基于图像形态学特征的GIS局部放电模式识别算法与监测系统

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (0 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract A set of ultra high frequency (UHF) signal pattern recognition algorithm and monitoring system based on image morphological features is proposed to improve the poor adaptability and low accuracy of traditional methods in gas insulated switchgear (GIS) partial discharge recognition and diagnosis, which are limited by sample sources and on-site conditions. Firstly, a particle swarm optimization (PSO) neural network is constructed based on the open-close operation variation rate, edges and corners, and invariant moments of phase resolved partial discharge (PRPD) and phase resolved pulse sequence (PRPS) spectra. Secondly, using laboratory models and real type test platform with pre-embedded defects, partial discharge and noise signals are collected to form sample sets along with third-party normalized image data; Finally, classification training and generalization through homologous, cross, and merged approaches are conducted. The experimental results show that image morphology algorithm can better accommodate samples from different sources, without relying on phase synchronization signal, demonstrating better recognition accuracy and robustness.

Key words： gas insulated switchgear (GIS) partial discharge ultra high frequency (UHF) pattern recognition image morphology

Received: 30 April 2024

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	FANG Zhou
	ZHANG Wei
	LIU Hui
	HUANG Zhong
	CAO Pei

Cite this article:

FANG Zhou,ZHANG Wei,LIU Hui等. Pattern recognition algorithm and monitoring system of GIS partial discharge based on image morphological features[J]. Electrical Engineering, 2024, 25(10): 48-54.

URL:

http://dqjs.cesmedia.cn/EN/Y2024/V25/I10/48

[1] 李星, 许渊, 丁登伟, 等. 温度对GIS绝缘子表面金属异物局部放电及闪络特性的影响[J]. 中国电机工程学报, 2022, 42(1): 406-415.
[2] 何俊达, 廖肇毅, 陈冰心. 一种新型局部放电特高频传感器性能分析[J]. 电气技术, 2024, 25(1): 52-55.
[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.
[4] 李楠, 李松原, 尚学军, 等. 基于交叉比对的UHF- PD在线监测装置现场校验方法[J]. 中国电力, 2022, 55(4): 100-107.
[5] 朱永利, 张翼, 蔡炜豪, 等. 基于辅助分类-边界平衡生成式对抗网络的局部放电数据增强与多源放电识别[J]. 中国电机工程学报, 2021, 41(14): 5044-5053.
[6] 宋思蒙, 钱勇, 王辉, 等. 基于方向梯度直方图属性空间的局部放电模式识别改进算法[J]. 电工技术学报, 2021, 36(10): 2153-2160.
[7] 孙聪, 鞠鹏飞, 李大华, 等. 基于自适应集合经验模态分解算法的局部放电信号降噪研究[J]. 电气技术, 2022, 23(2): 67-72.
[8] KARIMI M, MAJIDI M, MIRSAEEDI H, 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.
[9] 李泽, 王辉, 钱勇, 等. 基于加速鲁棒特征的含噪局部放电模式识别[J]. 电工技术学报, 2022, 37(3): 775-785.
[10] 杨霖, 刘博文, 王松, 等. GIS金属突出物缺陷局部放电发展全过程的严重程度评估[J]. 高压电器, 2020, 56(6): 100-106.
[11] 吴闽, 蒋伟, 罗颖婷, 等. 基于改进SSD的GIS多源局放模式识别[J]. 高电压技术, 2023, 49(2): 812-821.
[12] 何宁辉, 李秀广, 周秀, 等. GIS固体绝缘不同类型气隙缺陷的放电特征[J]. 高电压技术, 2021, 47(6): 2073-2083.
[13] 王艳新, 闫静, 王建华, 等. 基于多级二阶注意力孪生网络的小样本GIS局部放电诊断方法[J]. 电工技术学报, 2023, 38(8): 2255-2264.
[14] 万晓琪, 宋辉, 罗林根, 等. 卷积神经网络在局部放电图像模式识别中的应用[J]. 电网技术, 2019, 43(6): 2219-2226.
[15] 刘财明. 气体绝缘开关设备局部放电带电检测综合应用[J]. 电气技术, 2020, 21(10): 117-122.
[16] 邹阳, 周求宽, 刘明军, 等. 局部放电特高频检测装置抗电磁干扰性能的量化评估方法研究[J]. 电工技术学报, 2020, 35(10): 2275-2282.
[17] LI Xi, WANG Xiaohua, XIE Dingli, et al.Time-frequency analysis of PD-induced UHF signal in GIS and feature extraction using invariant moments[J]. IET Science, Measurement & Technology, 2018, 12(2): 169-175.