convolutional neural network and waveform concatenation in resonant grounding distribution systems[J].IEEE Transactions on Instrumentation and Measurement,2020,70:3501009.
CHENSheng, LIUPengfei, WANGPing,et al.Load forecasting method of power system based on LSTM artificial neural network[J].Journal of Shenyang University of Technology,2024,46(1):66-71.
[18]
XINS Q, LIY L, LIT,et al.Single phase ground fault locating method of multi-branch wind farm collector lines[C]//2021 IEEE 2nd China International Youth Conference on Electrical Engineering. December 15-17,2021.Chengdu, China. IEEE,2021:1-5.
[19]
SUX X, WEIH.A fault-line selection method for small-current grounded system based on deep transfer learning[J].Energies,2022,15(9):3467.
[20]
TEIMOURZADEHH, MORADZADEHA, SHOARANM,et al.High impedance single-phase faults diagnosis in transmission lines via deep reinforcement learning of transfer functions[J].IEEE Access,2021,9:15796-15809.
ZHENGYanyan, ZHUYongli, LIUTongtong,et al.Single-phase grounding fault location in wind farm based on zero-sequence current[J].Journal of System Simulation,2019,31(7):1408-1415.
CUANWanbing, XuebinLYU.Carbon emissions trading price prediction based on ARIMA-SSA-LSTM combination model[J].Journal of Xi΄an University of Science and Technology,2023,43(5):1025-1034.