Topological relation detection technology of substation wiring diagram in electric power system
-
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。
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.
-
Key words:
- substation wiring diagram /
- topological relation /
- deep learning /
- object detection /
- contour tracking
-
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 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 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 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 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 -
[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.htmSHA 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.htmZHANG 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.htmSHEN 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.htmZHANG 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.htmZHOU 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.htmCHEN 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.htmCHEN 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.htmLIAO 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.htmSU 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.htmSONG 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.htmZHANG 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.