摘要
借助机器视觉和深度学习进行变压器内部放电碳痕的检测识别,采用CLAHE算法进行图像特征增强和YOLOv4-tiny模型进行目标检测,验证其平均精度值满足实际检测需求。
Machine vision and deep learning are used to detect and identify the internal discharge carbon marks of the transformer.CLAHE algorithm is used to enhance image features and Yolov4-tiny model is used to detect targets.The average accuracy is verified to meet the actual detection requirements.
作者
魏菊芳
刘力卿
唐庆华
贺春
李松原
方琼
WEI Ju-fang;LIU Li-qing;TANG Qing-hua;HE Chun;LI Song-yuan;FANG Qiong(State Grid Tianjin Electric Power Research Institute,Tianjin 300384,China;Tianjin Key Laboratory of Internet of Things in Electricity,Tianjin 300384,China;State Grid Tianjin Electric Power Company,Tianjin 300384,China)
出处
《变压器》
2022年第2期6-12,共7页
Transformer
基金
国网天津市电力科技项目(KJ20-1-04)。
