基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断

doi:10.11930/j.issn.1004-9649.2017.05.052.07

中国电力 ›› 2017, Vol. 50 ›› Issue (5): 52-58.DOI: 10.11930/j.issn.1004-9649.2017.05.052.07

基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断

姜云土¹, 韩军², 丁建¹, 傅寒凝¹, 王榆夫², 曹伟²

1. 国网浙江省电力公司检修分公司,浙江杭州 310007;
2. 上海大学通信与信息工程学院,上海 200444

收稿日期:2017-02-17 出版日期:2017-05-20 发布日期:2017-05-26
作者简介:姜云土（1985—）,男,浙江衢州人,工程师,从事无人机巡检与检修研究工作。E-mail:284617314@qq.com
基金资助:
国家电网公司科技资助项目（520626140006）

The Identification and Diagnosis of Self-Blast Defects of Glass Insulators Based on Multi-Feature Fusion

JIANG Yuntu¹, HAN Jun², DING Jian¹, FU Hanning¹, WANG Yufu², CAO Wei²

1. State Grid Zhejiang Electric Power Company Overhaul Branch, Hangzhou 310007, China;
2. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China

Received:2017-02-17 Online:2017-05-20 Published:2017-05-26
Supported by:
This work is supported by Science and Technology Program of SGCC (No. 520626140006).

摘要/Abstract

摘要： 在无人机检测输电线路缺陷研究中,为提高识别绝缘子的正确率,有效降低背景纹理及光线的影响,提出了一种融合绝缘子形状、颜色与纹理进行识别绝缘子的方法。针对玻璃绝缘子的掉片缺陷,研究了一种感知绝缘子片重心间距离的缺陷检测方法。该方法对绝缘子正确识别率高于90%,误识别率低于10%。通过无人机巡检采集的大量输电线路图像,实验结果验证这种方法在各种复杂背景条件下能有效地识别出绝缘子,并能检测玻璃绝缘子的掉片缺陷。

关键词: 玻璃绝缘子, 绝缘子识别, 绝缘子缺陷诊断, 平行形状, 显著性模型

Abstract: In order to improve the recognition accuracy of insulators in UAV inspection and effectively reduce the influence of the background texture and illumination, a new insulator recognition method is proposed, which integrates the shape, color and texture of insulators. Aimed at the off-chip defects of glass insulators, a defect-detecting method is presented, which can sense the distance between gravity centers of insulator chips, and has an recognition accuracy of insulators higher than 90%. Based on testing with numerous UVA inspection images of transmission lines, it is proved that the proposed method can effectively recognize the insulators under various complicated background conditions, and detect the off-chip defects of glass insulators.

Key words: glass insulator, insulator recognition, insulator defect diagnosis, parallel shape, saliency model

中图分类号:

TM853

姜云土, 韩军, 丁建, 傅寒凝, 王榆夫, 曹伟. 基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断[J]. 中国电力, 2017, 50(5): 52-58.

JIANG Yuntu, HAN Jun, DING Jian, FU Hanning, WANG Yufu, CAO Wei. The Identification and Diagnosis of Self-Blast Defects of Glass Insulators Based on Multi-Feature Fusion[J]. Electric Power, 2017, 50(5): 52-58.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.2017.05.052.07

https://www.electricpower.com.cn/CN/Y2017/V50/I5/52

参考文献

[1] 林聚财,韩军,陈舫明,等. 基于彩色图像的玻璃绝缘子缺陷诊断[J]. 电网技术,2011,35（1）：127-133.
LIN Jucai, HAN Jun, CHEN Fangming, et al . Defects detection of glass insulator based on color image[J]. Power System Technology, 2011, 35(1): 127-133.
[2] 张少平,杨忠,黄宵宁,等. 航拍图像中玻璃绝缘子自爆缺陷的检测及定位[J]. 太赫兹科学与电子信息学报,2013,11（4）：609- 613.
ZHANG Shaoping, YANG Zhong, HUANG Xiaoning, et al . Defects detection and positioning for glass insulator from aerial images[J]. Journal of Terahertz Science and Electronic Information Technology, 2013, 11(4): 609-613.
[3] 姚春羽,金立军,闫书佳. 电网巡检图像中绝缘子的识别[J]. 系统仿真学报,2012,24（9）：1818-1822.
YAO Chunyu, JIN Lijun, YAN Shujia. Recognition of insulator string in power grid patrol images[J]. Journal of System Simulation, 2012, 24(9): 1818-1822.
[4] TODT E, TORRAS C. Color-contrast landmark detection and encoding in outdoor images [J]. Springer Berlin Heidelberg, 2005(S): 612-619.
[5] MOHAMMADPOUR M, MOZAFFARI S. A method for content- based image retrieval using visual attention model[C]//IKT2015 7th International Conference on Information and Knowledge Technology: 1-5.
[6] XU Yan, DUAN Fuzhou. Color space transformation and object oriented based information extraction of aerial images [C]//2013 21st International Conference on Geoinformatics: 1-4.
[7] POPESCU D, ICHIM L, ANGELESCU N, et al . Improving texture based classification of aerial images by fractal features[C]//2015 20th International Conference on Control Systems and Science:578-583.
[8] REID A, RAMOS F, SUKKARIEH S. Multi-class classification of vegetation in natural environments using an unmanned aerial system[C]//2011 IEEE International Conference on Robotics and Automation: 2953-2959.
[9] RAJA R, ROOMI S M, DHARMALAKSHMI D. Classification and retrieval of natural scenes[C]//2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT): 1-8.
[10] ELHARIRI E, BENDARY N E, ELLA HASSANIEN A. Plant classification system based on leaf features[C]//2014 9th International Conference on Computer Engineering & Systems (ICCES): 271-276.
[11] NAN Bingfei, XU Ye, MU Zhichun, et al . Content-based image retrieval using local texture-based color histogram[C]//2015 IEEE 2nd International Conference on Cybernetics(CYBCONF): 399-405.
[12] 张晶晶,韩军,赵亚博,等. 形状感知的绝缘子识别与缺陷诊断[J]. 中国图象图形学报,2014,19（8）：1077-1084.
ZHANG Jingjing, HAN Jun, ZHAO Yabo, et al . Insulator recognition and defects detection based on shape perceptual[J]. Journal of Image and Graphics, 2014, 19(8): 1194-1201.
[13] 韩军,张晶晶,王滨海. 基于感知组织的输电线路结构识别方法[J]. 红外与激光工程,2013,42（2）：3458-3463.
HAN Jun, ZHANG Jingjing, WANG Binhai. Method on recognizing the structure of transmission line based on perceptual organization[J]. Infrared and Laser Engineering, 2013, 42(2): 3458-3463.
[14] 郑秋玮,刘华钢,邹建明,等. ±500 kV兴安直流线路复合绝缘子积污特性[J]. 中国电力,2015,48（8）：86-91.
ZHENG Qiuwei, LIU Huagang, ZOU Jianming, et al .Contamination accumulating features of composite insulator of ±500 kV Xingren-Baoan HVDC transmission line[J]. Electric Power, 2015, 48(8): 86-91.

基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断

The Identification and Diagnosis of Self-Blast Defects of Glass Insulators Based on Multi-Feature Fusion

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 2

编辑推荐

Metrics

[1]	陈原, 吴光亚, 叶廷路, 高海峰, 高舜安, 苏建军, 夏彦卫, 宋福如, 周国华, 杨静, 罗永勤, 陕华平, 卢毅, 牛彪, 王馨, 张旭, 范硕超, 赵媛. 发展工厂复合化绝缘子提高特高压电网配置质量[J]. 中国电力, 2017, 50(8): 1-15.
[2]	李特，周国良，刘岩，谢成，章锡明. 220 kV玻璃绝缘子并联间隙雷电冲击放电路径研究[J]. 中国电力, 2015, 48(8): 92-96.

模态框（Modal）标题

基于多特征融合的玻璃绝缘子识别及自爆缺陷的诊断

The Identification and Diagnosis of Self-Blast Defects of Glass Insulators Based on Multi-Feature Fusion

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 2

编辑推荐

Metrics