基于ITD-ELM的发电机转子绕组轻微匝间短路故障诊断  

ITD-ELM-based Fault Diagnosis of Minor Turn-to-turn Short-circuit in Generator Rotor Windings

作　　者：张建峰 岳文亭 李永刚[2] 贺鹏康 侯岳佳 庄克军 ZHANG Jianfeng;YUE Wenting;LI Yonggang;HE Pengkang;HOU Yuejia;ZHUANG Kejun(Liujiaxia Hydropower Plant,State Grid Gansu Electric Power Company,Yongjing 731600,China;School of Electrical and Electronic Engineering,North China Electric Power University,Baoding 071003,China;Lanzhou Power Supply Company,State Grid Gansu Electric Power Company,Lanzhou 730070,China)

机构地区：[1]国家电网甘肃省电力公司刘家峡水电厂,永靖731600 [2]华北电力大学电气与电子工程学院,保定071003 [3]国网甘肃省电力公司兰州供电公司,兰州730070

出　　处：《电力系统及其自动化学报》2023年第4期116-123,共8页Proceedings of the CSU-EPSA

基　　金：国网甘肃省电力公司管理科技项目资助(522721220001水轮发电机组转子绕组匝间短路故障监测、识别、预防装置的开发与应用)。

摘　　要：针对转子绕组匝间短路早期故障不易检测的问题,本文提出一种基于本征时间尺度分解ITD(intrinsic time-scale decomposition)和极限学习机ELM(extreme learning machine)的发电机转子绕组轻微匝间短路故障诊断方法。首先,采用ITD算法将同步发电机的运行数据分解为若干旋转PR(proper rotation)分量,并根据峭度准则进行信号重构;然后将重构后的信号作为输入量,诊断结果作为输出量,构建基于ITD-ELM的发电机匝间短路故障诊断模型;最后以一台型号为MJF-30-6的同步发电机数据为样本,对其轻微匝间短路故障进行诊断,结果表明:基于ITD-ELM模型的故障诊断准确率较单一的ELM模型显著提高,验证了本文所提故障诊断方法的有效性和准确性。Aimed at the problem that the early fault of rotor winding turn-to-turn short-circuit is not easy to detect,a fault diagnosis method for generator rotor winding minor turn-to-turn short-circuit is proposed in this paper,which is based on intrinsic time-scale decomposition(ITD)and extreme learning machine(ELM).First,the operating data of a synchronous generator is decomposed into proper rotation(PR)components using the ITD algorithm,and the signal is reconstructed according to the kurtosis criterion.Then,the reconstructed signal is taken as the input and the diagnosis result as the output,and a fault diagnosis model of generator turn-to-turn short-circuit based on ITD-ELM is construct⁃ed.Finally,the data of an MJF-30-6 synchronous generator is taken as a sample,and its minor turn-to-turn short-cir⁃cuit fault is diagnosed.Results show that the fault diagnosis accuracy based on the ITD-ELM model is significantly high⁃er than that of the single ELM model,which verifies the validity and accuracy of the proposed fault diagnosis method.

关 键 词：同步发电机 本征时间尺度分解 峭度准则 极限学习机 匝间短路 故障诊断 

分 类 号：TM341[电气工程—电机]