中圖分類號：TM71 文獻標志碼：A DOI: 10.16157/j.issn.0258-7998.234109
中文引用格式： 劉禹澤，潘明明，鄒華，等. 基于圖像識別的用電安全檢查子系統(tǒng)設(shè)計與實現(xiàn)[J]. 電子技術(shù)應用，2023，49(10)：23-28.
英文引用格式： Liu Yuze，Pan Mingming，Zou Hua，et al. Design and implementation of electricity safety inspection subsystem based on monitoring image data[J]. Application of Electronic Technique，2023，49(10)：23-28.

Design and implementation of electricity safety inspection subsystem based on monitoring image data

Abstract： Electricity safety inspection is an important way to ensure the normal operation of the power grid. Traditional electricity safety inspection mainly relies on manual inspection of places and equipment with safety hazards one by one. With the development of artificial intelligence technology, intelligent analysis based on image data can assist in timely identification of relevant safety hazards, reduce the experience requirements for inspectors, and improve efficiency while ensuring the accuracy of safety inspections. In order to better improve the accuracy of electricity safety inspection, the article proposes an electricity hazard identification algorithm based on YOLO neural network, which can dynamically identify the indicator lights of electrical equipment and compare them with normal states, and promptly issue alarm messages when abnormal states are found. Based on this algorithm, the article also designed and implemented an electricity safety inspection subsystem based on image recognition. Through actual data validation, the system can achieve a high level of inconsistent detection of equipment indicator status, meeting the demand for electricity safety inspection.

Key words : target detection algorithm；electricity safety inspection sub system；image recognition