Partial Discharge in GIS Diagnosis Method Based on EWT-FE Analysis and Improved SVM Algorithm

doi:10.11985/2024.01.040

Abstract

Abstract:

To improve the accuracy of partial discharge type diagnosis in of gas insulated switchgear(GIS), a method of partial discharge diagnosis in GIS based on EWT-FE and IHPO-SVM algorithm is proposed. To deeply explore the internal features of the partial discharge signal, the empirical wavelet transform(EWT) combined with the fuzzy entropy(FE) algorithm is used to decompose the signal and extract the effective feature quantity. To improve the adaptive capability and classification recognition accuracy of support vector machine(SVM) algorithm, the cosine decay calculation method and the exponential descent function are used to improve the hunter-prey algorithm, resulting in the improved hunter-prey optimizer(IHPO) algorithm, and the parameters of SVM are optimally selected by this method. Finally, an experimental model of GIS partial discharge is constructed, and a partial discharge identification model based on EWT-FE signal analysis combined with IHPO-SVM is established to verify the effectiveness of the proposed algorithm. The experimental results show that the diagnostic accuracy of the proposed algorithm for partial discharge type of GIS is more than 95%, which is better than the traditional diagnostic algorithm.

Key words: Partial discharge, gas insulated switchgear, empirical wavelet transform, fuzzy entropy, improved hunter-prey optimizer, support vector machine

CLC Number:

TM595

WANG Limeng, WANG Shuo. Partial Discharge in GIS Diagnosis Method Based on EWT-FE Analysis and Improved SVM Algorithm[J]. Journal of Electrical Engineering, 2024, 19(1): 371-381.

Figures/Tables 16

References 20

[1]	臧旭, 马宏忠, 吴金利, 等. 基于振动原理的GIS母线导电杆松动故障分析与诊断[J]. 电力系统保护与控制, 2021, 49(9):12-20.
	ZANG Xu, MA Hongzhong, WU Jinli, et al. Analysis and diagnosis of loose conductive bar of GIS bus based on vibration principle[J]. Power System Protection and Control, 2021, 49(9):12-20.
[2]	LI Xi, WANG Zhixiang, WANG Xiaohua, et al. Chromatic processing for feature extraction of PD-induced UHF signals in GIS[J]. Global Energy Interconnection, 2020, 3(5):494-503. doi: 10.1016/j.gloei.2020.11.009
[3]	罗新, 牛海清, 胡日亮, 等. 基于小波包分解的XLPE配电电缆局部放电波形特征提取与识别[J]. 高压电器, 2013, 49(11):110-116,122.
	LUO Xin, NIU Haiqing, HU Riliang, et al. Feature extraction and recognition of partial discharge waveform of XLPE distribution cable based on wavelet packet decomposition[J]. High Voltage Apparatus, 2013, 49(11):110-116,122.
[4]	吕峥, 庄炜, 吴越, 等. 基于改进EMD方法的FBG传感网络光谱基线校正研究[J]. 仪器仪表学报, 2022, 43(1):190-197.
	LÜ Zheng, ZHUANG Wei, WU Yue, et al. Research on spectral baseline correction of FBG sensor network based on improved EMD method[J]. Chinese Journal of Scientific Instrument, 2022, 43(1):190-197.
[5]	李孟威, 史元浩, 杨彦茹, 等. 融合EMD和LSTM的受热面积灰预测研究[J]. 电子测量与仪器学报, 2020, 34(11):166-172.
	LI Mengwei, SHI Yuanhao, YANG Yanru, et al. Prediction of ash accumulation on heating surface by fusion of EMD and LSTM[J]. Journal of Electronic Measurement and Instrument, 2020, 34(11):166-172.
[6]	朱梅梅, 苏建徽, 陈智慧. 基于EEMD和IPSO的SVM短期光伏出力预测[J]. 电气工程学报, 2016, 11(4):47-54.
	ZHU Meimei, SU Jianhui, CHEN Zhihui. SVM short-term photovoltaic output prediction based on EEMD and IPSO[J]. Journal of Electrical Engineering, 2016, 11(4):47-54.
[7]	曲洪权, 吉祥, 盛智勇, 等. 基于局部均值分解的样本熵特征提取研究及应用[J]. 激光与光电子学进展, 2022, 59(7):97-107.
	QU Hongquan, JI Xiang, SHENG Zhiyong, et al. Research and application of sample entropy feature extraction based on local mean decomposition[J]. Laser & Optoelectronics Progress, 2022, 59(7):97-107.
[8]	张欢, 刘燕, 佟宝同, 等. 联合改进CEEMD与近似熵的脑电去噪方法[J]. 计算机工程, 2017, 43(6):53-58. doi: 10.3969/j.issn.1000-3428.2017.06.009
	ZHANG Huan, LIU Yan, TONG Baotong, et al. Electroencephalogram denoising method combining improved CEEMD and approximate entropy[J]. Computer Engineering, 2017, 43(6):53-58. doi: 10.3969/j.issn.1000-3428.2017.06.009
[9]	王卓, 朱宁宁, 郑祥. 基于LDA和RBF神经网络的开关柜局部放电模式识别方法研究[J]. 电子测量技术, 2021, 44(14):148-152.
	WANG Zhuo, ZHU Ningning, ZHENG Xiang. Research on pattern recognition method of partial discharge in switchgear based on LDA and RBF neural network[J]. Electronic Measurement Technology, 2021, 44(14):148-152.
[10]	王东, 朱永利. 基于模糊C均值聚类和改进相关向量机的变压器故障诊断[J]. 电测与仪表, 2019, 56(12):14-19.
	WANG Dong, ZHU Yongli. Transformer fault diagnosis based on fuzzy C-means clustering and improved correlation vector machine[J]. Electrical Measurement & Instrumentation, 2019, 56(12):14-19.
[11]	姚锐, 李俊, 惠萌, 等. 基于集成学习的自适应提升分类模型的局部放电识别研究[J]. 电网技术, 2022, 46(6):2410-2420.
	YAO Rui, LI Jun, HUI Meng, et al. Research on partial discharge recognition based on adaptive lifting classification model based on ensemble learning[J]. Power System Technology, 2022, 46(6):2410-2420.
[12]	陈继明, 许辰航, 李鹏, 等. 基于时频分析与分形理论的GIS局部放电模式识别特征提取方法[J]. 高电压技术, 2021, 47(1): 287-295.
	CHEN Jiming, XU Chenhang, LI Peng, et al. Feature extraction method of partial discharge pattern recognition in GIS based on time-frequency analysis and fractal theory[J]. High Voltage Engineering, 2021, 47(1):287-295.
[13]	刘秀丽, 王鸽, 吴国新, 等. VMD及PSO优化SVM的行星齿轮箱故障诊断[J]. 电子测量与仪器学报, 2022, 36(1):54-61.
	LIU Xiuli, WANG Ge, WU Guoxin, et al. Planetary gearbox fault diagnosis based on VMD and PSO optimization of SVM[J]. Journal of Electronic Measurement and Instrument, 2022, 36(1):54-61.
[14]	尚海昆, 李宇才, 林伟. 基于EWT-MQE的变压器局部放电特征提取[J]. 电力系统保护与控制, 2022, 50(14):161-171.
	SHANG Haikun, LI Yucai, LIN Wei. Feature extraction of partial discharge in transformer based on EWT-MQE[J]. Power System Protection and Control, 2022, 50(14):161-171.
[15]	CHEN Weiting, WANG Zhizhong, XIE Hongbo, et al. Characterization of surface EMG signal based on fuzzy entropy[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(2):266-272. pmid: 17601197
[16]	NARUEI I, KEYNIA F, SABBAGH A. Hunter-prey optimization:Algorithm and applications[J]. Soft Computing, 2022, 26(3):1279-1314. doi: 10.1007/s00500-021-06401-0
[17]	XUE Jiankai, SHEN Bo. A novel swarm intelligence optimization approach:Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1):22-34.
[18]	谢国民, 倪乐水. 基于IABC优化SVM的变压器故障诊断[J]. 电力系统保护与控制, 2020, 48(15):156-163.
	XIE Guomin, NI Leshui. Transformer fault diagnosis based on IABC optimization SVM[J]. Power System Protection and Control, 2020, 48(15):156-163.
[19]	周凯, 曹林, 胡志坚, 等. 基于决策树和支持向量机的智能变电站二次系统防误方法[J]. 电气工程学报, 2023, 18(1):118-125.
	ZHOU Kai, CAO Lin, HU Zhijian, et al. Error prevention method for secondary system of intelligent substation based on decision tree and support vector machine[J]. Journal of Electrical Engineering, 2023, 18(1):118-125.
[20]	胡聪, 徐敏, 洪德华, 等. 基于改进K-medoids聚类和SVM的异常用电模式在线检测方法[J]. 国外电子测量技术, 2022, 41(2):53-59.
	HU Cong, XU Min, HONG Dehua, et al. Online detection method of abnormal electricity consumption pattern based on improved K-medoids clustering and SVM[J]. Foreign Electronic Measurement Technology,2022, 41(2):53-59.

函数	算法	均值	均方差
f₁	IHPO	0	0
	HPO	1.436×10^-97	5.866×10^-98
	PSO	3.657×10^-61	9.352×10^-62
f₂	IHPO	0	0
f₂	HPO	0	0
	PSO	0	0

参数	数值和类型
额定电压/kV	160
额定频率/Hz	50
耦合电容量/pF	50
特高频局放检测参数	带宽300~2 000 MHz；灵敏度：1 pC
检波信号接收频率带宽/MHz	0~25
装置自身放电量/pC	≤0.5
变压器变比	1 000：1
绝缘介质	SF₆气体
气体压力/MPa	≤0.35

局放类型	FE1	FE2	FE3
尖端放电	0.044 7	0.024 9	0.015 5
	0.045 7	0.025 3	0.015 2
	0.044 3	0.025 3	0.015 2
气隙放电	0.010 0	0.010 6	0.010 3
	0.009 2	0.010 5	0.010 4
	0.009 4	0.010 5	0.010 4
悬浮放电	0.009 9	0.004 3	0.000 6
	0.009 9	0.004 3	0.000 5
	0.010 0	0.004 4	0.000 4
金属颗粒放电	0.021 1	0.003 1	0.000 9
	0.021 4	0.003 7	0.001 1
	0.020 7	0.003 3	0.001 0

诊断方法	识别率(%)				总识别率(%)
诊断方法	尖端放电	气隙放电	悬浮放电	颗粒放电	总识别率(%)
EWT-FE-IHPO-SVM	100	100	96.67	96.67	98.33
EWT-FE-HPO-SVM	96.67	100	90	86.67	93.33
EWT-FE-PSO-SVM	93.33	93.33	86.67	90.00	91.67
EWT-EM-IHPO-SVM	93.33	96.67	86.67	86.67	90.83
EEMD-FE-IHPO-SVM	93.33	93.33	83.33	83.33	89.17
EMD-FE-IHPO-SVM	100	70	90	86.67	86.67
EWT-AE-IHPO-SVM	96.67	50	90	83.33	80

放电类型	诊断准确率(%)
尖端放电	99.03
气隙放电	97.09
悬浮放电	98.06
金属颗粒放电	96.12