|本期目录/Table of Contents|

[1]赵泽予,余 强,侯玉莲,等.电流互感器红外故障热像图自动诊断方法[J].工业仪表与自动化装置,2021,(06):78-82.[doi:10.19950/j.cnki.cn61-1121/th.2021.06.015]
　ZHAO Zeyu,YU Qiang,HOU Yulian,et al.Automatic diagnosis method of infrared fault thermal image of current transformer[J].Industrial Instrumentation & Automation,2021,(06):78-82.[doi:10.19950/j.cnki.cn61-1121/th.2021.06.015]
点击复制

电流互感器红外故障热像图自动诊断方法

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年06期
页码:
78-82
栏目:
出版日期:
2021-12-15

文章信息/Info

Title:
Automatic diagnosis method of infrared fault thermal image of current transformer
作者:
赵泽予1; 余 强1; 侯玉莲1; 高牧风1; 袁 刚2; 陈 诚3; 黄海洋3; 许志浩2
（1.国网湖北省电力有限公司检修公司，湖北 武汉 430050；2.南昌工程学院机械与电气工程学院，江西 南昌 330099；3.上海思源弘瑞自动化有限公司，上海 201100）
Author(s):
ZHAO Zeyu1;  YU Qiang1;  HOU Yulian1;  GAO Mufeng1;  YUAN Gang2;  CHEN Cheng3;  HUANG Haiyang3;  XU Zhihao2
(1.Maintenance company of State Grid Hubei Electric Power Co., Ltd., Hubei Wuhan 430050, China;2. School of Mechanical and Electrical Engineering, Nanchang Institute of Technology, Jiangxi Nanchang 330099, China；3. Shanghai SHR Automation Co., Ltd, Shangh
关键词:
红外图像; 电流互感器; 相对温差法; 同类比较法; 故障检测; 图像分割
Keywords:
infrared image;  current transformer;  relative temperature difference method;  homogeneous comparison method;  fault detection;  image segmentation
分类号:
TN215；TM452
DOI:
10.19950/j.cnki.cn61-1121/th.2021.06.015
文献标志码:
A
摘要:
相对温差法是电力设备红外图像故障诊断的定性方法，但该方法易将电压致热型缺陷误判或遗漏。因此，文中提出用目标检测算法做图像分割处理，结合自适应滑动窗口技术提取温度特征和坐标信息判断电流、电压致热故障诊断方法。其过程是，以目标检测算法的预测框坐标分割设备，设置自适应滑动窗口在分割后的图像中滑动，分别筛选出当前窗口中的最大温度值，将同位置中温度最小的一个作为设备的正常温度，其余的作为热点温度，根据窗口的位置判断热点温度的致热类型。以电流互感器为研究对象，根据致热类型相应的计算热点温度的相对温差或设备相同部位的温差来对设备进行诊断。实验表明，该方法最终能够对电流互感器的故障位置、故障类型和故障等级自动识别，能实现电流互感器故障的智能和高效诊断。
Abstract:
Relative temperature difference method is a qualitative method for infrared image fault diagnosis of power equipment, but it is easy to misjudge or omit the voltage induced heat defects. Therefore, this paper proposes an image segmentation method based on target detection algorithm, combined with adaptive sliding window technology to extract temperature characteristics and coordinate information to judge current and voltage thermal fault diagnosis method. The process is that, in the prediction of target detection algorithm coordinates integral equipment, set up the adaptive sliding window after the segmentation of the image, respectively, selected maximum temperature in the current window, with a minimum temperature in the location as the equipment of the normal temperature, the rest of the as a hot spot temperature, according to the position of the window of hot point temperature judgment to heat type. In this paper, the current transformer is taken as the research object, and the relative temperature difference of hot spot temperature or the temperature difference of the same part of the equipment is calculated according to the corresponding thermal type to diagnose the equipment. The experimental results show that this method can automatically identify the fault location, fault type and fault grade of CT, and realize intelligent and efficient fault diagnosis of CT.

参考文献/References:

[1]熊芬芳.基于图像处理技术的电气设备故障诊断方法研究[D].上海：东华大学,2015.

[2]LEE S Y , TEOH S S . A Survey on Infrared Thermography Based Automatic Electrical Fault Diagnosis Techniques[M]. School of Electrical and Electronic Engineering, Universiti Sains Malaysia, USM Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia, 2019.
[3]陈达,唐文虎,牛哲文.基于深度学习的电力设备红外图像故障诊断方法[J].广东电力,2021,34(01):97-105.
[4]刘云鹏,裴少通,武建华,等.基于深度学习的输变电设备异常发热点红外图片目标检测方法[J].南方电网技术,2019,13(02):27-33.
[5]王旭红,李浩,樊绍胜,等.基于改进SSD的电力设备红外图像异常自动检测方法[J].电工技术学报,2020,35(S1):302-310.
[6]张海春.变电运维工作中对电压致热型设备的红外测温技术[J].电子元器件与信息技术,2019,3(07):112-114+118.
[7]赖岳雄,潘月多.对电流致热型设备红外诊断技术的探讨[J].广东电力,2004(04):49-52.
[8]康龙.基于红外图像处理的变电站设备故障诊断[D].北京：华北电力大学,2016.
[9]徐雪涛.基于红外成像技术的电气设备故障诊断[D]. 北京：华北电力大学,2014.
[10]ZOU H , HUANG F . A novel intelligent fault diagnosis method for electrical equipment using infrared thermography[J]. Infrared Physics & Technology, 2015, 73:29-35.
[11]李文璞,谢可,廖逍,等.基于Faster RCNN变电设备红外图像缺陷识别方法[J].南方电网技术,2019,13(12):79-84.
[12]林颖,郭志红,陈玉峰.基于卷积递归网络的电流互感器红外故障图像诊断[J].电力系统保护与控制制,2015,43(16):87-94.
[13]中华人民共和国电力行业标准.带电设备红外诊断应用规范:DL/T 664-2016[S].2016.
[14]王小芳,毛华敏.一种复杂背景下的电力设备红外图像分割方法[J].红外技术,2019,41(12):1111-1116.
[15]林颖,郭志红,陈玉峰.基于卷积递归网络的电流互感器红外故障图像诊断[J].电力系统保护与控制制,2015,43(16):87-94.
[16]叶婕.基于图像分割的变电站电气设备故障自动检测[D].西安：西安科技大学,2012.
[17]GONG X , YAO Q , WANG M , et al. A deep learning approach for oriented electrical equipment detection in thermal images[J]. IEEE Access, 2018：1.
[18]XIA Z , NI Y , JIA H . Modified Object Detection Method Based on YOLO[M]. 2017.
[19]吕欣欣.红外图像分割算法研究及其在电气设备故障诊断中的应用[D].天津理工大学,2019.
[20]孙怡,吴邦树,刘仪卜,等.基于红外图像处理的电气设备故障诊断方法[J].机电工程技术,2016,45(06):59-62.
[21]CHOU Y C , YAO L . Automatic Diagnostic System of Electrical Equipment Using Infrared Thermography[C]// International Conference of Soft Computing & Pattern Recognition. IEEE, 2009.
[22]蔺丽华.基于红外成像的变电站设备安全预警关键技术研究[D].西安：西安科技大学,2014.
[23]刘一凡.基于红外热成像的电气设备故障诊断[D].保定：河北农业大学,2014.

相似文献/References:

[1]吕志强,田 勇,路夏甲,等.现场电流互感器误差测试间接检定法的研究[J].工业仪表与自动化装置,2014,(06):79.
　L? Zhiqiang,TIAN Yong,LU Xiajia,et al.The research of the indirect calibration methods on the site current transformers error test[J].Industrial Instrumentation & Automation,2014,(06):79.
[2]周小军,郭 佳,姜玉泉,等.红外图像几种边缘检测算法对比分析[J].工业仪表与自动化装置,2015,(04):58.
　ZHOU Xiaojun,GUO Jia,JIANG Yuquan,et al.Comparative study on several kinds of edge detection algorithm in infrared image[J].Industrial Instrumentation & Automation,2015,(06):58.
[3]李许军,姜毅龙,李宗义.电流互感器频率特性分析及改善研究[J].工业仪表与自动化装置,2018,(03):7.[doi:1000-0682（2018）03-0000-00]
　LI Xujun,JIANG Yilong,LI Zongyi.The analysis and improvement of frequency characteristics of current transformer[J].Industrial Instrumentation & Automation,2018,(06):7.[doi:1000-0682（2018）03-0000-00]
[4]张 曼,周 宁,田渭蓉,等.电流互感器容量与变比对测量精度的影响分析[J].工业仪表与自动化装置,2020,(05):90.[doi:1000-0682(2020)05-0000-00]
　ZHANG Man,ZHOU Ning,TIAN Weirong XU Jin,et al.Current transformer capacity and the variable ratio on the measuring accuracy analysis[J].Industrial Instrumentation & Automation,2020,(06):90.[doi:1000-0682(2020)05-0000-00]

备注/Memo

备注/Memo:
收稿日期：2021-06-15
作者简介:赵泽予(1991)，男，湖北孝感人，工程师，学士学位，研究方向：高压试验以及带电检测、仪器仪表校验专业工作研究。
通讯作者：许志浩（1988），男，湖北武汉人，讲师，博士，硕导，研究方向为电力设备智能检测与人工智能应用。
更新日期/Last Update: 1900-01-01