基于图像能量和NSST的电力设备发热定位方法  

Heating Location Method for Power Equipment Based on Image Energy and NSST

作　　者：潘超 胡梓熊 钱勇[2] 盛戈皞[2] 周小丽 Pan Chao;Hu Zixiong;Qian Yong;Sheng Gehao;Zhou Xiaoli(School of Information Science and Technology,Fudan University,Shanghai 200433,China;School of Electronic Information and Electrical Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]复旦大学信息科学与工程学院,上海200433 [2]上海交通大学电子信息与电气工程学院,上海200240

出　　处：《电气自动化》2024年第5期66-68,共3页Electrical Automation

摘　　要：为了解决现有红外检测技术中电力设备发热点定位不够准确的问题,基于图像能量和非下采样剪切波变换,提出了一种实时监测方法。结合红外图像灰度与温度的关系,使用了图像能量算法和种子生长算法对红外图像进行分割;同时在分析终端使用非下采样剪切波变换融合可见光与红外图像,提高了发热区域的定位精准度;对发热特征进行分析,减小了误判、漏判情况出现的概率。研究结果表明,所提方法为电力设备故障发热区域定位提供了有效信息,可用于在线监测与故障定位。In order to solve the problem of inaccurate positioning of power equipment hot spots in existing infrared detection technologies,a real-time monitoring method based on image energy and non-subsampled shear wave transformation(NSST)was proposed.Combining the relationship between infrared image grayscale and temperature,image energy algorithm and seed growth algorithm were used to segment the infrared image;at the same time,NSST was used in the analysis terminal to fuse visible and infrared images,improving the positioning accuracy of the heating area;by analyzing the heating characteristics,the probability of misjudgment and missing judgment was reduced.The research results show that the proposed method provides effective information for locating the heating area of power equipment faults,and can be used for online monitoring and fault location.

关 键 词：红外图像 可见光图像 图像能量算法 种子生长算法 非下采样剪切波变换 

分 类 号：TM81[电气工程—高电压与绝缘技术]