基于改进YOLOv4的变电站刀闸状态自动识别方法

Automatic Recognition Method of the Knife-switch State in Substation Based on Improved YOLOv4

传统的变电站刀闸状态自动识别方法存有不足之处,因此提出基于改进YOLOv4的变电站刀闸状态自动识别方法。首先对基于改进YOLOv4的变电站刀闸状态自动识别方法进行设计,其中包括变电站刀闸状态的预测,设定变电站刀闸设备运行状态指标,最后,实现变电站刀闸运行状态自动识别,基于以上步骤完成基于改进YOLOv4的变电站刀闸状态自动识别方法。为证实所设计方法的有效性,建立对比实验,将文中即基于改进YOLOv4的变电站刀闸状态自动识别方法与基于巡检机器人的变电站刀闸状态自动识别方法,以及基于深度学习的变电站刀闸状态自动识别方法进行对比研究。最后得出较为准确的基于改进YOLOv4的变电站刀闸状态自动识别,且优于其它两种方法。

The traditional automatic recognition method of substation knife-switch state possesses some shortcomings,so,an improved YOLOv4 based automatic recognition method of substation knife-switch state is proposed.Firstly,the automatic recognition method of substation knife-switch state based on improved YOLOv4 is designed,including the prediction of substation knife-switch state,setting the operating state indicators of substation knife-switch equipment,and finally,realizing the automatic recognition of substation knife-switch operating state.Based on the above steps,the automatic recognition method of substation knife-switch state based on improved YOLOv4 is completed.In order to verify the effectiveness of the designed method,a comparative experiment was established,and the proposed method,namely,the automatic recognition method of substation knife-switch state based on improved YOLOv4,the automatic recognition method of substation knife-switch state based on inspection robot and the automatic recognition method of substation knife-switch state based on deep learning were compared and studied.Finally,it is concluded that the automatic recognition method based on improved YOLOv4 is more accurate and better than the other two methods.