基于加速鲁棒特征的含噪局部放电模式识别

doi:10.19595/j.cnki.1000-6753.tces.210018

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (6360 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要由于变电站现场环境复杂多样,实测的局部放电（PD）数据存在大量的干扰信号。为提高含噪PD类型识别准确度,提出一种基于加速鲁棒特征（SURF）和改进支持向量机（BFO-SVM）的PD模式识别方法。首先,将单源PD数据与噪声及干扰数据叠加形成染噪PD数据,并构造脉冲序列分布（PRPS）模式;然后,利用SURF算法自动提取PRPS灰度图像的特征点及特征描述符,结合词袋模型思想和K-means聚类方法生成不同PD类型的视觉单词频率特征;最后,将提取的特征量输入BFO-SVM分类器,并将该算法与基于灰度梯度共生矩阵（GLCM）的特征提取方法和传统SVM优化算法的识别效果进行对比。结果表明：该算法在高幅值白噪声背景及典型干扰环境中具有较高的识别准确率及较强的抗干扰能力。研究结果可为现场PD检测和识别提供参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李泽
	王辉
	钱勇
	黄锐
	崔其会

关键词 ：局部放电, 特征提取, 加速鲁棒特征, 细菌觅食优化算法, 支持向量机

Abstract：Due to the complex environmental impacts, the patrial discharge (PD) data obtained at substation always contain lots of noisy signals. To improve the accuracy of PD recognition, a PD pattern recognition method based on speeded up robust features (SURF) and improved support vector machine (BFO-SVM) is proposed. Contaminated PD data were made by fusing the pure PD data with noise and the phase resolved pulse sequence (PRPS) patterns were constructed. Then the SURF algorithm was used to extract the feature points and feature descriptors of the PRPS grayscale images automatically. After that, visual word frequency features of different PD types were generated by using bag-of-words and K-means clustering method. The features were input into the BFO-SVM classifier, and the recognition results were contrasted with those acquired from the gray gradient co-occurrence matric (GLCM) and the traditional SVM optimization algorithm. Results show that the algorithm has high recognition accuracy and strong anti-interference ability under high-amplitude white noise background and typical interference environment. The finding results can be used as reference for PD detection and identification on the spot.

Key words： Partial discharge feature extraction speeded up robust features(SURF) bacterial foraging optimization algorithm support vector machine

收稿日期: 2021-01-07

PACS:

TM85

基金资助:国家自然科学基金资助项目（62075045）

通讯作者: 王辉男,1982年生,博士,研究方向电力设备绝缘状态诊断与在线监测技术。E-mail：wanghui8203@sjtu.edu.cn

作者简介: 李泽女,1997年生,博士研究生,研究方向电力设备局部放电状态监测与智能化。E-mail：lize123@sjtu.edu.cn

引用本文:

李泽, 王辉, 钱勇, 黄锐, 崔其会. 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. Li Ze, Wang Hui, Qian Yong, Huang Rui, Cui Qihui. Pattern Recognition of Partial Discharge in the Presence of Noise Based on Speeded up Robust Features. Transactions of China Electrotechnical Society, 2022, 37(3): 775-785.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.210018 https://dgjsxb.ces-transaction.com/CN/Y2022/V37/I3/775

[1] 张连根, 路士杰, 李成榕, 等. GIS中线形和球形金属微粒的运动行为和危害性[J]. 电工技术学报, 2019, 34(20): 4217-4225.
Zhang Liangen, Lu Shijie, Li Chengrong, et al.Motor behavior and hazard of spherical and liner particle in gas insulated switchgear[J]. Transactions of China Electrotechnical Society, 2019, 34(20): 4217-4225.
[2] 唐志国, 唐铭泽, 李金忠, 等. 电气设备局部放电模式识别研究综述[J]. 高电压技术, 2017, 43(7): 2263-2277.
Tang Zhiguo, Tang Mingze, Li Jinzhong, et al.Review on partial discharge pattern recognition of electrical equipment[J]. High Voltage Engineering, 2017, 43(7): 2263-2277.
[3] 朱煜峰, 许永鹏, 陈孝信, 等. 基于卷积神经网络的直流XLPE电缆局部放电模式识别技术[J]. 电工技术学报, 2020, 35(3): 659-668.
Zhu Yufeng, Xu Yongpeng, Chen Xiaoxin, et al.Pattern recognition of partial discharges in DC XLPE cables based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(3): 659-668.
[4] Rudd S, McArthur S D, Judd M D. A generic knowledge-based approach to the analysis of partial discharge data[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2010, 17(1): 149-156.
[5] 臧奕茗, 王辉, 钱勇, 等. 基于三维光学指纹和NPSO-KELM的GIL局部放电定位方法[J]. 中国电机工程学报, 2020, 40(20): 6754-6764.
Zang Yiming, Wang Hui, Qian Yong, et al.GIL partial discharge localization method based on 3D optical fingerprint and NPSO-KELM[J]. Proceedings of the CSEE, 2020, 40(20): 6754-6764.
[6] 邓冉, 朱永利, 刘雪纯, 等. 基于变量预测-谷本相似度方法的局部放电中未知类型信号识别[J]. 电工技术学报, 2020, 35(14): 3105-3115.
Deng Ran, Zhu Yongli, Liu Xuechun, et al.Pattern recognition of unknown types in partial discharge signals based on variable predictive model and tanimoto[J]. Transactions of China Electrotechnical Society, 2020, 35(14): 3105-3115.
[7] 律方成, 金虎, 王子建, 等. 基于主成分分析和多分类相关向量机的GIS局部放电模式识别[J]. 电工技术学报, 2015, 30(6): 225-231.
Lü Fangcheng, Jin Hu, Wang Zijian, et al.GIS partial discharge pattern recognition based on principal component analysis and multiclass relevance vector machine[J]. Transactions of China Electrotechnical Society, 2015, 30(6): 225-231.
[8] 秦雪, 钱勇, 许永鹏, 等. 基于2D-LPEWT的特征提取方法在电缆局部放电分析中的应用[J]. 电工技术学报, 2019, 34(1): 170-178.
Qin Xue, Qian Yong, Xu Yongpeng, et al.Application of feature extraction method based on 2D-LPEWT in cable partial discharge analysis[J]. Transactions of China Electrotechnical Society, 2019, 34(1): 170-178.
[9] 高佳程, 朱永利, 郑艳艳, 等. 基于VMD-WVD分布与堆栈稀疏自编码网络的局放类型识别[J]. 中国电机工程学报, 2019, 39(14): 4118-4129.
Gao Jiacheng, Zhu Yongli, Zheng Yanyan, et al.Pattern recognition of partial discharge based on VMD-WVD and SSAE[J]. Proceedings of the CSEE, 2019, 39(14): 4118-4129.
[10] Majidi M, Fadali M S, Etezadi-Amoli M, et al.Partial discharge pattern recognition via sparse representation and ANN[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2015,22(2): 1061-1070.
[11] 宋辉, 代杰杰, 张卫东, 等. 复杂数据源下基于深度卷积网络的局部放电模式识别[J]. 高电压技术, 2018, 44(11): 3625-3633.
Song Hui, Dai Jiejie, Zhang Weidong, et al.Partial discharge pattern recognition based on deep convolutional neural network under complex data sources[J]. High Voltage Engineering, 2018, 44(11): 3625-3633.
[12] 刘宇舜, 程登峰, 夏令志, 等. 基于单通道盲源分离算法的局部放电特高频信号去噪方法[J]. 电工技术学报, 2018, 33(23): 5625-5636.
Liu Yushun, Cheng Dengfeng, Xia Lingzhi, et al.Partial discharge ultra-high frequency signal de-noising method based on single-channel blind source separation algorithm[J]. Transactions of China Electrotechnical Society, 2018, 33(23): 5625-5636.
[13] Tang Ju, Jin Miao, Zeng Fuping, et al.Assessment of PD severity in gas-insulated switchgear with an SSAE[J]. IET Science, Measurement & Technology, 2016, 11(4): 423-430.
[14] Sriram S, Nitin S, Parbhu K M M, et al. Signal denoising techniques for partial discharge measurements[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2005, 12(6): 1182-1191.
[15] 钱勇, 黄成军, 陈陈, 等. 多小波消噪算法在局部放电检测中的应用[J]. 中国电机工程学报, 2007, 27(6): 89-95.
Qian Yong, Huang Chengjun, Chen Chen, et al.Application of multi-wavelet based on denoising algorithm in partial discharge detection[J]. Proceedings of the CSEE, 2007, 27(6): 89-95.
[16] 谢军, 刘云鹏, 刘磊, 等. 局放信号自适应加权分帧快速稀疏表示去噪方法[J]. 中国电机工程学报, 2019, 39(21): 6428-6439.
Xie Jun, Liu Yunpeng, Liu Lei, et al.A partial discharge signal denoising method based on adaptive weighted framing fast sparse representation[J]. Proceedings of the CSEE, 2019, 39(21): 6428-6439.
[17] Raymond W J K, Illias H A, Abu Bakar A H. High noise tolerance feature extraction for partial discharge classification in XLPE cable joints[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(1): 66-74.
[18] 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.
Wan Xiaoqi, Song Hui, Luo Lingen, et al.Application of convolutional neural networks in pattern recognition of partial discharge image[J]. Power System Technology, 2019, 43(6):2219-2226.
[19] 魏振, 齐波, 左健, 等. 基于局部放电图像特征的换流变压器油纸绝缘缺陷诊断方法[J]. 电网技术, 2015, 39(4): 1160-1166.
Wei Zhen, Qi Bo, Zuo Jian, et al.A method to diagnose defects in oil-paper insulation of converter transformer based on image feature of partial discharge[J]. Power System Technology, 2015, 39(4): 1160-1166.
[20] 周沙, 景亮. 基于矩特征与概率神经网络的局部放电模式识别[J]. 电力系统保护与控制, 2016, 44(3): 98-102.
Zhou Sha, Jing Liang.Pattern recognition of partial discharge based on moment features and probabilistic neural network[J]. Power System Protection and Control, 2016, 44(3): 98-102.
[21] Satish L, Nazneen B.Wavelet-based denoising of partial discharge signals buried in excessive noise and interference[J]. IEEE Transactions on Industrial Electronics, 2003, 14(1): 3-14.
[22] 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, 2019, 67(4): 3277-3287.
[23] Bay H, Ess A, Tuytelaars T, et al.Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.
[24] 刘翠响, 李敏, 张凤林. 基于词包模型和SURF局部特征的人脸识别[J]. 河北大学学报(自然科学版) , 2017, 37(4): 411-418.
Liu Cuixiang, Li Min, Zhang Fenglin.Face recognition based on BOW and SURF local features[J]. Journal of Hebei University (Natural Science Edition), 2017, 37(4): 411-418.
[25] 李康顺, 王福滨, 张丽霞, 等. 基于改进BOF算法的图像识别和分类[J]. 中南大学学报(自然科学版), 2016, 47(5): 1599-1605.
Li Kangshun, Wang Fubin, Zhang Lixia, et al.Image recognition and classification based on improved BOF algorithm[J]. Journal of Central South University (Science and Technology), 2016, 47(5): 1599-1605.
[26] 邱志斌, 阮江军, 黄道春, 等. 基于支持向量机的棒-板空气间隙击穿电压预测方法及其应用[J]. 电工技术学报, 2017, 32(19): 220-228.
Qiu Zhibin, Ruan Jiangjun, Huang Daochun, et al.Breakdown voltage prediction method of rod-plane air gaps based on support vector machine and its applications[J]. Transactions of China Electrotechnical Society, 2017, 32(19): 220-228.
[27] Passino K M.Biomimicry of bacterial foraging for distributed optimization and control[J]. IEEE Control Systems Magazine(S0272-1708), 2002, 22(3): 52-67.
[28] 商立群, 朱伟伟. 基于全局学习自适应细菌觅食算法的光伏系统全局最大功率点跟踪方法[J]. 电工技术学报, 2019, 34(12): 2606-2614.
Shang Liqun, Zhu Weiwei.Photovoltaic system global maximum power point tracking method based on the global learning adaptive bacteria foraging algorithm[J]. Transactions of China Electrotechnical Society, 2019, 34(12): 2606-2614.