您好,欢迎来到login_星欧(官方)代理招商直营娱乐!

首页> 《中国测试》期刊 >本期导读>基于信号图像化和CNN-ResNet的配电网单相接地故障选线方法

基于信号图像化和CNN-ResNet的配电网单相接地故障选线方法

388    2024-06-26

¥0.50

全文售价

作者:缪欣1, 张忠锐1, 郭威2, 侯思祖3

作者单位:1. 东方电子股份有限公司,山东 烟台 264000;
2. 北方工业大学电气与控制工程学院,北京 100144;
3. 华北电力大学电气与电子工程学院,河北 保定 071003


关键词:变分模态分解;卷积神经网络;残差网络;故障选线;排列熵


摘要:

配电网发生单相接地故障时,零序电流呈现较强的非线性与非平稳性,故障选线较为困难,针对此问题,提出一种基于信号图像化和卷积神经网络-残差网络的配电网单相接地故障选线方法。首先,利用排列熵优化变分模态分解算法的参数,将零序电流信号分解成一系列固有模态函数;其次,引入新的数据预处理方式,将固有模态函数转成二维图像,获得零序电流信号的时频特征图;最后,利用一维卷积神经网络提取零序电流信号的相关性和特征,利用残差网络提取时频特征图的特征,将两个网络融合,构建混合卷积神经网络结构,实现故障选线。仿真与实验结果表明,该方法能够在高阻接地、采样时间不同步、强噪声等情况下准确地选择出故障线路,可满足配电网对故障选线准确性和可靠性的需求。


Single-phase ground fault line selection method for distribution network based on signal imaging and CNN-ResNet
MIAO Xin1, ZHANG Zhongrui1, GUO Wei2, HOU Sizu3
1. Dongfang Electronics Co., Ltd., Yantai 264000, China;
2. School of Electrical and Control Engineering, North China University of Technology, Beijing 100144, China;
3. School of Electrical and Electronic Engineering,North China Electric Power University, Baoding 071003, China
Abstract: When a single-phase grounding fault occurs in a distribution network, the zero-sequence current exhibits strong nonlinearity and non-stationarity, making fault line selection difficult. To address this issue, a distribution network single-phase grounding fault line selection method based on signal imaging and CNN-ResNet is proposed. Firstly, the parameters of the variational mode decomposition (VMD) algorithm are optimized using permutation entropy, decomposing the zero-sequence current signal into a series of intrinsic mode functions. Secondly, a new data preprocessing method is introduced, converting the intrinsic mode functions into two-dimensional images to obtain the time-frequency feature map of the zero-sequence current signal. Finally, a one-dimensional convolutional neutral network (CNN) is used to extract the correlation and features of the zero-sequence current signal, while a residual neural network (ResNet) is employed to extract the features of the time-frequency feature map. The two networks are merged to create a hybrid convolutional neural network structure, enabling fault line selection. Simulation and experimental results show that this method can eliminate the influence of manual features, accurately select the fault line under conditions such as high-resistance grounding, asynchronous sampling time, and strong noise, meeting the requirements of accuracy and reliability for fault line selection in distribution networks.
Keywords: variational mode decomposition; convolutional neutral network; residual neural network; fault line selection; permutation entropy
2024, 50(6):157-166 收稿日期: 2023-07-07;收到修改稿日期: 2023-09-15
基金项目: 国家重点研发计划(2018YFF01011900);北方工业大学科研启动基金项目资助(11005136024XN147-30)
作者简介: 缪欣(1972-),男,广东五华县人,硕士,从事配网自动化、调度自动化等方面的研究工作。
参考文献
[1] 余晓, 吕飞鹏, 张国星, 等. 循环神经网络输电线路双端故障测距方法[J]. 中国测试, 2021, 47(9): 119-125.
YU X, LV F P, ZHANG G X, et al. Two-terminal fault location algorithm for transmission lines based on recurrent neural network[J]. China Measurement & Test, 2021, 47(9): 119-125.
[2] 陈博帆, 孙岩洲, 王彬. 基于改进SSA-VMD和多尺度模糊熵的接地故障选线方法[J]. 国外电子测量技术, 2023, 42(1): 28-34.
CHEN B F, SUN Y Z, WANG B. Line selection of grounding fault based on improved SSA-VMD and multi-scale fuzzy entropy[J]. Foreign Electronic Measurement Technology, 2023, 42(1): 28-34.
[3] 侯思祖, 郭威, 王子奇, 等. 基于小波AlexNet网络的配电网故障区段定位方法[J]. 电测与仪表, 2022, 59(3): 46-57.
HOU S Z, GUO W, WANG Z Q, et al. Fault segment location method for distribution network based on wavelet AlexNet network[J]. Electrical Measurement & Instrumentation, 2022, 59(3): 46-57.
[4] WANG D, PSARAS V, EMHEMED A, et al. A novel fault let-through energy based fault location for LVDC distribution networks[J]. IEEE Transactions on Power Delivery, 2021, 36(2): 966-974.
[5] 侯思祖, 郭威. 基于自适应陷波滤波器和混沌振子的配电网故障选线[J]. 电测与仪表, 2020, 57(6): 61-66.
HOU S Z, GUO W. Fault line selection in distribution network based on adaptive notch filter and chaos oscillator[J]. Electrical Measurement & Instrumentation, 2020, 57(6): 61-66.
[6] 刘宝稳, 曾祥君, 张慧芬, 等. 注入电流馈线分布特征及其在接地故障检测中的应用[J]. 电网技术, 2021, 45(7): 2731-2740.
LIU B W, ZENG X J, ZHENG H F, et al. Distribution model of injection current in feeder and its application in single phase to ground fault detection[J]. Power System Technology, 2021, 45(7): 2731-2740.
[7] 张淑清, 翟欣沛, 董璇, 等. EMD及Duffing振子在小电流系统故障选线方法中的应用[J]. 中国电机工程学报, 2013, 33(10): 161-167.
ZHANG S Q, ZHAI X P, DONG X, et al. Application of EMD and duffing oscillator to fault line detection in un-effectively grounded system[J]. Proceedings of the CSEE, 2013, 33(10): 161-167.
[8] 郭亮, 杜欢, 王晓卫, 等. 基于磁场检测与多判据融合的架空线路接地故障定位方法[J]. 电力系统保护与控制, 2022, 50(17): 24-34.
GUO L, DU H, WANG X W, et al. Single phase to ground fault location method of an overhead line based on magnetic field detection and multi-criteria fusion[J]. Power System Protection and Control, 2022, 50(17): 24-34.
[9] 严太山. 基于人类进化算法的配电网故障定位[J]. 仪器仪表学报, 2015, 36(3): 694-700.
YAN T S. Fault location for distribution network based on the human evolutionary algorithm[J]. Chinese Journal of Scientific Instrument, 2015, 36(3): 694-700.
[10] 高杰, 程启明, 程尹曼, 等. 基于量子遗传双稳态系统的配电网故障选线方法[J]. 电力自动化设备, 2018, 38(5): 164-170.
GAO J, CHENG Q M, CHENG Y M, et al. Faulty line selection method based on quantum genetic bistable system for distribution network[J]. Electric Power Automation Equipment, 2018, 38(5): 164-170.
[11] 李霆, 方志坚, 罗义旺, 等. 基于改进蚁群算法的配电网故障定位研究[J]. 微型电脑应用, 2020, 36(9): 86-88.
LI T, FANG Z J, LUO Y W, et al. Research on fault location of distribution network based on improved ant colony algorithm[J]. Microcomputer Applications, 2020, 36(9): 86-88.
[12] 马磊, 黄伟, 李克成, 等. 基于Attention-LSTM的光伏超短期功率预测模型[J]. 电测与仪表, 2021, 58(2): 146-152.
MA L, HUANG W, LI K C, et al. Photovoltaic ultra-short-term power prediction model based on Attention-LSTM[J]. Electrical Measurement & Instrumentation, 2021, 58(2): 146-152.
[13] 王阳, 乐健, 周谦, 等. 基于小波包分析与神经网络的变压器区内外故障判断方法[J]. 电测与仪表, 2020, 57(7): 1-7+15.
WANG Y, LE J, ZHOU Q, et al. Inner and outer zone fault diagnosis method of transformer based on wavelet packet analysis and neural network[J]. Electrical Measurement & Instrumentation, 2020, 57(7): 1-7+15.
[14] 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.
[15] LUO G M, TAN Y J, LI M, et al. Stacked auto-encoder-based fault location in distribution network[J]. IEEE Access, 2020, 8: 28043-28053.
[16] 程文傲, 徐明, 高金峰. 小电流接地系统单相接地故障选线空间域图像生成及融合方法[J]. 电力自动化设备, 2021, 41(7): 97-103.
CHENG W A, XU M, GAO J F. Spatial domain image generation and fusion method of single-phase grounding fault line selection for small current grounding system[J]. Electric Power Automation Equipment, 2021, 41(7): 97-103.
[17] 戴洪德, 陈强强, 戴邵武, 等. 基于样本分位数排列熵的故障诊断方法[J]. 振动与冲击, 2019, 38(23): 152-156.
DAI H D, CHEN Q Q, DAI S W, et al. Fault diagnosis method based on sample quantile permutation entropy[J]. Journal of Vibration and Shock, 2019, 38(23): 152-156.
[18] 刘长良, 武英杰, 甄成刚. 基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J]. 中国电机工程学报, 2015, 35(13): 3358-3365.
LIU C L, WU Y J, ZHEN C G. Rolling bearing fault diagnosis based on variational mode decomposition and fuzzy c means clustering[J]. Proceedings of the CSEE, 2015, 35(13): 3358-3365.
[19] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[20] 郑近德, 程军圣, 杨宇. 改进的EEMD算法及其应用研究[J]. 振动与冲击, 2013, 32(21): 21-26.
ZHENG J D, CHENG J S, YANG Y. Modified EEMD algorithm and its applications[J]. Journal of Vibration and Shock, 2013, 32(21): 21-26.
[21] WEN L, LI X, GAO L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65(7): 5990-5998.
[22] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC: IEEE Computer Society, 2016: 770-778.
[23] 林旭梅, 胡川, 朱广辉, 等. 一种改进ADAM-CNN模型的钢筋混凝土腐蚀检测方法[J]. 中国测试, 2023, 49(2): 8-14.
LIN X M, HU C, ZHU G H, et al. An improved ADAM-CNN model for corrosion detection of reinforced concrete[J]. China Measurement & Test, 2023, 49(2): 8-14.