Research Article
Research and Design of Hidden Trouble Target Reconfirmation and Repeated Hidden Trouble Target Filtering Technology in Transmission Line Online Monitoring
@INPROCEEDINGS{10.1007/978-3-031-65123-6_1, author={Yi Yang and Zhengheng Li and Nanhao Liu and Yu Su and Xifeng Yan and Huabo Tao}, title={Research and Design of Hidden Trouble Target Reconfirmation and Repeated Hidden Trouble Target Filtering Technology in Transmission Line Online Monitoring}, proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Systems. 19th EAI International Conference, QShine 2023, Shenzhen, China, October 8 -- 9, 2023, Proceedings, Part II}, proceedings_a={QSHINE PART 2}, year={2024}, month={8}, keywords={AI visualization IOU intersection over union algorithm hidden danger target identification hidden danger target reconfirmation repeated hidden danger target filtering}, doi={10.1007/978-3-031-65123-6_1} }- Yi Yang
Zhengheng Li
Nanhao Liu
Yu Su
Xifeng Yan
Huabo Tao
Year: 2024
Research and Design of Hidden Trouble Target Reconfirmation and Repeated Hidden Trouble Target Filtering Technology in Transmission Line Online Monitoring
QSHINE PART 2
Springer
DOI: 10.1007/978-3-031-65123-6_1
Abstract
Transmission line online monitoring system is an important part of the transmission link of smart grid, and is an important technical means to realize the transmission line state operation, maintenance management, and improve the lean level of production and operation management. This paper introduces a hidden danger target identification and alarm filtering technology based on AI visualization and IOU intersection and comparison algorithm to improve the security and reliability of transmission lines in power system. First through the advanced deep learning target detection model, accurate target identification and classification, and then through the IOU the algorithm calculation continuous time period of the previous target identification box and the current target identification results of the boundary box overlap rate to confirm whether is the same entity, at the same time based on the context storage alarm filtering method, filter out the repeated alarm, reduce the network traffic transmission and server load, and reduce the workload of operational personnel. The experimental results show that the method is effective in enhancing target identification and reducing repeated alarm, and provides an efficient and reliable solution for the transmission line monitoring system.
