摘要
提出了一种小波变换多尺度信息综合的行波波头检测算法,首先利用小波变换的多尺度分析对故障行波信号进行处理,得到各个尺度下的小波系数模极大值,然后将模极大值依次标定在平行坐标系下并形成灰度图片,最后利用卷积神经网络搭建波头检测模型。本算法利用平行坐标系巧妙的将小波变换与CNN相联系,结合了小波变换多尺度下的信息,为行波波头的检测提供了一种新思路。
The key to traveling wave protection and ranging technology lies in the detection of fault wave heads, which is also the focus of research. Wavelet multi-scale information fusion based traveling wave detection algorithm is proposed. Firstly, the wavelet signal is processed by multi-scale analysis of wavelet transform to get the modular maxima at each scale. Then the modular maxima are calibrated in parallel coordinate system and gray scale images are formed. Finally, a wave head detection model is constructed using convolutional neural network. This algorithm uses the parallel coordinate system to intelligently associate the wavelet transform with CNN,which provides a new idea for the detection of traveling wave heads.
引文
[1]何军娜,陈剑云,艾颖梅,等.电力系统行波测距方法及其发展[J].电力系统保护与控制,2014,42(24):148-154.HE Junna,CHEN Jianyun,AI Yingmei,et al. Fault location methods based on traveling wave theory for power system and its development[J]. Power System Protection and Control,2014,42(24):148-154.
[2]李振兴,吴李群,田斌,等.不同步双端数据修正波速的单端行波测距算法研究[J].电力系统保护与控制,2017,45(8):16-22.LI Zhenxing,WU Liqun,TIAN Bin,et al.Single-terminal traveling wave location algorithm based on amending wave velocity[J].Power System Protection and Control,2017,45(8):16-22.
[3]闫红艳,高艳丰,王继选,等.同杆双回线路行波故障测距的关键问题研究[J].电力系统保护与控制,2018,46(4):120-128.YAN Hongyan,GAO Yanfeng,WANG Jixuan,et al. Research on key problems of traveling wave location of doublecircuit lines on the same tower[J].Power System Protection and Control,2018,46(4):120-128.
[4]杜向楠,杨飞,郭宁明,等.基于EMMD局域波分解的网络行波测距方法研究[J].电力系统保护与控制,2018,46(21):181-187.DU Xiangnan,YA NG Fei,GUO Ningming,et al. Researchon network traveling wave fault location based on the decomposition of EMMD[J]. Power System Protection and Control,2018,46(21):181-187.
[5]廖利荣,董臣,俞凯,等.小波变换在超高压输电线路双端故障测距中的应用[J].广东电力,2010,23(11):10-13.LIAO Lirong,DONG Chen,YU Kai,et al. Application of wavelet transform in double-ended fault location of EHV transmission lines[J].Guangdong Electric Power,2010,23(11):10-13.
[6]饶莹,郑建勇,梅军.电力系统故障信号的小波变换奇异性检测[J].电力工程技术,2005,24(4):17-19.RAO Ying,ZHENG Jianyong,MEI Jun.Detection of singularity of wavelet transform in power system fault signal[J].Electric Power Engineering Technology,2005,24(4):17-19.
[7]张广斌,束洪春,于继来.基于Hough变换直线检测的行波波头标定[J].中国电机工程学报,2013, 33(19):165-173.ZHANG Guangbin, SHU Hongchun, YU Jilai. Surge identification for travelling wave based on straight lines detection via Hough transform[J]. Proceedings of the CSEE,2013, 33(19):165-173.
[8]李传健,陈炯聪,黄曙,等.基于卡尔曼滤波的行波波头检测算法研究[J].电网与清洁能源,2016,32(1):53-58.LI Chuanjian, CHEN Jiongcong, HUANG Shu, et al.Research on the wave head detecting algorithm based on kalman filtering[J]. Power System and Clean Energy,2016, 32(1):53-58.
[9]张小丽,曾祥君,马洪江,等.基于Hilbert-Huang变换的电网故障行波定位方法[J].电力系统自动化,2008,32(8):64-68.ZHANG Xiaoli, ZENG Xiangjun, MA Hongjiang, et al.Power grid faults location with traveling wave based on Hilbert-Huang transform[J].Automation of Electric Power Systems,2008, 32(8):64-68.
[10]郑州,吕艳萍,王杰,等.基于小波变换的双端行波测距新方法[J].电网技术,2010,34(01):203-207.ZHENG Zhou,L(U|¨)Yanping,WANG Jie,et al.A new twoterminal traveling wave fault location method based on wavelet transform[J]. Power System Technology,2010,34(01):203-207.
[11]吴仲朗,周书民,汪志成.基于小波变换与模极大值法的高速铁路牵引网故障行波波头自动识别算法[J].科学技术与工程,2012, 12(22):5541-5545.WU Zhonglang, ZHOU Shumin, WANG Zhicheng.Algorithm of high-speed railway traction nets fault traveling wave head automatic recognition based on wavelet transform and modulus maxima[J]. ScienceTechnology and Engineering,2012, 12(22):5541-5545.
[12]马丹丹,王晓茹.基于小波模极大值的单端行波故障测距[J].电力系统保护与控制,2009, 37(3):55-59.MA Dandan, WANG Xiaoru. Single terminal methods of traveling wave fault location based on wavelet modulus maxima[J].Power System Protection and Control,2009, 37(3):55-59.
[13]雷莉.基于小波能量谱的输电线路故障行波定位与保护方法[D].长沙:长沙理工大学,2007.
[14]覃剑,陈祥训,郑健超,等.利用小波变换的双端行波测距新方法[J].中国电机工程学报,2000,20(8):6-10.QIN Jian, CHEN Xiangxun, ZHENG Jianchao, et al.A new double terminal method of travelling wave fault location using wavelet transform[J]. Proceedings of the CSEE,2000, 20(8):6-10.
[15]张宸宇,邓凯,史明明,等.基于小波变换的直流主动配电网电压波动源辨识[J].电力工程技术,2017,36(04):21-24+30.ZHANG Yuyu,DENG Kai,SHI Mingming,et al.Identification of voltage pollution source based on wavelet transform in DC active distributed network[J].Electric Engineering Technology,2017,36(04):21-24+30.
[16]陈伟,何家欢,裴喜平.基于相空间重构和卷积神经网络的电能质量扰动分类[J].电力系统保护与控制,2018,46(14):87-93.CHEN Wei, HE Jiahuan,PEI Xiping. Classification for power quality dis-turbance based on phase-space reconstruction and convolution neural network[J].Power System Protection and Control,2018,46(14):87-93.
[17]董重,魏迎梅.运用平行坐标系的多变元时序数据可视化方法[J].小型微型计算机系统,2015, 36(10):2408-2411.DONG Zhong, WEI Yingmei. Visualization method for multi-variable time series data using parallel coordinates[J].Journal of Chinese Computer Systems, 2015, 36(10):2408-2411.
[18] INSELBERG A. The plane with parallel coordinates[J].Visual Computer, 1985, 1(2):69-91.
[19] INSELBERG A. Parallel coordinates:visual multidimensional geometry and its applications[M]. Springer-Verlag New York,Inc.2009.
[20] INSELBERG A. Parallel Coordinates[M]. Springer New York,2009.