基于多源传感器数据融合的断路器故障诊断方法  

Fault Diagnosis Method of Circuit Breaker Based on Multi-source Sensor Data Fusion

作　　者：张国宝 王朝廷 黄伟民 杨为 袁欢[2] 王小华[2] ZHANG Guobao;WANG Chaoting;HUANG Weimin;YANG Wei;YUAN Huan;WANG Xiaohua(Power Research Institute of State Grid Anhui Electric Power Co.,Ltd.,Hefei 230601,China;School of Electrical Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]国网安徽省电力有限公司电力科学研究院,合肥230601 [2]西安交通大学电气工程学院,西安710049

出　　处：《高电压技术》2025年第2期660-668,共9页High Voltage Engineering

基　　金：国家重点研发计划(2022YFB2403400)。

摘　　要：为解决单源传感器故障诊断可识别故障种类少、诊断精度低的问题,该文利用电流与振动传感器数据,提出了一种基于前向搜索(sequential forward selection,SFS)的模糊C均值(fuzzy C-means,FCM)聚类多源特征筛选融合方法,该方法通过调整兰德指数(adjusted rand index,ARI)来衡量聚类效果,对提取出的多源传感器特征进行筛选融合得到最优特征集。在此基础上,模拟了9种断路器故障,将其划分为3类,采用支持向量机(support vector machine,SVM)分别对单源传感器特征和多源融合特征进行分类,以验证该文提出方法的有效性,并通过其他3种常见分类器进行了对比试验。结果表明:多源融合特征识别准确率明显高于单源特征,在3类故障中分别达到95.0%、92.5%、96.5%,且在多种分类器下均能得到相似结果,兼具有效性和普适性,该文方法为多源传感器背景下的断路器故障诊断提供了新思路。To solve the problems of few identifiable fault types and low diagnosis accuracy of single-source sensor fault diagnosis,by utilizing current and vibration sensor data,we proposed a multi-source feature selection and fusion method based on the sequential forward selection(SFS)and fuzzy C-means(FCM)clustering.This method evaluates the cluster-ing performance by adjusting the Adjusted Rand Index(ARI),and selects and fuses the extracted multi-source sensor features to obtain the optimal feature set.Based on this,nine types of circuit breaker faults are simulated and divided into three classes.Support vector machine(SVM)is used to classify the single-source sensor features and the multi-source fu-sion features separately so as to verify the effectiveness of the proposed method.Moreover,three other common classifiers are used for comparison experiments.The results show that the multi-source fusion features have significantly higher recognition accuracy than the single-source features,reaching 95.0%,92.5%,and 96.5%,respectively,in the three classes of faults,and they can achieve similar results under multiple classifiers,which is effective and universal.The pro-posed method provides a new approach for circuit breaker fault diagnosis in the context of multi-source sensors.

关 键 词：断路器 多源传感器 数据融合 特征筛选 模糊C均值聚类 故障诊断 

分 类 号：TM5[电气工程—电器]