基于窥孔结构LSTM的电力系统跳闸故障诊断
作者:
中图分类号:

TP277

基金项目:

国家自然科学基金(61972207);国网河南省电力公司科技计划项目(SGTYHT/17-JS-199)


Power system tripping fault diagnosis based on peephole structure LSTM
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    跳闸是输电和配电电力系统中普遍存在的故障.目前一般采用基于继电保护动作和电气元件动作的保护方法应对跳闸故障.然而,这些面向电气保护的方法在处理跳闸故障时存在滞后性.因此,提前预测跳闸故障对处理隐藏问题和电力恢复起着至关重要的作用.本文提出一种基于多源时序数据的电力系统跳闸故障预测方法,使用窥孔长短时记忆网络(LSTM)提取多源数据的时间特征,缓解了循环神经网络(RNN)在长时间序列上的梯度消失问题.模型在三层栅极上添加窥孔连接结构使得单个单元能够查看上一阶段的LSTM单元状态以此强化网络时序记忆能力;使用参数归一化等L2正则措施缓解故障预测中的过拟合问题对结果的影响;引入支持向量机分类器提高总体模型的泛化能力和鲁棒性.实验结果表明,与现有的数据挖掘方法相比,所提方法具有分类准确性高的优点.最后,对实际应用进行讨论,证明了所提方法在实际场景中的可行性.

    Abstract:

    Tripping is a common fault in power transmission and distribution systems.Protection measures against tripping used to be relaying operation and electrical component action, which have hysteresis in handling tripping faults.Therefore, the prediction of tripping faults plays a vital role in dealing with hidden problems and power recovery.Here, a method of power system tripping fault prediction based on multisource time series data is proposed.LSTM is used to extract the time characteristics of multisource data, which alleviates the problem of RNN gradient disappearance on long time series.A peephole connection structure is added to the three-layer grid to enable single units to check the LSTM unit status in the previous stage, thereby strengthening the network timing memory capability.Then L2 regularization measures such as parameter normalization are used to mitigate the impact of over fitting in fault prediction.Finally, support vector machine classifier is introduced to improve the generalization ability and robustness of the overall model.The experimental data were obtained from relevant institutions of the State Grid of China.Experiment results show that the proposed method has higher classification accuracy compared with existing data mining methods.The practical application is discussed for its feasibility in actual scenarios.

    参考文献
    [1] 赵胜军.智能配电网中的大数据技术应用[J].集成电路应用, 2023, 40(1):291-293 ZHAO Shengjun.Application of big data technology in intelligent distribution network[J].Application of IC, 2023, 40(1):291-293
    [2] Guo L, Li R Z, Jiang B.A data-driven long time-series electrical line trip fault prediction method using an improved stacked-informer network[J].Sensors (Basel, Switzerland), 2021, 21(13):4466
    [3] Sevin M, Audrey O, Andrew S.Probabilistic prediction of trip travel time and its variability using hierarchical Bayesian learning[J].ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A:Civil Engineering, 2023, 9(2):04023011
    [4] Wang Y X, Liu M Q, Bao Z J, et al.Stacked sparse autoencoder with PCA and SVM for data-based line trip fault diagnosis in power systems[J].Neural Computing and Applications, 2019, 31(10):6719-6731
    [5] Tan M Y, Li J M, Chen X Q, et al.Power grid fault diagnosis method using intuitionistic fuzzy Petri nets based on time series matching[J].Complexity, 2019, 2019(4):1-14
    [6] 刘可真, 苟家萁, 骆钊, 等.基于粒子群优化-长短期记忆网络模型的变压器油中溶解气体浓度预测方法[J].电网技术, 2020, 44(7):2778-2784 LIU Kezhen, GOU Jiaqi, LUO Zhao, et al.Prediction of dissolved gas concentration in transformer oil based on PSO-LSTM model[J].Power System Technology, 2020, 44(7):2778-2784
    [7] Zhang J E, Wu D, Boulet B.Time series anomaly detection for smart grids:a survey[C]//2021 IEEE Electrical Power and Energy Conference (EPEC).October 22-31, 2021, Toronto, ON, Canada.IEEE, 2021:125-130
    [8] 郑征, 谭磊, 周楠, 等.基于多头注意力卷积网络的电力负荷预测[J].南京信息工程大学学报(自然科学版), 2022, 14(5):535-542 ZHENG Zheng, TAN Lei, ZHOU Nan, et al.Power load prediction based on multi-headed attentional convolutional network[J].Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 2022, 14(5):535-542
    [9] Ponraj R P, Sigamani T.A novel design and performance improvement of symmetric multilevel inverter with reduced switches using genetic algorithm[J].Soft Computing, 2021, 25(6):4597-4607
    [10] Eissa M M.Challenges and novel solution for wide-area protection due to renewable sources integration into smart grid:an extensive review[J].IET Renewable Power Generation, 2018, 12(16):1843-1853
    [11] Li W L, Monti A, Ponci F.Fault detection and classification in medium voltage DC shipboard power systems with wavelets and artificial neural networks[J].IEEE Transactions on Instrumentation and Measurement, 2014, 63(11):2651-2665
    [12] 李嘉雨, 廖如超, 李钰楷.不平衡数据下基于PSO-BP算法的输电线路弧垂预测[J].南京信息工程大学学报(自然科学版), 2021, 13(5):576-581 LI Jiayu, LIAO Ruchao, LI Yukai.Transmission line sag prediction based on PSO-BP neural network with unbalanced data[J].Journal of Nanjing University of Information Science & Technology (Natural Science Edition), 2021, 13(5):576-581
    [13] 张明阳.有限数据下语音转换的深度学习算法[D].南京:东南大学, 2021 ZHANG Mingyang.Deep learning algorithm for speech conversion under limited data[D].Nanjing:Southeast University, 2021
    [14] 李华旭.基于RNN和Transformer模型的自然语言处理研究综述[J].信息记录材料, 2021, 22(12):7-10 LI Huaxu.A review of natural language processing based on RNN and Transformer models[J].Information Recording Materials, 2021, 22(12):7-10
    [15] 刘凤魁, 邓春宇, 王晓蓉, 等.基于改进快速密度峰值聚类算法的电力大数据异常值检测[J].电力信息与通信技术, 2017, 15(6):36-41 LIU Fengkui, DENG Chunyu, WANG Xiaorong, et al.Outlier detection of smart grid big data based on improved fast search and find density peaks clustering algorithm[J].Electric Power Information and Communication Technology, 2017, 15(6):36-41
    [16] Cui Y Q, Shi J Y, Wang Z L.Power system fault reasoning and diagnosis based on the improved temporal constraint network[J].IEEE Transactions on Power Delivery, 2016, 31(3):946-954
    [17] 徐瑶, 李栓, 韩英华.基于CNN-GS-SVM的用户异常用电行为检测[J].控制工程, 2021, 28(10):1989-1997 XU Yao, LI Shuan, HAN Yinghua.Abnormal behavior detection of electric users based on CNN-GS-SVM[J].Control Engineering of China, 2021, 28(10):1989-1997
    [18] 刘冬兰, 马雷, 刘新, 等.基于深度学习的电力大数据融合与异常检测方法[J].计算机应用与软件, 2018, 35(4):61-64, 136 LIU Donglan, MA Lei, LIU Xin, et al.Deep learning based anomaly detection approach for power big data[J].Computer Applications and Software, 2018, 35(4):61-64, 136
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张平,王鹏展,龚宁,郑征,高晶,张晓东,庄伟.基于窥孔结构LSTM的电力系统跳闸故障诊断[J].南京信息工程大学学报(自然科学版),2023,15(6):712-722
ZHANG Ping, WANG Pengzhan, GONG Ning, ZHENG Zheng, GAO Jing, ZHANG Xiaodong, ZHUANG Wei. Power system tripping fault diagnosis based on peephole structure LSTM[J]. Journal of Nanjing University of Information Science & Technology, 2023,15(6):712-722

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2023-03-02
  • 在线发布日期: 2023-12-15
  • 出版日期: 2023-11-28

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司