图像特征提取与识别技术保护压板状态监测

Image Feature Extraction and Recognition Technology State Monitoring of Protection Plate

变电站自动化水平极大提升了电网运行效率和安全性.压板是用来投入或退出对应保护功能的,继电保护装置的压板管理需要保护管理指定人员、保护试验人员、运行操作人员三方面共同负责.从保护功能来看,它是保护跳闸的最后一道屏障.文章研究了一种利用计算机深度学习算法实现电力保护压板状态识别的装置,本装置利用深度学习的算法实现图像的特征提取、分割分类与识别,实现保护压板状态的监测,并将监测的结果发送到远端云数据.

The level of substation automation greatly improves the effi ciency and safety of power grid operation.The pressing plate is used to input or exit the corresponding protection function.The pressing plate management of the relay protection device needs the joint responsibility of the protection management designated personnel,protection test personnel and operation personnel.In terms of protection function,it is the last barrier for protection tripping.In this paper,we study a kind of device to realize the state recognition of power protection strap by using the computer deep learning algorithm.In this device,we use the algorithm of deep learning to realize the feature extraction,segmentation,classifi cation and recognition of the image to realize the state monitoring of protection strap,and send the monitoring results to the remote cloud data.