Research on intelligent substation instrument reading recognition based on deep learning and augmented reality

SUN Rongrong; WANG Chengsi; LUO Yulin; TIAN Songlin; ZHUANG Qiunai; XIA Chengwen

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Research on intelligent substation instrument reading recognition based on deep learning and augmented reality

更新时间：2026-05-21

- Research on intelligent substation instrument reading recognition based on deep learning and augmented reality
- Vol. 63, Issue 5, (2026)
- 作者机构：
  
  1. 深圳供电局有限公司
  2. 南方电网数字平台科技广东有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
SUN Rongrong, WANG Chengsi, LUO Yulin, et al. Research on intelligent substation instrument reading recognition based on deep learning and augmented reality[J]. 2026, 63(5).
DOI：

SUN Rongrong, WANG Chengsi, LUO Yulin, et al. Research on intelligent substation instrument reading recognition based on deep learning and augmented reality[J]. 2026, 63(5). DOI：

摘要

针对现有智能变电站仪表读数识别方法中存在的识别效果不佳和仅能单一识别指针仪表或数字仪表的问题

基于增强现实的电力巡检系统

提出了一种结合改进YOLOv8模型、改进DeepLabV3+模型和改进Transformer模型的智能变电站仪表读数识别方法。改进YOLOv8模型完成仪表分类和区域定位

改进DeepLabV3+模型完成指针式仪表的读取识别

改进Transformer模型完成数字仪表读数识别

通过实验对其性能进行验证。结果表明

改进YOLOv8模型在仪表分类和定位中有效提高了检测精度

检测准确率大于98.00%。改进DeepLabV3+模型在指针式仪表读数识别中有效提高了分割精度

识别误差小于1.50%。改进Transformer模型在数字仪表读数识别中有效提高了识别精度

识别准确率大于97.00%。

Abstract

Addressing the issues of poor recognition performance and the ability to only recognize pointer or digital instruments in existing intelligent substation instrument reading recognition methods

based on the augmented reality power inspection system

a smart substation instrument reading recognition method combining improved YOLOv8 model

improved DeepLabV3+model

and improved Transformer model has been proposed. Improve the YOLOv8 model to complete instrument classification and regional positioning

improve the DeepLabV3+model to complete reading and recognition of pointer instruments

and improve the Transformer model to complete digital instrument reading recognition

verify its performance through experiments. The results indicate that

improved YOLOv8 model effectively improves detection accuracy in instrument classification and positioning

with a detection accuracy rate greater than 98.00%. The improved DeepLabV3+model effectively improves segmentation accuracy in pointer instrument reading recognition

with a recognition error of less than 1.50%. The improved Transformer model effectively improves the recognition accuracy in digital instrument reading recognition

with a recognition accuracy rate greater than 97.00%. which can provide certain assistance for the safe operation of the power grid.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on routing strategy of wireless sensor network in intelligent substation based on improved EEUC algorithm

Fault location of secondary equipment in smart substation based on GRU

Research on clustering routing strategy for wireless sensor networks in intelligent substation based on energy balance

Design and Implementation of a Test System for Smart Substation Intelligence Subsystem Based on IEC104 Protocol

A High-precision Method of Electric Power Calculation for Digital Watt-hour Meters in Intelligent Substation

Related Author

LIU Yuming

CUI Chen

SUN Yanzhi

LI Xu

TIAN Feng

WANG Hongbin

LI Zhi

TONG Xiaoyang

Related Institution

云南电力调度控制中心

重庆合川三峰新能源发电有限公司

西南交通大学电气工程学院

国网重庆市电力公司电力科学研究院

中国电力科学研究院

AI问答

⁰