摘要
随着视频分析识别技术和数据处理方法的不断成熟,其在电力行业监控领域正在逐步应用推广,结合变电站视频数据应用特色,本文搭建了一套基于视频图像技术的变电站智能化应用系统.该系统采用B/S架构,客户端WEB界面智能化应用请求,通过ICE中间件实现信令和数据交互,总线服务程序根据不同应用请求分发数据,各专项服务程序根据数据消息进行分析判定,最终实现智能化应用功能.系统主要具有以下几个特色:用于辅助变电站综自系统的刀闸状态视频校核;协助在线监测装置故障数据分析结果的视频图像遥视联动功能;变电站现场作业人员违章安全监管预警.应用表明:本系统方案能够很好地提升变电站智能化应用水平.
As the video analysis technology and data processing methods getting more and more mature,its application in monitoring of electric power industry is gradually improving.Combining with electrical characteristics,a set of substation intelligent system based on video image technology was built.This system adopts B/S architecture.Firstly,client WEB interface intelligentize application request and signaling and data interaction is realized by ICE middleware;secondly,bus service program distribute data according to different application requirements,then each special service program analyzes and determines according to the data message.Finally,intelligent application system function is realized.The system has the following characteristics:auxiliary breaker status video checking of transformer substation,on-line monitoring device failure data analysis results linkage function,early warning for laws-violation operator in substation.Application shows that this system can enhance the Intelligent level of substation.
引文
[1]张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报,2017,43(8):1289-1305.Zhang Hui,Wang Kunfeng,Wang Feiyue.Advances and perspectives on applications of deep learning in visual object detection[J].Acta Automatica Sinica,2017,43(8):1289-1305(in Chinese)
[2]王向东,张丽红.基于动静态特征结合的改进模糊支持向量机行为识别[J].测试技术学报,2017,31(2):125-130.Wang Xiangdong,Zhang Lihong.Behavior recognition base on improved FSVM employing dynamic and static characteristics[J].Journal of Test and Measurement Technology,2017,31(2):125-130.(in Chinese)
[3]徐勤军,吴镇扬.视频序列中的行为识别研究进展[J].电子测量与仪器学报,2014(4):343-351.Xu Qinjun,Wu Zhenyang.Research progress on activity recognition in video[J].Journal of Electronic Measurement and Instrumentation,2014(4):343-351.(in Chinese)
[4]郭玉杰.基于视频的目标感知与行为识别[D].太原:中北大学,2014.
[5]唐超,王文剑,李伟,等.基于多学习器协同训练模型的人体行为识别方法[J].软件学报,2015,26(11):2939-2950.Tang Chao,Wang Wenjian,Li Wei,et al.Multi-learner co-training model for Human action recognition[J].Journal of Software,2015,26(11):2939-2950.(in Chinese)
[6]沈海平,姚楠,黄薛凌.基于智能视觉的变电站设备状态智能巡视[J].现代电子技术,2017,40(9):169-172.Shen Haiping,Yao Nan,Huang Xueling.Substation equipment state intelligent patrol based on intelligent vision[J].Modern Electronics Technique,2017,40(9):169-172.(in Chinese)
[7]赵义奎,李惠民,王乐挺,等.ICE在配网自动化主站中的应用[J].电力系统保护与控制,2014,42(1):102-107.Zhao Yikui,Li Huimin,Wang Leting,et al.Application of ICE in the master station of distribution automation[J].Power System Protection and Control,2014,42(1):102-107.(in Chinese)