电力系统厂站接线图拓扑关系检测技术

李昊; 管荑; 王杉; 石玮; 刘子鑫; 刘晓川

doi:10.13700/j.bh.1001-5965.2020.0476

电力系统厂站接线图拓扑关系检测技术

doi: 10.13700/j.bh.1001-5965.2020.0476

李昊^1, ,,
管荑²,
王杉¹,
石玮¹,
刘子鑫³,
刘晓川³

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

基金项目:

国网山东省电力公司科技项目 5206021900TW

详细信息

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

通讯作者:
李昊, E-mail: lihao-0717@163.com

中图分类号: TP399;TM734
计量
- 文章访问数: 786
- HTML全文浏览量: 230
- PDF下载量: 108
- 被引次数: 0
出版历程
- 收稿日期: 2020-08-31
- 录用日期: 2020-09-05
- 网络出版日期: 2021-03-20

Topological relation detection technology of substation wiring diagram in electric power system

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

Funds:

Science and Technology Project of State Grid Shandong Electric Power Company 5206021900TW

More Information

Corresponding author: LI Hao, E-mail: lihao-0717@163.com

摘要

摘要:
厂站接线图中电气元件的拓扑关系是厂站接线图自动生成技术所需的核心数据。目前，已知的厂站接线图自动生成技术仍然依靠人工获取图中的拓扑关系。通过利用基于深度学习的目标检测技术与传统的计算机图像处理技术相结合的方式，能够实现厂站接线图拓扑关系检测。首先，利用基于深度学习的目标检测方法对电气元件进行识别，并利用计算机图像处理技术对标量格式接线图进行预处理，完成电气元件与连接线的分割。然后，利用轮廓跟踪算法对连接线连通区域进行检测标记。最后，根据获取的电气元件信息与连接线信息获取图纸的拓扑关系。采用国家电网有限公司提供的数据集，并设计了对比实验，验证了所提方法的有效性。
- 厂站接线图 /
- 拓扑关系 /
- 深度学习 /
- 目标检测 /
- 轮廓跟踪
Abstract:
Topological relation of electrical components is the core-data required by substation wiring diagram automatic generation technology. At present, known technologies still rely much on artificial access to topological relations. By the combination of deep learning based object detection technology and traditional computer image processing technology, topological relation can be detected automatically. Firstly, to segment the electrical components and connection lines, deep learning based object detection technology was used to identify the electrical components, and the image processing technology was used to preprocess the scalar-format wiring diagram of power plants. Secondly, a contour tracking algorithm was adopted to detect and mark the connected area of the connection lines. Finally, the topological relation of the drawing was acquired according to the obtained information of electrical components and connection lines. Comparative experiments based on a dataset released by the State Grid Corporation of China indicate the effectiveness of the proposed method.
- substation wiring diagram /
- topological relation /
- deep learning /
- object detection /
- contour tracking

HTML全文

图 1 标量格式接线图示例

Figure 1. An example of scalar-format wiring diagram

下载: 全尺寸图片幻灯片

图 2 厂站接线图拓扑关系检测流程

Figure 2. Flowchart of topological relation detection of substation wiring diagram

下载: 全尺寸图片幻灯片

图 3 图像二值化

Figure 3. Image binarization

下载: 全尺寸图片幻灯片

图 4 去除图元

Figure 4. Removing graphics

下载: 全尺寸图片幻灯片

图 5 保护处理

Figure 5. Protection processing

下载: 全尺寸图片幻灯片

图 6 分割前后各类元件的平均精度

Figure 6. Average precision of various components before and after segmentation

下载: 全尺寸图片幻灯片

表 1 拓扑关系检测结果

Table 1. Results of topological relation detection

设备名称	x坐标	y坐标	电压等级/kV	链接点号
刀闸_25	1 298	1416	35	54, 68
刀闸_10	1 273	182	35	9, 12
变压器_2	2 010	1 168	35	74, 76
避雷器_10	1 891	1 496	35	43, 51
避雷器_5	873	1 806	35	23, 31
熔断器_4	297	2 155	35	18, 25
电容_2	297	2 197	35	15, 18
电容_3	356	2 198	35	15, 16

下载: 导出CSV

表 2 青岛市区县变电站接线图数据集

Table 2. Wiring diagram dataset of district and county substation in Qingdao

元件类别	数目
断路器	344
接地刀闸	1 093
电抗	208
刀闸	1 258
变压器	144
避雷器	829
母线	275
手车开关	991
隔离手车	308
所变	172
电力电感器	205
电容	974

下载: 导出CSV

表 3 分割前后目标检测平均精度均值

Table 3. Mean average precision of object detection before and after segmentation

分割前后	mAP/%
分割前	62.91
分割后	84.37

下载: 导出CSV

表 4 分割前后拓扑关系检测结果对比

Table 4. Comparison of topological relation detection results before and after segmentation

分割前后	Precision/%	Recall/%	F1-score/%
分割前	81.27	74.09	77.41
分割后	85.02	85.86	85.42

下载: 导出CSV

表 5 预处理前后拓扑关系检测结果对比

Table 5. Comparison of topological relation detection results before and after preprocessing

有/无预处理	Precision/%	Recall/%	F1-score/%
无预处理	35.92	1.64	3.11
有预处理	85.02	85.86	85.42

下载: 导出CSV

参考文献(16)

[1]	W3C. Scalable vector graphics(SVG) 1.2 specification[EB/OL]. (2004-10-27)[2020-08-01]. http://www.w3.org/TR/2004/WD-SVG12-20041027.
[2]	沙树名, 林峰. 一种基于CIM的厂站接线图自动生成技术[J]. 电力系统自动化, 2008, 32(21): 68-71. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT200821014.htm SHA S M, LIN F. A technique of automatic generation of substation wiring diagram based on CIM[J]. Automation of Electric Power Systems, 2008, 32(21): 68-71(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT200821014.htm
[3]	章坚民, 叶义, 徐冠华. 变电站单线图模数图一致性设计与自动成图[J]. 电力系统自动化, 2013, 37(9): 84-91. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201309015.htm ZHANG J M, YE Y, XU G H. Consistency design and automatic mapping of single line diagram modulus diagram of substation[J]. Automation of Electric Power Systems, 2013, 37(9): 84-91(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201309015.htm
[4]	沈伟, 吴文传, 张伯明, 等. 能量管理系统中电网潮流单线图自动生成算法[J]. 电力系统自动化, 2010, 34(6): 48-53. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201006012.htm SHEN W, WU W C, ZHANG B M, et al. A power grid one-line diagram automatic generation method in the EMS[J]. Automation of Electric Power Systems, 2010, 34(6): 48-53(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201006012.htm
[5]	章坚民, 叶琳, 孙维真, 等. 基于地理相对位置的省级输电网均匀接线图自动生成[J]. 电力系统自动化, 2010, 34(24): 55-59. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201024011.htm ZHANG J M, YE L, SUN W Z, et al. Automatic generation of the uniformly-distributed provincial transmission power grid diagram based on relative geographical location information[J]. Automation of Electric Power Systems, 2010, 34(24): 55-59(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201024011.htm
[6]	周博曦, 孟昭勇, 王志臣, 等. 基于CIM的变电站与配电馈线一次接线图自动绘制算法[J]. 电力系统自动化, 2012, 36(11): 77-81. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201211015.htm ZHOU B X, MENG Z Y, WANG Z C, et al. Automatic graphing algorithm for primary electric wiring diagram of substation and distribution feeder based on CIM[J]. Automation of Electric Power Systems, 2012, 36(11): 77-81(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201211015.htm
[7]	陈连杰, 赵仰东, 韩韬, 等. 基于层次结构及模型驱动的配电网图形自动生成[J]. 电力系统自动化, 2015, 39(1): 226-232. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201501039.htm CHEN L J, ZHAO Y D, HAN T, et al. Hierarchically structured and model driven automatic generation of distribution network graphs[J]. Automation of Electric Power Systems, 2015, 39(1): 226-232(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201501039.htm
[8]	陈璐, 陈连杰, 欧阳文, 等. 基于环形结构的配电网联络图布局算法[J]. 电力系统自动化, 2016, 40(24): 151-156. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201624022.htm CHEN L, CHEN L J, OUYANG W, et al. Ring structure based layout algorithm for distribution network contact graph[J]. Automation of Electric Power Systems, 2016, 40(24): 151-156(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201624022.htm
[9]	廖凡钦, 刘东, 闫红漫, 等. 基于拓扑分层的配电网电气接线图自动生成算法[J]. 电力系统自动化, 2014, 38(13): 174-181. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201413028.htm LIAO F Q, LIU D, YAN H M, et al. An automatic electrical diagram generation method for distribution networks based on hierarchical topology model[J]. Automation of Electric Power Systems, 2014, 38(13): 174-181(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT201413028.htm
[10]	苏运光, 罗俊, 熊浩, 等. 基于存量图形拓扑分析的厂站接线图自动生成[J]. 电力系统自动化, 2020, 44(3): 162-168. https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT202003020.htm SU Y G, LUO J, XIONG H, et al. Automatic generation of substation wiring graph based on inventory graph topology analysis[J]. Automation of Electric Power Systems, 2020, 44(3): 162-168(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-DLXT202003020.htm
[11]	宋晓宇, 王永会, 栾方军. 基于动态跟踪步长的直线快速矢量化算法[J]. 计算机工程与应用, 2002, 38(2): 92-93. https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG200202031.htm SONG X Y, WANG Y H, LUAN F J. Straight lines vector algorithm based on dynamic trace step[J]. Computer Engineering and Applications, 2002, 38(2): 92-93(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG200202031.htm
[12]	CHANG F, LUY C, PAVLIDIS T. Feature analysis using line sweep thinning algorithm[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(2): 145-158. http://ieeexplore.ieee.org/document/748823
[13]	SONG J Q, SU F, TAI C L, et al. An object-oriented progressive-simplification-based vectorization system for engineering drawing: Model, algorithm, and performance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(8): 1048-1060. doi: 10.1109/TPAMI.2002.1023802
[14]	张琪, 叶颖. 基于对象图例及其拓扑关系识别的二维工程CAD图纸矢量化方法[J]. 计算机与现代化, 2018(11): 40-45. https://www.cnki.com.cn/Article/CJFDTOTAL-JYXH201811010.htm ZHANG Q, YE Y. 2D engineering CAD drawings vectorization method based on recognition of object legends and their topology[J]. Computer and Modernization, 2018(11): 40-45(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JYXH201811010.htm
[15]	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. doi: 10.1109/TPAMI.2016.2577031
[16]	PRATTW K, ADAMS J E. Digital image processing[J]. Journal of Electronic Imaging, 2007, 16(2): 131-145.