Recently, the transmission line infrared defect intelligent identification system developed by State Grid Power Space Technology Co., Ltd.

in conjunction with the school and other units has recently achieved industrial application in the operation and maintenance of major UHV

lines in my country. This is the first time in China that artificial intelligence (AI) technology has been applied to the detection of heat

generation in transmission lines on a large scale.

“This time, the technical research team combined with the business scenario and adopted the technical route of ‘minimized labeling + step-by

-step learning + interference point shielding’ to realize the intelligent identification of infrared defects and hidden dangers, and the model

identification accuracy rate reached more than 90%.” The system The application side, Guo Xiaobing, director of the inspection department

of the Space Technology Application Center of State Grid Electric Space Technology Co., Ltd., said.

According to reports, the system is currently being deployed and applied by State Grid Power Space Technology Co., Ltd., and it is the first

time in China that artificial intelligence technology has been applied to the detection of heat generation on transmission lines on a large scale.

Taking the infrared video of a 240 base tower as an example, traditional manual data review takes 5 hours, but now with this system, it only

takes 2 hours from uploading the video to completing the analysis, and there is no need for manual intervention in the process.

In the past, the process of using artificial intelligence to identify infrared image data was relatively complicated, and it was necessary to manually

identify the heating fault point in the screen, which was easily missed due to factors such as the experience and attention of the maintenance

personnel; in addition, the amount of infrared video data is huge. The re-inspection work is extremely difficult and inefficient, and it is easy to

cause dangerous events such as insulator drop-off. Using the newly developed infrared defect intelligent identification system for transmission lines,

it only needs to upload inspection infrared video with one click to quickly extract frames and intelligently identify heating defects, which can assist

line operation and maintenance units to eliminate hidden dangers of line tripping and power failure in a timely manner. The application of AI

technology to power grid inspection will greatly improve the inspection efficiency.