基于传感器信息融合的小电流接地选线装置异常检测研究  

Research on Anomaly Detection of Small Current Grounding Line Selection Device Based on Sensor Information Fusion

作　　者：张桂晨 杨正颖 辛威 ZHANG Guichen;YANG Zhengying;XIN Wei(Shangqiu Power Supply Company,State Grid Henan Electric Power Company,Shangqiu 476000,China;Huojia Power Supply Company,State Grid Henan Electric Power Company,Xinxiang 453800,China)

机构地区：[1]国网河南省电力公司商丘供电公司,河南商丘476000 [2]国网河南省电力公司获嘉县供电公司,河南新乡453800

出　　处：《传感器世界》2025年第1期36-41,共6页Sensor World

摘　　要：为了保证小电流接地选线装置的安全稳定运行,提出基于传感器信息融合的小电流接地选线装置异常检测方法。采用传感器技术监测小电流接地选线装置的振动信号,通过等距离重采样处理对原始信号进行预处理。利用经验小波变换(Empirical Wavelet Transform,EWT)对预处理后的信号进行分解,以有效提取其运行特征。将融合后的传感器信息作为分类器的输入,分类器会根据提取的运行特征来评估选线装置当前是处于正常状态还是异常状态,实现小电流接地选线装置异常检测。实验结果显示,所提方法的均方根误差值不超过0.1,平均绝对误差也控制在0.2以内,检测精度高。In order to ensure the safe and stable operation of small current grounding line selection devices,a method for detecting anomalies in small current grounding line selection devices based on sensor information fusion is proposed.Using sensor technology to monitor the vibration signal of the low current grounding line selection device,and preprocessing the original signal through equidistant resampling processing.Using Empirical Wavelet Transform(EWT)to decompose the preprocessed signal and effectively extract its operational features.The fused sensor information is used as input for the classifier,which evaluates whether the line selection device is currently in a normal or abnormal state based on the extracted operating features,achieving abnormal detection of low current grounding line selection devices.The experimental results show that the root mean square error value of the proposed method does not exceed 0.1,and the average absolute error is also controlled within 0.2,indicating high detection accuracy.

关 键 词：传感器信息融合 小电流 接地选线装置 异常检测 等距离重采样 经验小波变换 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]