微型电脑应用

实时、可靠掌握双地刀隔离开关的防误操作状态是保证电网安全运行的基础。因此，提出双地刀隔离开关新型防误操作装置故障自动化检测系统。所提出的系统的数据采集模块利用特高频传感器采集双地刀隔离开关运行状态数据，网络模块以控制器局域网(CAN)总线为核心，将数据传送至检测模块，该模块完成数据的分布式存储后，利用经验模态分解提取故障特征，依据提取结果，利用长短时记忆(LSTM)网络模型完成双地刀隔离开关的防误操作故障。测试结果显示，所提出的系统能够较好地完成隔离开关运行状态数据采集，各个传输通道的时延结果均在0.1 s以内，拟合度结果均在0.947以上，有效完成对隔离开关防误操作不同类别故障的检测。

Real time and reliable grasp of the anti mis-operation status of the double earth knife isolation switch is the foundation for ensuring the safe operation of the power grid. Therefore, a new type of anti mis-operation device fault automatic detection system for the double earth knife isolation switch is proposed. The data acquisition module of the proposed system uses ultra-high frequency sensors to collect the operating status data of the double earth knife isolation switch. The network module takes the controller area network(CAN) bus as the core and transmits the data to the detection module. After the distributed storage of the data, the module uses empirical mode decomposition to extract fault features. Based on the extraction results, the anti mis-operation fault of the double earth knife isolation switch is completed through a long and short-term memory(LSTM) network model. The test results show that the proposed system can effectively collect the operating status data of the isolation switch, and the delay results of each transmission channel are within 0.1 s, the fitting results are all above 0.947, effectively complete the detection of different types of faults in anti mis-operation of isolation switches.