基于边缘计算和多传感器融合的输电线路监测研究

Research on Transmission Line Monitoring Based on Edge Computing and Multi-Sensor Fusion

为了提高输电线路运行的安全性,研究设计了一种基于边缘计算和多传感器融合的输电线路监测系统;研究利用多种传感器采集数据,采用Edge X Foundry平台作为系统构架,对数据进行处理,从而通过边缘计算实现低延迟、高可靠性的实时监测、在线查看现场、无线通讯等功能;实验结果显示,优化后的ARIMA模型的最小MAE为0.476,最小MSE为0.623,最大R^(2)为0.984;监测系统在白天和夜晚对线路舞动的最高预警准确率分别达到了97.1%和93.5%,说明设计的监测系统对导线舞动的预警性能具有显著的准确性和可靠性,为输电线路的安全运行提供了实践依据。

In order to improve the security and efficiency of transmission line operation,a transmission line monitoring system based on edge computing and multi-sensor fusion is designed;The designed system uses a variety of sensors to collect data,the Edge X Foundry edge platform is taken as a system framework to process the data,thus the real-time monitoring,online viewing of the scene,wireless communication and other functions are realized trough the edge computing of the collected data.The experimental results show that the optimized auto regressive integrated moving average(ARIMA)model has a minimum mean absolute err(MAE)of 0.476,minimum nean-square error(MSE)of 0.623,and maximum coefficient of determinination(R^(2))of 0.984;The highest warning accuracy of the monitoring system for line galloping during the day and night reached 97.1%and 93.5%,respectively,indicating that the designed monitoring system has a significant accuracy and reliability in warning wire galloping,and it provides a practical basis for the safe operation of transmission lines.