GIS Equipment Fault Identification Based on BP Neural Network and Improved DS Evidence Fusion

doi:10.11985/2023.04.038

Abstract

Abstract:

Accurately identifying internal insulation defects in gas insulated switchgear(GIS) helps assess the hazards of partial discharge(PD) and provides essential guidance for equipment maintenance. However, the traditional single monitoring method has the disadvantages of incomplete information utilization, high feature dimensionality and low recognition rate. To overcome these problems, a partial discharge experimental platform is first built on a 220 kV GIS, and four typical defect models, such as insulator fouling, insulator air gap, floating electrode and metal protrusions, are set up. The partial discharge signals of various defects are collected by pulse current method and UHF method. The fusion decision of PD signal based on time resolved partial discharge and phase resolved partial discharge is introduced into the proposed diagnosis method of BP neural network and improved DS evidence theory. By introducing the degree of evidence fusion, the proposed diagnosis algorithm is used for fault identification. The results show that the proposed recognition method can deeply mine effective information and has ability to reject false diagnosis, so that the final overall recognition rate is higher than 96.7%, which is significantly high than the traditional BP neural network.

Key words: Gas insulated switchgear, partial discharge, BP neural network, improved DS evidence theory, fault diagnosis

CLC Number:

TM561

YU Cong, TANG Kaibo, LI Zhe, LIU Zhipeng, CHEN Bo, LIU Yuanchao, FANG Yaqi. GIS Equipment Fault Identification Based on BP Neural Network and Improved DS Evidence Fusion[J]. Journal of Electrical Engineering, 2023, 18(4): 361-369.

Figures/Tables 12

References 24

[1]	LI Shengchun. Location and analysis of abnormal partial discharge of 750 kV GIS equipment[C]// 2021 13th International Conference on Measuring Technology and Mechatronics Automation(ICMTMA),Beihai,China, 2021:83-85.
[2]	REN Ming, ZHOU Jierui, MIAO Jin. Adopting spectral analysis in partial discharge fault diagnosis of GIS with a micro built-in optical sensor[J]. IEEE Transactions on Power Delivery, 2021, 36(2):1237-1240. doi: 10.1109/TPWRD.2020.3028511
[3]	SALAMA M M A, BARTNIKAS R. Fuzzy logic applied to PD pattern classification[J]. IEEE Transactions on Electrical Insulation, 2000, 7(1):118-123.
[4]	刘宝稳, 汤容川, 马钲洲, 等. 基于S变换D-SVM AlexNet模型的GIS机械故障诊断与试验分析[J]. 高电压技术, 2021, 47(7):2526-2538.
	LIU Baowen, TANG Rongchuan, MA Zhengzhou, et al. GIS mechanical fault diagnosis and test analysis based on S transform D-SVM AlexNet model[J]. High Voltage Engineering, 2021, 47(7):2526-2538.
[5]	吴旭涛, 马云龙, 何宁辉, 等. 基于多源数据融合的GIS机械故障检测技术[J]. 高压电器, 2022, 58(11):191-196,204.
	WU Xutao, MA Yunlong, HE Ninghui, et al. Mechanical fault detection technology of GIS based on multi-source data fusion[J]. High Voltage Engineering, 2022, 58(11):191-196,204.
[6]	王克胜, 赵彦平, 原帅, 等. 基于电场计算及模态分析的220 kV GIS盆式绝缘子裂纹缺陷检测方法研究[J]. 电网与清洁能源, 2021, 37(8):32-38.
	WANG Kesheng, ZHAO Yanping, YUAN Shuai, et al. Thecrack defect detection method of 220 kV GIS basin-type insulators based on electric field calculation and modalanalysis[J]. Power System and Clean Energy, 2021, 37(8):32-38.
[7]	AMBIKAIRAJAH R, PHUNG B T, RAVISHANKAR J, et al. Spectral features for the classification of partial discharge signals from selected insulation defect models[J]. IET Science Measurement Technology, 2013, 7(2):104-111. doi: 10.1049/smt2.v7.2
[8]	张波. 基于超声波法的GIS局部放电模式识别的研究[D]. 北京: 华北电力大学, 2015.
	ZHANG Bo. Research on partial discharge pattern recogoniton of GIS based on ultrasonic detection[D]. Beijing: North China Electric Power University, 2015.
[9]	GULSKI E, KREUGER F H. Computer-aided recognition of discharge sources[J]. IEEE Transactions on Electrical Insulation, 1992, 27(1):82-92. doi: 10.1109/14.123443
[10]	WANG Yanxin, YAN Jing, YANG Zhou, et al. Gas-insulated switchgear insulation defect diagnosis via a novel domain adaptive graph convolutional network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-10.
[11]	KOO J Y, JUNG S Y, RYU C H, et al. Identification of insulation defects in gas-insulated switchgear by chaotic analysis of partial discharge[J]. IET Science Measurement Technology, 2010, 4(3):115-124. doi: 10.1049/iet-smt.2009.0028
[12]	史志侠. 局放测量新标准IEC60270的特点及其对局放测量工作的影响[J]. 高压电器, 2001, 3:29-32.
	SHI Zhixia. Feature of new standard IEC 60270 for partial discharge measurement and its influence on pd measuring activity[J]. High Voltage Apparatus, 2001, 3:29-32.
[13]	袁文海, 刘彪, 徐浩, 等. 基于复合神经网络的GIS局放故障类型识别[J]. 电力科学与技术学报, 2021, 36(4):157-164.
	YUAN Wenhai, LIU Biao, XU Hao, et al. Partial discharge fault type identification of GIS based on composite neural network[J]. Journal of Electric Power Science and Technology, 2021, 36(4):157-164.
[14]	宋辉, 苑龙祥, 郭双权. 基于数据增强和特征注意力机制的灰狼优化算法-优化残差神经网络变压器故障诊断方法[J/OL]. 现代电力:1-9[2023-03-07]. DOI:10.19725/j.cnki.1007-2322.2022.0163.
	SONG Hui, YUAN Longxiang, GUO Shuangquan. GWO-resnet power transformer fault diagnosis method based on data augmentation and feature attention mechanism[J]. Modern Electric Power:1-9[2023-03-07]. DOI:10.19725/j.cnki.1007-2322.2022.0163.
[15]	XU Guangke, LI Xing, CHEN Lingying, et al. Study on filtering and eigenvalue extraction of partial discharge signal of GIS[C]// 2020 Asia Energy and Electrical Engineering Symposium(AEEES),Chengdu,China, 2020:1014-1017.
[16]	王艳新, 闫静, 王建华, 等. 基于域对抗迁移卷积神经网络的小样本GIS绝缘缺陷智能诊断方法[J]. 电工技术学报, 2022, 37(9):2150-2160.
	WANG Yanxin, YAN Jing, WANG Jianhua, et al. Intelligent diagnosis for GIS with small samples using a novel adversarial transfer learning in convolutional neural network[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2150-2160.
[17]	张新伯, 唐炬, 潘成, 等. 用于局部放电模式识别的深度置信网络方法[J]. 电网技术, 2016, 40(10):3272-3278.
	ZHANG Xinbo, TANG Ju, PAN Cheng, et al. Research of partial discharge recognition based on deep belief nets[J]. Power System Technology, 2016, 40(10):3272-3278.
[18]	石宜金, 谭贵生, 赵波, 等. 基于模糊综合评估模型与信息融合的电力变压器状态评估方法[J]. 电力系统保护与控制, 2022, 50(21):167-176.
	SHI Yijin, TAN Guisheng, ZHAO Bo, et al. Condition assessment method for power transformers based on fuzzy comprehensive evaluation and information fusion[J]. Power System Protection and Control, 2022, 50(21):167-176.
[19]	耿伊雯, 芮逸凡, 范路, 等. 基于D-S证据多源信息融合与固态光电倍增-UHF联合检测的GIS局部放电模式识别[J]. 绝缘材料, 2022, 55(11):109-117.
	GENG Yiwen, RUI Yifan, FAN Lu, et al. GIS partial discharge pattern recognition based on D-S evidence multi-source information fusion and solid state photomultiplier-UHF combined detection[J]. Insulating Materials, 2022, 55(11):109-117.
[20]	MASOUD K, MEHRDAD M, HAMED M, et al. A novel application of deep belief networks in learning partial discharge patterns for classifying corona surface and internal discharges[J]. IEEE Transactions on Industrial Electronics, 2020, 67(4):3277-3287. doi: 10.1109/TIE.41
[21]	LIAO Ruijin, ZHENG Hanbo, GRZYBOWSKI S, et al. An integrated decision-making model for condition assessment of power transformers using fuzzy approach and evidential reasoning[J]. IEEE Transactions on Power Delivery, 2011, 26(2):1111-1118. doi: 10.1109/TPWRD.2010.2096482
[22]	关昕, 郭俊萍, 王星. 基于改进DS理论的双重模糊信息安全评估[J]. 计算机工程与应用, 2017, 53(2):112-117. doi: 10.3778/j.issn.1002-8331.1504-0043
	GUAN Xin, GUO Junping, WANG Xing. Double fuzzy information security evaluation algorithm based on improved DS theory[J]. Computer Engineering and Applications, 2017, 53(2):112-117. doi: 10.3778/j.issn.1002-8331.1504-0043
[23]	高天昊, 曲卫, 董尧尧, 等. 基于改进D-S证据理论的MPAR行为状态识别方法[J]. 电光与控制, 2022, 29(12):1-6.
	GAO Tianhao, QU Wei, DONG Yaoyao, et al. An MPAR behavioral state identification method based on modified D-S evidence theory[J]. Electronics Optics & Control, 2022, 29(12):1-6.
[24]	LIU Yuwei, CHEN Yuqiang, ZHANG Zhenzhen, et al. Multi-information fusion fault diagnosis based on knn and improved evidence theory[J]. Journal of Vibration Engineering & Technologies, 2021, 10(3):841-852.

缺陷	外施电压等级/kV
金属表面污秽缺陷	15.1→17.3→19.2→21.4→23.1→25.6
绝缘子气隙缺陷	9.4→11.6→13.7→15.6→18.0→20.2
悬浮电极缺陷	17.2→19.4→21.5→23.9→25.5→27.8
金属突出物缺陷	8.6→10.1→12.8→14.2→16.1→17.5

缺陷类型	训练集	测试集	识别率(%)
污秽	30	60	82.6
气隙	30	60	90.5
悬浮电极	30	60	79.2
突出物	30	60	80.7
总计	120	240	83.25

缺陷类型	训练集	测试集	识别率(%)
污秽	30	60	83.6
气隙	30	60	91.2
悬浮电极	30	60	78.2
突出物	30	60	80.7
总计	120	240	83.42

缺陷类型	训练集	测试集	识别率(%)
污秽	30	60	92.6
气隙	30	60	86.5
悬浮电极	30	60	84.2
突出物	30	60	87.7
总计	120	240	87.8

缺陷类型	正确/错误/未判断	识别率(%)
污秽	58/2/1	96.7
气隙	59/0/1	98.3
悬浮电极	57/2/1	95.6
突出物	57/3/0	96.2
总计	231/7/3	96.7