基于DST的调相机转子轻微匝间短路故障诊断  

Diagnosis of Slight Inter‑turn Short‑Circuit Fault of Synchronous Condenser Based on DST

作　　者：张玉良 马宏忠[1] 蒋梦瑶 蔚超 林元棣 ZHANG Yuliang;MA Hongzhong;JIANG Mengyao;WEI Chao;LIN Yuandi(College of Energy and Electrical Engineering,Hohai University Nanjing,211100,China;State Grid Jiangsu Electric Power Co.,Ltd.Research Institute Nanjing,211103,China;Xuzhou Heavy Machinery Co.,Ltd.Xuzhou,221000,China)

机构地区：[1]河海大学能源与电气学院,南京211100 [2]国网江苏省电力有限公司电力科学研究院,南京211103 [3]徐州重型机械有限公司,徐州221000

出　　处：《振动．测试与诊断》2023年第2期355-362,413,共9页Journal of Vibration,Measurement & Diagnosis

基　　金：国网江苏省电力公司科技资助项目(J2019114);111引智计划资助项目(B14022);国家自然科学基金资助项目(51577050)。

摘　　要：转子绕组匝间短路故障是调相机的一种常见故障,一旦出现就会直接影响调相机在系统中的无功输出。由于调相机在运行过程中时常要对无功功率进行调节,仅用单独的特征量难以准确地对故障进行诊断,极易出现误判。针对此问题,提出一种基于DS证据理论(DS evidence theory,简称DST)的调相机转子轻微匝间短路故障的诊断方法,综合利用振动信号和励磁电流中的感应谐波对故障进行诊断。首先,通过随机森林计算单独特征量下的故障概率;其次,通过DST的组合规则将二者的结果进行综合诊断;最后,通过实验进行验证。实验结果表明,该方法诊断的正确率均高于单独特征量的诊断,可以有效提高调相机转子轻微匝间短路故障识别的准确性。Inter-turn short-circuit fault of rotor winding is a common fault of synchronous condenser,and once it appears,it will directly affect the reactive power output of the synchronous condenser in the system.Since the synchronous condenser often needs to adjust the reactive power in the process of operation,it is difficult to accurately diagnose the fault with only a single characteristic quantity,so it is easy to misjudge.In this paper,a diagnosis method based on DS evidence theory(DST)for slight inter-turn short-circuit fault of synchronous condenser is presented.In the diagnosis,the fault probability under the single feature quantity is firstly calculated by random forest,and then the results of the two are synthetically diagnosed by the combined rule of DST.Finally,it is verified by experiment.The experimental results show that the accuracy of the method is higher than that of the single feature,and it can effectively improve the identification accuracy of the slight inter-turn short-circuit fault of the synchronous condenser.

关 键 词：调相机 转子匝间短路 振动分析 随机森林 DS证据理论 故障诊断 

分 类 号：TM342[电气工程—电机]