基于深度学习的变电站巡检机器人自动抄表研究

微特电机 ›› 2023, Vol. 51 ›› Issue (10): 58-62.

基于深度学习的变电站巡检机器人自动抄表研究

李大川,杨志明

国网甘肃省电力公司金昌供电公司,金昌 737100

收稿日期:2022-12-07 出版日期:2023-10-28 发布日期:2023-10-25

Research on Automatic Meter Reading for Substation Inspection Robot Based on Deep Learning

LI Dachuan, YANG Zhiming

State Grid Gansu Electric Power Company Jinchang Power Supply Company,Jinchang 737100,China

Received:2022-12-07 Online:2023-10-28 Published:2023-10-25

摘要/Abstract

摘要： 为提高变电站巡检机器人自动抄表识别的精度,提出一种深度学习的自动抄表识别方法。以 YOLOX网络作为基础框架,在网络通道层和空间层添加卷积注意力模块,同时采用 Focal-Loss 函数替代 BCE-Loss 函数,以提高网络的训练速度和识别精度。结果表明, 相较于标准的 YOLOX 网络、 SSD 算法和DenseBox 算法, 改进的YOLOX 网络在 P_avg、P 和 R 指标上表现具有明显优势,分别达 91. 44%,96. 36%和 98. 89%;将改进的 YOLOX 网络用于变电站巡检机器人自动抄表识别中, 实现了智能电表数据的准确识别, 且识别的 P_avg 值达 90. 23%, P 值达93. 56%,R 值达到 98. 12%。变电站巡检机器人的识别方法可用于自动抄表中,且具有一定的工程应用价值。

关键词: 变电站, 巡检机器人, 智能电表识别, 识别精度, YOLOX 网络

Abstract: In order to improve the precision of automatic meter reading recognition of substation inspection robots, an automatic meter reading recognition method of deep learning was proposed. The YOLOX network was taken as the basic framework, the convolutional attention modules were added at the network channel level and space level, and the FocalLoss function was used to replace BCE-Loss function, so as to improve the training speed and recognition accuracy of the network. The results showed that compared with the standard YOLOX network, SSD algorithm and DenseBox algorithm, the improved YOLOX network proposed had obvious advantages in P_avg, P and R, reaching 91. 44%, 96. 36% and 98. 89%.
The improved YOLOX network was used in the automatic meter reading recognition of substation inspection robots, and the accurate recognition of smart meter data was realized, with P_avg value of 90. 23%, P value of 93. 56% and R value of 98. 12%. It can be concluded that the identification method of substation inspection robots can be used for automatic meter reading, which has certain engineering application value.

Key words: substation, inspection robot, smart meter recognition, recognition precision, YOLOX network

李大川, 杨志明. 基于深度学习的变电站巡检机器人自动抄表研究[J]. 微特电机, 2023, 51(10): 58-62.

LI Dachuan, YANG Zhiming. Research on Automatic Meter Reading for Substation Inspection Robot Based on Deep Learning[J]. Small & Special Electrical Machines, 2023, 51(10): 58-62.