基于模糊和灰色关联的配电自动化开关柜故障诊断方法  

A fault diagnosis method for distribution automation switch cabinet based on fuzzy and gray correlation

作　　者：韩学森[1] 刘博文 李永杰 于雷[2] 王松[3] 陶诗洋[3] 刘皓璐 HAN Xuesen;LIU Bowen;LI Yongjie;YU Lei;WANG Song;TAO Shiyang;LIU Haolu(Urban Power Supply Company of State Grid Beijing Electric Power Company, Beijing 110102, China;Yizhuang Power Supply Company of State Grid Beijing Electric Power Company, Beijing 102600, China;State Grid Beijing Electric Power Company, Beijing 100031, China;School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China)

机构地区：[1]国网北京市电力公司城区供电公司,北京110102 [2]国网北京市电力公司亦庄供电公司,北京102600 [3]国网北京市电力公司,北京100031 [4]武汉大学电气与自动化学院,湖北武汉430072

出　　处：《电力科学与技术学报》2021年第2期107-115,共9页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(51507114);国网北京市电力公司科技项目(52020218006V)。

摘　　要：针对配电自动化开关柜故障诊断对配电网安全性和可靠性的影响,提出一种基于模糊C均值聚类和灰色关联的配电自动化开关柜故障诊断方法。首先,该方法通过各类遥测信息分层影响因子,计算隶属度函数并采用AHP-熵权法确定权重完成配电自动化开关柜状态评价的分层模糊运算。然后,针对配电自动化开关柜典型故障信息,应用FCM法聚类后灰色关联分析,完成六类配电自动化开关柜典型故障的诊断,在保证诊断准确度的同时极大地减少了计算量。最后,对北京市某地区配电自动化开关柜故障信息的状态评价及故障诊断结果并与传统灰色关联分析对比表明,所提出方法的故障诊断准确度可达90%,为快速、准确、客观地实现对配电自动化开关柜状态的实时监测及智能电网自动化的进一步发展提供参考。This paper proposes a fault diagnosis method for distribution automation switch cabinet based on the Fuzzy C-means(FCM)clustering and gray correlation,aiming at exploring the effect of the distribution automation switch cabinet fault diagnoses on the safety and reliability of distribution networks.Firstly,through various telemetry information,the membership function is calculated,the weight is determined by the AHP-entropy method,and thus the evaluation of hierarchical fuzzy operations of the distribution automation switch cabinet state can be completed.Moreover,according to the typical information of the distribution automation switch cabinet faults,the gray correlation analysis combined with the FCM method are applied to diagnose six common types of fault,which can greatly reduce the calculation complexity and ensure the diagnosis accuracy simultaneously.A case study based on the distribution automation switch cabinet faults in a certain area of Beijing are presented,where the proposed method is compared with the traditional gray correlation analysis.The status evaluation and fault diagnosis results show that the accuracy of the proposed method can reach 90%,which can support the fast,accurate and objective real-time monitoring of distribution automation switch cabinet status and the further development of smart grid automation.

关 键 词：配电自动化开关柜 模糊C均值聚类 灰色关联 故障诊断 

分 类 号：TM56[电气工程—电器]