北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (3): 539-548.doi: 10.13700/j.bh.1001-5965.2020.0478

• 论文 • 上一篇    下一篇

基于深度学习和图匹配的接线图检测与校核

李昊1, 王杉1, 耿玉杰2, 王黎1, 孙文昌3, 苗纯源3   

  1. 1. 国网山东省电力公司青岛供电公司 电力调度控制中心, 青岛 266002;
    2. 国网山东省电力公司 电力调度控制中心, 济南 250001;
    3. 山东大学(青岛) 计算机科学与技术学院, 青岛 266237
  • 收稿日期:2020-08-31 发布日期:2021-04-08
  • 通讯作者: 李昊 E-mail:lihao-0717@163.com
  • 作者简介:李昊,男,硕士,工程师。主要研究方向:电力调度自动化;王杉,男,技师。主要研究方向:电力调度自动化;耿玉杰,男,硕士,高级工程师。主要研究方向:电力调度自动化;王黎,女,硕士,高级工程师。主要研究方向:电力调度自动化与继电保护;孙文昌,男,硕士研究生。主要研究方向:计算机视觉;苗纯源,男,硕士研究生。主要研究方向:计算机视觉。
  • 基金资助:
    国网山东省电力公司科技项目(5206021900TW)

Wiring diagram detection and check based on deep learning and graph matching

LI Hao1, WANG Shan1, GENG Yujie2, WANG Li1, SUN Wenchang3, MIAO Chunyuan3   

  1. 1. Electric Power Dispatching & Control Center, State Grid Qingdao Power Supply Company, Qingdao 266002, China;
    2. Electric Power Dispatching & Control Center, State Grid Shandong Electric Power Company, Jinan 250001, China;
    3. School of Computer Science and Technology, Shandong University(Qingdao), Qingdao 266237, China
  • Received:2020-08-31 Published:2021-04-08
  • Supported by:
    Science and Technology Project of State Grid Shandong Electric Power Company (5206021900TW)

摘要: 传统的厂站一次接线图的绘制和管理主要依靠电网运行人员,费时费力且缺乏科学可校核的参考标准。提出了一种基于深度神经网络和数字图像处理相结合的厂站一次接线图的自动检测、识别和校核算法。首先,使用目标检测Faster R-CNN模型检测厂站接线图中的电器元件,并达到92%的检测准确率,同时使用端到端的文字检测识别模型识别厂站接线图中的文字信息,并达到94.2%的文字检测准确率和92%的文字识别准确率;然后,使用数字图像处理技术进行厂站接线图连接线、拓扑关系识别;最后,使用改进的VF2算法进行厂站一次接线图和人工维护的厂站一次接线图拓扑关系匹配校核,将拓扑数据抽象为无向图,通过轮廓序号得到元件的相对位置信息,根据改进的VF2算法得到2张图的匹配率,并通过匹配率与设定好的阈值来帮助核验,相比于节点遍历的匹配方法,核验准确率提高了37.5%。基于某供电公司提供的部分变电站的厂站一次接线图标注了接线图电器元件,贡献了一个小型接线图数据集。

关键词: 厂站一次接线图, 拓扑关系匹配, 自动生成, 自动校核, 深度学习, 数字图像处理

Abstract: The drawing and management of the traditional primary wiring diagram of plant and station mainly depend on the operators of power grid, which wastes time and labor and lacks scientific and verifiable reference standards. Towards this problem, based on the deep neural networks and digital image processing, we propose an algorithm for automatic detection, recognition and verification. Specifically, Faster R-CNN is first adopted to detect the electrical components of wiring diagram with 92% detection accuracy. In the meantime, an end-to-end text detection and recognition model is used to recognize the text with 94.2% detection accuracy and 92% character recognition accuracy. Then we take advantage of digital image processing technique to identify the connection of wiring diagram and topological relation. Finally, improved graph matching algorithm VF2 is used to check the difference between the electronic and manually maintained diagrams. The topological data is abstracted into an undirected graph, and the relative position information of components is obtained through the outline number. Based on the improved VF2 algorithm, we can compute the matching rate of two graphs to help the verification. Compared with the matching method of node traversal, the verification accuracy can be improved by 37.5%. Based on the first wiring diagram of some substations provided by a power supply company, this paper marks the electrical components of wiring diagram and contributes a small wiring diagram dataset.

Key words: primary wiring diagram of plant and station, topological relation matching, automatic generation, automatic check, deep learning, digital image processing

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发