基于变电站视频图像的变压器冷却风机运行状态识别方法研究  

Research on Identification Method for Operating Condition of Transformer Cooling Fan Based on Video Image of Substation

作　　者：汶爱文 王印松[1] 常政威[2] 

机构地区：[1]华北电力大学,河北保定071003 [2]国网四川省电力公司电力科学研究院,四川成都610072

出　　处：《四川电力技术》2015年第1期9-13,共5页Sichuan Electric Power Technology

基　　金：国网四川省电力公司研究开发项目(52199713506h)

摘　　要：基于OpenCV2图像处理技术,提出了两种针对变压器冷却风机转动情况判断的方案:1连通区域质心分析法:结合阈值算法和分水岭算法得到感兴趣区域的连通区域,并求其质心,通过分析质心位置的变化情况判断风机转动与否;2直方图统计分析法:通过求取图像直方图信息判断风机转动与否。实验结果和实验相关数据的分析验证了两种方案的可行性和实用性。Two schemes are proposed which are the judgments about the rotation of transformer cooling fan based on OpenCV2 image processing technology. One is centroid analysis of connected region： combined with threshold algorithm and watershed algorithm, the interested connected region is obtained to get its eentroid, and then the changes of centroid＇s position are ana- lyzed to judge whether the fan rotates or not. The other one is histogram statistical analysis ： through calculating the histogram information of images, it is determined whether the fan rotates or not. The experiment results show that the proposed two schemes are feasible and practical.

关 键 词：OpenCV2 连通区域 质心 直方图 

分 类 号：TM85[电气工程—高电压与绝缘技术]