基于广义回归神经网络的特高频局部放电定位法

doi:10.11930/j.issn.1004-9649.202005016

中国电力 ›› 2021, Vol. 54 ›› Issue (2): 11-17.DOI: 10.11930/j.issn.1004-9649.202005016

• 国家“十三五”智能电网重大专项专栏：（五）电力传感技术及应用专栏 • 上一篇下一篇

基于广义回归神经网络的特高频局部放电定位法

郁琦琛, 罗林根, 吴凡, 盛戈皞, 江秀臣

上海交通大学电气工程系，上海 200240

收稿日期:2020-05-06 修回日期:2020-08-27 发布日期:2021-02-06
作者简介:郁琦琛(1995-),女,硕士,从事电力设备在线监测研究,E-mail:artemisyork@sjtu.edu.cn;罗林根(1982-),男,博士,副研究员,从事电力设备状态评估及智能化、复杂电力系统脆弱性评估等研究,E-mail:llg523@sjtu.edu.cn
基金资助:
国家重点研发计划资助项目(2017YFB0902705)

UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network

YU Qichen, LUO Lingen, WU Fan, SHENG Gehao, JIANG Xiuchen

Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2020-05-06 Revised:2020-08-27 Published:2021-02-06
Supported by:
This work is supported by the National Key Research and Development Program of China (No.2017YFB0902705)

摘要/Abstract

摘要： 局部放电的检测和定位是变电站电力设备状态监测和诊断的重要手段。现有的基于时差法的特高频局部放电定位技术，由于高昂的设备成本限制了其应用范围。提出的基于广义回归神经网络和接收信号幅值强度（RSSI）指纹图的局部放电定位法，分为2个阶段。在算法的离线阶段，建立被测区域的RSSI指纹图；在线阶段，利用广义回归神经网络（GRNN）实现对局部放电源的定位。现场测试表明：提出的方法平均定位误差为0.51 m，定位误差小于1 m的累积概率为81.6%。和基于RSSI信号衰减模型定位法的克拉美罗下界（CRLB）最小均方误差相比，均方误差小于0.6 m²的GRNN定位误差累积概率为66.7%，要优于基于信号衰减模型定位方法的CRLB。该方法解决了传统方法定位精度低、成本高的缺点，具有较低的硬件成本和良好的环境适应性。

关键词: 局部放电, RSSI指纹, 广义回归神经网络, 信号衰减模型, 定位技术

Abstract: Partial discharge (PD) detection and localization is an important means for condition monitoring and diagnosis of power equipment. The existing time-difference based ultra-high frequency (UHF) PD localization techniques are limited in application due to their high costs. A novel PD localization method is proposed based on generalized regression neural network (GRNN) and received signal strength indicator (RSSI) fingerprint, which consists of two stages. In the off-line stage of algorithm, a RSSI fingerprint map is built. In the on-line stage, the GRNN is used to calculate the position of the PD source. The field testing shows that the proposed UHF PD localization method has an average localization error of 0.51 m, and a cumulative probability of 81.6% for the localization error of less than 1 m. Compared to the minimum mean square error (MSE) of the Cramér-Rao lower bound (CRLB), which is based on RSSI log normal shadowing model positioning method, the cumulative probability of the GRNN localization error with the mean square error less than 0.6 m² is 66.7%, which is better than CRLB. The proposed method overcomes the shortcomings of low positioning accuracy and high costs of the traditional methods, and has the characteristics of low hardware cost and good environmental adaptability.

Key words: partial discharge, RSSI fingerprint, GRNN, log normal shadowing model, positioning technology

郁琦琛, 罗林根, 吴凡, 盛戈皞, 江秀臣. 基于广义回归神经网络的特高频局部放电定位法[J]. 中国电力, 2021, 54(2): 11-17.

YU Qichen, LUO Lingen, WU Fan, SHENG Gehao, JIANG Xiuchen. UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network[J]. Electric Power, 2021, 54(2): 11-17.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202005016

https://www.electricpower.com.cn/CN/Y2021/V54/I2/11

参考文献

[1] AREFIFAR S A, MOHAMED Y A R I, EL-FOULY T H M. Comprehensive operational planning framework for self-healing control actions in smart distribution grids[J]. IEEE Transactions on Power Systems, 2013, 28(4): 4192-4200.
[2] LI C R, MA G M, QI B, et al. Condition monitoring and diagnosis of high-voltage equipment in China-recent progress[J]. IEEE Electrical Insulation Magazine, 2013, 29(5): 71-78.
[3] 李军浩, 韩旭涛, 刘泽辉, 等. 电气设备局部放电检测技术述评[J]. 高电压技术, 2015, 41(8): 2583-2601
LI Junhao, HAN Xutao, LIU Zehui, et al. Review on partial discharge measurement technology of electrical equipment[J]. High Voltage Engineering, 2015, 41(8): 2583-2601
[4] 侯慧娟, 盛戈皞, 苗培青, 等. 基于超高频电磁波的变电站局部放电空间定位[J]. 高电压技术, 2012, 38(6): 1334-1340
HOU Huijuan, SHENG Gehao, MIAO Peiqing, et al. Partial discharge location based on radio frequency antenna array in substation[J]. High Voltage Engineering, 2012, 38(6): 1334-1340
[5] SINAGA H H, PHUNG B T, AO P L, et al. Partial discharge localization in transformers using UHF sensors[C]//2011 Electrical Insulation Conference (EIC). Annapolis, MD, USA. IEEE, 2011: 64-68.
[6] YIN J H, WAN Q, YANG S W, et al. A simple and accurate TDOA-AOA localization method using two stations[J]. IEEE Signal Processing Letters, 2016, 23(1): 144-148.
[7] 杨森, 熊俊, 郑服利, 等. 基于特高频无线智能传感器的局部放电定位法[J]. 电气自动化, 2017, 39(2): 110-112, 115
YANG Sen, XIONG Jun, ZHENG Fuli, et al. Partial discharge localization based on UHF wireless smart sensors[J]. Electrical Automation, 2017, 39(2): 110-112, 115
[8] 韩宝国, 马驰, 李静鹏, 等. 基于DTCWT与LLE算法的变压器局部放电特高频信号特征参数提取方法[J]. 电力系统保护与控制, 2019, 47(20): 65-72
HAN Baoguo, MA Chi, LI Jingpeng, et al. A feature parameters extraction method of PD UHF signal based on DTCWT and LLE algorithm[J]. Power System Protection and Control, 2019, 47(20): 65-72
[9] 陶为戈, 朱昳华, 贾子彦. 基于RSSI混合滤波和最小二乘参数估计的测距算法[J]. 传感技术学报, 2012, 25(12): 1748-1753
TAO Weige, ZHU Yihua, JIA Ziyan. A distance measurement algorithm based on RSSI hybrid filter and least square estimation[J]. Chinese Journal of Sensors and Actuators, 2012, 25(12): 1748-1753
[10] ASLAM M W, ZHU Z C, NANDI A K. Automatic modulation classification using combination of genetic programming and KNN[J]. IEEE Transactions on Wireless Communications, 2012, 11(8): 2742-2750.
[11] CHEN F C. Back-propagation neural networks for nonlinear self-tuning adaptive control[J]. IEEE Control Systems Magazine, 1990, 10(3): 44-48.
[12] JIN Y Y, SOH W S, WONG W C. Indoor localization with channel impulse response based fingerprint and nonparametric regression[J]. IEEE Transactions on Wireless Communications, 2010, 9(3): 1120-1127.
[13] 陈伟根, 奚红娟, 苏小平, 等. 广义回归神经网络在变压器绕组热点温度预测中的应用[J]. 高电压技术, 2012, 38(1): 16-21
CHEN Weigen, XI Hongjuan, SU Xiaoping, et al. Application of generalized regression neural network to transformer winding hot spot temperature forecasting[J]. High Voltage Engineering, 2012, 38(1): 16-21
[14] NOSE-FILHO K, LOTUFO A D P, MINUSSI C R. Short-term multinodal load forecasting using a modified general regression neural network[J]. IEEE Transactions on Power Delivery, 2011, 26(4): 2862-2869.
[15] 李冬辉, 尹海燕, 郑博文. 基于MFOA-GRNN模型的年电力负荷预测[J]. 电网技术, 2018, 42(2): 585-590
LI Donghui, YIN Haiyan, ZHENG Bowen. An annual load forecasting model based on generalized regression neural network with multi-swarm fruit fly optimization algorithm[J]. Power System Technology, 2018, 42(2): 585-590
[16] CARDOSO G, ROLIM J, ZURN H H. Application of neural network modules to electric power system fault section estimation[J]. IEEE Power Engineering Society General Meeting, 2004, 115(1): 1034-1041.
[17] SPECHT D F. A general regression neural network[J]. IEEE Transactions on Neural Networks, 1991, 2(6): 568-576.
[18] PARZEN E. On estimation of a probability density function and mode[J]. The Annals of Mathematical Statistics, 1962, 33(3): 1065-1076.
[19] TAYLOR J H. The Cramer-Rao estimation error lower bound computation for deterministic nonlinear systems[J]. 1978 IEEE Conference on Decision and Control Including the 17th Symposium on Adaptive Processes, 1978: 1178-1181.
[20] GEZICI S. A survey on wireless position estimation[J]. Wireless Personal Communications, 2008, 44(3): 263-282.

基于广义回归神经网络的特高频局部放电定位法

UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	鞠玲, 黄怿. 基于EFPI的数字配电网超声检测传感器[J]. 中国电力, 2023, 56(6): 194-201.
[2]	冯洋, 周磊, 马全福, 尹松, 王朔. 检测GIS局部放电的小型化多频带复合天线[J]. 中国电力, 2023, 56(4): 167-174.
[3]	黄辉, 杨智豪, 魏建国, 邓辉, 刘诣. 变压器套管局部放电射频信号在外部空间的分布特征[J]. 中国电力, 2023, 56(4): 175-183.
[4]	史强, 刘鹍, 李金嵩, 李福超. 基于t-SNE与CFSFDP算法的多源局部放电脉冲分类技术[J]. 中国电力, 2022, 55(5): 102-110.
[5]	谢荣斌, 杨超, 申强, 李诗勇, 罗勇, 于泊宁. TEV与HFCT法测量开关柜局部放电的特性对比[J]. 中国电力, 2022, 55(3): 37-47.
[6]	张利, 屈斌, 王永宁, 陈荣, 刘宝稳, 张少杰, 韩斌, 马宏忠. GIS壳体振动机理和局部放电优化诊断与应用[J]. 中国电力, 2022, 55(3): 80-86.
[7]	黄雪莜, 熊俊, 张宇, 刘辉, 陈鹭, 孟祥麟, 江秀臣. 基于残差卷积神经网络的开关柜局部放电模式识别[J]. 中国电力, 2021, 54(2): 44-51.
[8]	闫帅, 李朋宇, 王高洁, 李强, 吴凡, 罗林根. 基于特高频无线智能传感阵列的敞开式变电站放电定位方法[J]. 中国电力, 2021, 54(2): 52-57,65.
[9]	李巍巍, 朱轲, 邓元实, 王子康, 黄永禄, 周凯. 温度对电缆附件界面缺陷处局放引发影响机制研究[J]. 中国电力, 2021, 54(11): 181-189.
[10]	张成, 王卫东, 杨延滨, 赵洋, 周弋, 张竟成. 新型电缆多参量带电检测装置设计与应用[J]. 中国电力, 2021, 54(10): 144-151.
[11]	王利, 张伟, 罗定南. 基于随机奇异值分解的局部放电脉冲提取及去噪技术[J]. 中国电力, 2021, 54(10): 196-203.
[12]	刘东超, 林语, 原辉, 王帅, 姜敏, 俞华, 李海涛. 灰度纹理与油气特征融合的油纸绝缘老化状态评估[J]. 中国电力, 2020, 53(12): 159-166,197.
[13]	田宇, 罗沙, 李宾宾, 孙文. 采用Fisher线性判别法提取GIS内部局部放电信号最优能量特征[J]. 中国电力, 2019, 52(9): 93-101.
[14]	栾贻青, 李建祥, 李超英, 黄锐, 吕俊涛. 高压开关柜局部放电检测机器人的开发与应用[J]. 中国电力, 2019, 52(3): 169-176.
[15]	范敏, 叶会生, 段肖力, 黄海波. 真型开关柜模拟缺陷下的局部放电试验研究[J]. 中国电力, 2019, 52(2): 134-138,143.

模态框（Modal）标题

基于广义回归神经网络的特高频局部放电定位法

UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics