| 引用本文: | 付文龙,谭佳文,吴喜春,陈铁,胡文斌,钟浩.基于图像处理与形态特征分析的智能变电站保护压板状态识别[J].电力自动化设备,2019,39(7): |
| FU Wenlong,TAN Jiawen,WU Xichun,CHEN Tie,HU Wenbin,ZHONG Hao.Protection platen status recognition based on image processing and morphological feature analysis for smart substation[J].Electric Power Automation Equipment,2019,39(7): |
|
| 本文已被：浏览 4225次 下载 2003次 |
|
|
|
| 基于图像处理与形态特征分析的智能变电站保护压板状态识别 |
|
付文龙1,2, 谭佳文1,2, 吴喜春3, 陈铁1,2, 胡文斌1,2, 钟浩1,2
|
|
1.三峡大学 电气与新能源学院，湖北 宜昌 443002;2.三峡大学 梯级水电站运行与控制湖北省重点实验室，湖北 宜昌 443002;3.国网湖北省电力有限公司 宜昌供电公司，湖北 宜昌 443000
|
|
| 摘要: |
| 针对目前变电站二次保护压板仍多由人工进行位置读取和核对操作，存在误操作风险且制约着智能化水平提升的问题，提出了一种基于图像处理与形态特征分析的智能变电站保护压板状态识别方法。该方法首先对移动终端采集到的屏柜图像进行图像处理，将其转化为包含有效压板区域和背景干扰区域的二值图，进而采用8连通的方式进行连通区域提取并对所有区域进行形态特征分析，再依据形态特征从中提取出有效压板区域，最后依据有效压板区域方向角确定压板投退状态，同时结合各区域的重心确定屏柜上的有效压板顺序，进而得到表征屏柜压板投退状态的标识序列。不同场景和分辨率下的保护压板状态识别实例结果表明，所提方法具有较好的适用性。 |
| 关键词: 智能变电站 保护压板 图像处理 二值图 形态特征分析 投退状态 |
| DOI：10.16081/j.issn.1006-6047.2019.07.030 |
| 分类号:TM732;TM764 |
| 基金项目:国家自然科学基金资助项目(51741907)；梯级水电站运行与控制湖北省重点实验室开放基金资助项目(2017KJX06)；湖北省技术创新重大专项(2017AAA132)；宜昌市科技局应用基础研究项目(A17-302-a12) |
|
| Protection platen status recognition based on image processing and morphological feature analysis for smart substation |
|
FU Wenlong1,2, TAN Jiawen1,2, WU Xichun3, CHEN Tie1,2, HU Wenbin1,2, ZHONG Hao1,2
|
|
1.College of Electrical Engineering & New Energy, China Three Gorges University, Yichang 443002, China;2.Hubei Key Laboratory of Cascaded Hydropower Stations Operation & Control, China Three Gorges University, Yichang 443002, China;3.Yichang Power Supply Company, State Grid Hubei Electric Power Co.,Ltd.,Yichang 443000, China
|
| Abstract: |
| In order to solve the problem that secondary protection platen in substations is still mainly read and checked manually, which has the risk of misoperation and restricts the improvement of intelligent level, a novel re-cognition method of protection platen based on image processing and morphological feature analysis for smart substation is proposed. In this method, the cabinet image collected by mobile terminal is first processed and converted into a binary image containing valid platen regions and background interference regions. Then extraction of connected regions is achieved through eight-connection pattern and the morphological features of all regions are analyzed, according to which the valid platen regions are extracted. Finally, the platen’s on/off state is determined based on the direction angle of the valid platen region respectively. Meanwhile, the order of valid platens on the cabinet is determined according to the center of gravity in each region, thus the identification sequence indicating the on/off state of the platens on the cabinet is obtained. The results of different collected image scenes and resolutions show that the proposed method possesses better applicability. |
| Key words: smart substations protection platen image processing binary image morphological feature analysis on/off state |
