采用无人机航拍图像的电力绝缘子缺损检测

Power Insulator Defect Detection Using UAV Aerial Imagery

高压输电线路距离远、规模大,工作环境恶劣,采用人力巡检耗时长、劳动强度大,不能满足日益增长的巡检需求。结合视觉检测与智能算法,使用无人机航拍图像实现目标检测和故障辨识,能准确快速定位故障点,大幅提高巡检质量,提高故障检测的效率,已经成为当前研究的热点。本文在深入调查大量国内外文献的基础上,使用Faster-RCNN算法,使用848张无人机捕获的绝缘子图像构建数据集,训练出了用于检测绝缘子以及绝缘子缺损的模型,引入平均精度MAP等指标对模型进行评价,在绝缘子以及绝缘子缺损两类识别中,MAP分别达到了97.73%和90.52%。结果表明,该算法在识别绝缘子缺损故障具有良好的效果。

Finding automated fault identification methods for transmission lines has been a hot research problem in the field of power applications in order to meet the growing need for electricity consumption and safe operation of power grid systems.In this paper,based on an in-depth survey of a large amount of domestic and international literature,the Faster-RCNN algorithm is used to train a model for detecting insulators as well as missing insulators using 848 UAV-captured insulator images as the main research object,and the model is evaluated by introducing indexes such as MAP,which reaches 97.73% in the recognition of insulators as well as missing insulators and 90.52%.The implementation results show that the algorithm can achieve good results in the field of identifying missing insulator faults.