深度学习在绝缘子红外图像异常诊断的应用

范鹏; 冯万兴; 周自强; 赵淳; 周盛; 姚翔宇

深度学习在绝缘子红外图像异常诊断的应用

范鹏^{1, 2,},
冯万兴^{1, 2},
周自强^{1, 2},
赵淳^{1, 2},
周盛^{1, 2},
姚翔宇^{1, 2}

1.
南瑞集团（国网电力科学研究院）有限公司，江苏南京 211106
2.
国网电力科学研究院武汉南瑞有限责任公司，湖北武汉 430074

基金项目:

国网电力科学研究院有限公司科技项目 524625190054

详细信息

作者简介:
范鹏（1986-），男，硕士，高级工程师，主要从事电网智能运检、电力物联网与人工智能方面的技术研究工作。E-mail: fanpeng2@sgepri.sgcc.com.cn

中图分类号: TN219
计量
- 文章访问数: 558
- HTML全文浏览量: 183
- PDF下载量: 59
出版历程
- 收稿日期: 2020-03-07
- 修回日期: 2020-11-21
- 刊出日期: 2021-01-19

Application of Deep Learning in Abnormal Insulator Infrared Image Diagnosis

FAN Peng^{1, 2,},
FENG Wanxing^{1, 2},
ZHOU Ziqiang^{1, 2},
ZHAO Chun^{1, 2},
ZHOU Sheng^{1, 2},
YAO Xiangyu^{1, 2}

1.
NARI Group (State Grid Electric Power Research Institute) Co., Ltd., Nanjing 211106, China
2.
Wuhan NARI Limited Liability Company, State Grid Electric Power Research Institute, Wuhan 430074, China

摘要

摘要: 绝缘子的红外图像分析一般采用图像处理的方法，易受背景环境和数据量的影响，准确率和效率均较低，本文提出一种深度学习的异常诊断方法，基于改进的Faster R-CNN方法搭建检测网络，开展不同类型的绝缘子测试。研究结果表明：相对于神经网络（Back Propagation，BP）、Faster R-CNN方法，本文方法可高效地诊断出绝缘子的异常缺陷，平均检测精度达到90.2%；单Ⅰ型和Ⅴ型绝缘子的异常诊断准确率高于双Ⅰ型绝缘子。研究结果可为输电线路绝缘子异常诊断提供一定的参考。
- 绝缘子 /
- 异常诊断 /
- 深度学习 /
- Faster R-CNN /
- 平均检测精度 /
- 红外图谱
Abstract: Because of the effects of the background environment and data volume, the accuracy and efficiency of abnormal defects in traditional infrared images of insulators are generally low. In this study, a deep-learning anomaly diagnosis method is proposed. Based on the improved faster region-based convolutional neural network (R-CNN) method, a detection network is built to test different types of insulators. Results show that compared with the back propagation neural network and faster R-CNN methods, the proposed method can diagnose abnormal defects of insulators efficiently with a mean average precision of 90.2%. In addition, the diagnostic accuracy of single type Ⅰ and type Ⅴ insulators is higher than that of double type Ⅰ insulators. The results can provide a reference for insulator defect identification in transmission lines.
- insulator /
- abnormal diagnosis /
- deep learning /
- Faster R-CNN /
- mAP /
- infrared image

HTML全文

图 1 Faster R-CNN的算法流程

Figure 1. Algorithm flow of Faster R-CNN

下载: 全尺寸图片幻灯片

图 2 正负样本判定

Figure 2. Positive and negative sample decision

下载: 全尺寸图片幻灯片

图 3 改进的Faster R-CNN结构

Figure 3. Structure of improved Faster R-CNN

下载: 全尺寸图片幻灯片

图 4 准确率-召回率关系曲线

Figure 4. Relation curves of precision and recall

下载: 全尺寸图片幻灯片

图 5 不同类型绝缘子的红外图像

Figure 5. Infrared image of different types of insulators

下载: 全尺寸图片幻灯片

表 1 软硬件配置

Table 1 Hardware and software configuration

Name	Model
Operating system	Ubuntu 16.04.1
Database	mysql 5.5.20
CPU	Intel Xeon Silver 4114T 12C
GPU	NVIDIA GTX1080Ti
Memory	32 G
Hard disk	1 T
Frame	Detectron

下载: 导出CSV

表 2 样本配置信息

Table 2 Information of sample configuration

sample type	training set	verification set	test set	total
positive	500	250	750	1500
negative	500	250	125	875
total	1000	500	875	2375

下载: 导出CSV

表 3 不同方法的实验结果统计

Table 3 Statistics of experimental results by different methods

Name	Precision	Recall	mAP	Time/s
BP	93.5%	90.4%	80.3%	2.3
Faster R-CNN	98.7%	95.3%	88.7%	1.2
BFEM	99.2%	97.6%	90.2%	0.9

下载: 导出CSV

表 4 绝缘子异常诊断的准确率

Table 4 Accuracy of insulator anomaly diagnosis

Insulator type	Abnormal total	Detected number	Accuracy
Single Ⅰ	62	61	98.4%
Double Ⅰ	47	44	93.6%
Ⅴ	31	31	100.0%

下载: 导出CSV

参考文献(19)

[1]	陈俊佑, 金立军, 段绍辉, 等.基于Hu不变矩的红外图像电力设备识别[J].机电工程, 2013, 30(1): 5-8. https://www.cnki.com.cn/Article/CJFDTOTAL-JDGC201301003.htm CHEN Junyou, JIN Lijun, DUAN Shaohui, et al. Power equipment identification in infrared image based on Hu invariant moments[J]. Journal of Mechanical & Electrical Engineering, 2013, 30(1): 5-8. https://www.cnki.com.cn/Article/CJFDTOTAL-JDGC201301003.htm
[2]	邹辉, 黄福珍.基于改进Fast-Match算法的电力设备红外图像多目标定位[J].中国电机工程学报, 2017, 37(2): 591-598. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201702027.htm ZOU Hui, HU Fuzhen. Multi-target localization for infrared images of electrical equipment based on improved fast-match algorithm[J]. Proceedings of the CSEE, 2017, 37(2): 591-598. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDC201702027.htm
[3]	魏秀深.解析深度学习:卷积神经网络原理与视觉实践[M].北京:电子工业出版社, 2018. WEI Xiushen. Analytic Deep Learning: Convolutional Neural Network Theory And Visual Practice[M]. Beijing: Electronic Industry Press, 2018.
[4]	罗舜.电力变压器套管将军帽发热故障的红外诊断分析[J].变压器, 2018, 55(1): 50-53. https://www.cnki.com.cn/Article/CJFDTOTAL-BYQZ201801018.htm LUO Sun. Infrared diagnosis analysis of power transformer bushing coupler heating[J]. Transformer, 2018, 55(1): 50-53. https://www.cnki.com.cn/Article/CJFDTOTAL-BYQZ201801018.htm
[5]	张杰, 付泉泳, 袁野.变压器局部放电带电检测技术应用研究[J].变压器, 2018, 55(8): 66-71. https://www.cnki.com.cn/Article/CJFDTOTAL-BYQZ201808023.htm ZHANG Jie, FU Quanyong, YUAN Ye. Application research of electric detection technology of partial discharge for transformer[J]. Transformer, 2018, 55(8): 66-71. https://www.cnki.com.cn/Article/CJFDTOTAL-BYQZ201808023.htm
[6]	梁天明, 袁焯锋, 石延辉.高压交流滤波电容器局部过热诱因分析及预防[J].电力电容器与无功补偿, 2015, 36(6): 49-53. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201506011.htm LIANG Tianming, YUAN Daofeng, SHI Yanhui. Cause analysis and preventions on local overheating of high voltage ac filter capacitor[J]. Power Capacitor & Reactive Power Compensation, 2015, 36(6): 49-53. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201506011.htm
[7]	潘臻, 安立.一起35 kV并联电容器组事故爆炸原因分析[J].电力电容器与无功补偿, 2015, 36(3): 17-20. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201503005.htm PAN Zhen, AN Li. Analysis of 35 kV shunt capacitor banks explosion accident[J]. Power Capacitor & Reactive Power Compensation, 2015, 36(3): 17-20. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201503005.htm
[8]	黄斌, 李昊, 徐姗姗, 等.一起35 kV并联电容器组爆炸原因分析及防范措施[J].电力电容器与无功补偿, 2018, 39(1): 23-27. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201801005.htm HUANG Bin, LI Hao, XU Sansan, et al. Reason analysis and precautionary measures for a 35kv shunt capacitor bank explosion[J]. Power Capacitor & Reactive Power Compensation, 2018, 39(1): 23-27. https://www.cnki.com.cn/Article/CJFDTOTAL-DLDY201801005.htm
[9]	商俊平, 李储欣, 陈亮.基于视觉的绝缘子定位与自爆缺陷检测[J].电子测量与仪器学报, 2017, 31(6): 844-849. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201706007.htm SHANG Junping, LI Chuxin, CHEN Liang. Location and detectionfor self-explode insulator based on vision[J]. Journal of Electronic Measurement and Instrumentation, 2017, 31(6): 844-849. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201706007.htm
[10]	沈新平, 彭刚, 袁志强.基于霍夫变换和RANSAC算法的绝缘子定位方法[J].电子测量技术, 2017, 40(6): 132-137. https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL201706031.htm SHEN Xinping, PENG Gang, YUAN Zhiqiang. Insulator location method based on hough transformation and RANSAC algorithm[J]. Electronic Measurement Technology, 2017, 40(6): 132-137. https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL201706031.htm
[11]	李军锋, 王钦若, 李敏.结合深度学习和随机森林的电力设备图像识别[J].高电压技术, 2017, 43(11): 3705-3711. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ201711028.htm LI Junfeng, WANG Qinruo, LI Min, et al. Electric Equipment Image Recognition Based on Deep Learning and Random Forest[J]. High Voltage Engineering, 2017, 43(11): 3705-3711. https://www.cnki.com.cn/Article/CJFDTOTAL-GDYJ201711028.htm
[12]	侯春萍, 章衡光, 张巍, 等.输电线路绝缘子自爆缺陷识别方法[J].电力系统及其自动化学报, 2019, 31(6): 1-6. HOU Chunping, ZHANG Hengguang, ZHANG Wei, et al. Recognition method for faults of insulators on transmission lines[C]//Proceedings of the CSU-EPSA, 2019, 31(6): 1-6.
[13]	左川.基于图像识别的输电线路绝缘子检测方法研究[D].北京: 华北电力大学, 2019. ZUO Chuang. Research on detection method of transmission line insulator based on image recognition[D]. Beijing: North China Electric Power University, 2019.
[14]	杨光俊.卷积神经网络在电力设备红外图像识别中的应用研究[D].广州: 华南理工大学, 2019. YANG Guangjun. Research on the application of convolutional neural network in infrared image recognition of power equipment[D]. Guangzhou: South CHINA University of Technology, 2019.
[15]	周可慧, 廖志伟, 肖异瑶, 等.基于改进CNN的电力设备红外图像分类模型构建研究[J].红外技术, 2019, 41(11): 1033-1038. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201911007.htm ZHOU Kehui, LIAO Zhiwei, XIAO Yiyao, et al. Construction of infrared image classification model for power equipments based on improved CNN[J]. Infrared Technology, 2019, 41(11): 1033-1038. https://www.cnki.com.cn/Article/CJFDTOTAL-HWJS201911007.htm
[16]	许必宵.基于多尺度特征融合与上下文分析的目标检测技术研究[D].南京: 南京邮电大学, 2019. XU Bixiao. Research on object detection technology based on multi-scale feature fusion and context analysis[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2019.
[17]	张丹丹.基于航拍图像的绝缘子自爆位置的检测[D].成都: 西华大学, 2018. ZHANG Dandan. Detection of self-exploding position of insulator based on aerial image[D]. Chengdu: Xihua University, 2018.
[18]	王梦.基于绝缘子图像的缺陷检测方法研究[D].武汉: 华中科技大学, 2019. WANG Meng. A thesis submitted in partial fulfillment of the requirements[D]. Wuhan: Huazhong University of Science & Technology, 2019.
[19]	国家能源局.带电设备红外诊断应用规范: DL/T 664-2008[S].北京: 中国标准出版社, 2008. National Energy Administration. Application rules of infrared diagnosis for live electrical equipment: DL/T 664-2008[S]. Beijing: China Electric Power Press, 2008.

施引文献(24)

期刊类型引用(10)

1.	马庆禄，汪曦洪，马恋，段学锋. 隧道内不均匀照度下无人驾驶视觉融合感知方法. 应用光学. 2025(01): 89-101 . 百度学术
2.	段锦，张昊，宋靖远，刘举. 深度学习偏振图像融合研究现状. 红外技术. 2024(02): 119-128 . 本站查看
3.	陈锦妮，陈宇洋，李云红，拜晓桦. 基于结构与分解的红外光强与偏振图像融合. 红外技术. 2023(03): 257-265 . 本站查看
4.	张哲卿，朱志宇，魏莱，古静，顾健，臧旭. 复杂海面背景下船舶红外偏振图像融合方法. 电光与控制. 2023(07): 68-72 . 百度学术
5.	张媛，陆小妍，郭群，邱建博，缪正飞. 基于主成分分析和双树复小波变换的CT和MRI图像融合改进算法研究. 中国医学装备. 2022(04): 7-12 . 百度学术
6.	王晓娜，潘晴，田妮莉. 基于NSST-DWT-ICSAPCNN的多模态图像融合算法. 红外技术. 2022(05): 497-503 . 本站查看
7.	田立凡，杨莘，梁佳明，吴谨. 基于SGWT和多显著性的红外与可见光图像融合. 红外技术. 2022(07): 676-685 . 本站查看
8.	安晓东，李亚丽，王芳. 汽车驾驶辅助系统红外与可见光融合算法综述. 计算机工程与应用. 2022(19): 64-75 . 百度学术
9.	刘立群，顾任远，周煜博，火久元. 多尺度分解双寻优策略SPCNN的果园苹果异源图像融合模型. 农业工程学报. 2022(17): 158-167 . 百度学术
10.	贺兴容，龚奕宇，范松海，吴天宝，刘益岑，刘小江. 基于帧差检测技术与区域特征的红外与可见光图像融合算法. 现代电子技术. 2019(01): 57-61 . 百度学术