Abstract
The current high impedance fault (HIF) detection devices are mainly based on threshold method, the hardware cannot meet the computing requirements of artificial intelligence (AI), and the software structure is difficult to adapt to the upgrade requirements of AI. These AI detection algorithms are mainly based on simulation analysis and laboratory testing and have not yet been applied practically. The paper develops an edge AI-based HIF detection device, it combines the main body and independent AI module. The AI module embeds an edge identification algorithm and shares the sampling data with the main body. The detection result is achieved from intelligent classifier in edge AI module and fed back to the main device. Finally, the device is tested on the Luohe distribution network true test platform, the detection accuracy for multiple types of fault is 98.6%.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
