基于轴电压信号时频变换和深度残差收缩网络的同步发电机缺陷识别

Abstract
Figure/Table
References
Related Citation (13)

Download: PDF (9207 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract During the operation of a synchronous generator, the shaft voltage signal on the shaft system can, to some extent, reflect the equipment’s operating condition. This paper proposes a defect identification method for synchronous generators using the shaft voltage signal as a feature signal, based on time-frequency transformation and a deep residual shrinkage network (DRSN). First, defect simulation experiments are conducted on a three-phase synchronous generator, where shaft voltage signals under normal conditions and three typical defects including rotor eccentricity, inter-turn short circuit, and electrostatic induction are acquired using an data acquisition card. Second, two time-frequency transforms, namely Mel spectrogram transform and synchrosqueezing transform, are respectively employed to construct datasets, and a deep residual shrinkage network is used to build a feature extractor. Finally, a full connected layer is adopted to classify the spectral features. The results show that the Mel-DRSN model achieves a classification accuracy of 99.05% for generator defects, outputing other compared models. The proposed method provides an effective aproach for defect identification in three-phase synchronous generators.

Key words： synchronous generator shaft voltage time-frequency transformation deep residual shrinkage network (DRSN)

Received: 20 November 2025

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Xinmin
	CHANG Ye
	ZHU Jianbin
	CHEN Hongchang

Cite this article:

ZHANG Xinmin,CHANG Ye,ZHU Jianbin等. Defect identification in synchronous generators based on time-frequency transformation of shaft voltage signals and deep residual shrinkage network[J]. Electrical Engineering, 2026, 27(9): 21-27.

URL:

https://dqjs.cesmedia.cn/EN/Y2026/V27/I9/21

[1] 税航伟, 刘红蕾, 张茂振, 等. 静止励磁汽轮发电机轴电压的形成和预防[J]. 电机技术, 2014(4): 56-59.
[2] 刘欢, 钱厚军, 陈子明, 等. 发电机轴电压的测量与判定[J]. 科技视界, 2022, 12(8): 40-42.
[3] 王晓华, 李永刚, 武玉才. 汽轮发电机轴电压的分析[J]. 电力科学与工程, 2009, 25(11): 73-76.
[4] 李勇, 刘侃. 发电机轴电压的形成与测量方法[J]. 工业仪表与自动化装置, 2010(1): 90-91.
[5] 史德利, 顾守录, 王英志, 等. 汽轮发电机轴电压轴电流在线监测装置的研制[J]. 大电机技术, 2016(4): 15-18.
[6] 孙昊, 王宏华, 陈凌, 等. 大型汽轮发电机静态励磁产生的轴电压及其抑制策略仿真研究[J]. 机械制造与自动化, 2015, 44(2): 164-167.
[7] 韩小地, 徐荣鹏, 李伟, 等. 双馈式风力发电机的轴电流分析及防范措施研究[J]. 中国设备工程, 2021(15): 182-184.
[8] 李知浩, 刘瑞芳, 张亮亮, 等. 绝缘轴承对变频电机高频轴电流的抑制机理与效果[J]. 电工技术学报, 2024, 39(4): 1046-1058.
[9] 李毅, 张文斌, 李洲, 等. 静止励磁轴电压滤波回路对发电机转子接地保护装置的影响[J]. 华电技术, 2015, 37(12): 7-9, 14.
[10] 伏翥, 高启尧. 静态励磁系统轴电压滤波器的分析[J]. 集成电路应用, 2021, 38(1): 20-21.
[11] 金媛媛, 刘灵君. 汽轮发电机轴电压分析与安全运行[J]. 电机技术, 2019(4): 20-23, 28.
[12] 姜彤, 周春阳, 徐永金, 等. 汽轮发电机中静止励磁轴电压的分析与抑制[J]. 电力系统保护与控制, 2012, 40(6): 142-146.
[13] 武玉才, 李永刚, 李和明. 基于轴电压的隐极同步发电机转子典型故障诊断[J]. 电工技术学报, 2010, 25(6): 178-184.
[14] 李和明, 武玉才, 李永刚. 转子绕组匝间短路对电机轴电压的影响[J]. 中国电机工程学报, 2009, 29(36): 96-100.
[15] 李剑立, 武玉才, 卢伟甫. 水轮发电机机电故障的轴电压特征分析及诊断[J]. 电机与控制学报, 2023, 27(9): 10-18.
[16] 马立玲, 刘潇然, 沈伟, 等. 基于一种改进的一维卷积神经网络电机故障诊断方法[J]. 北京理工大学学报, 2020, 40(10): 1088-1093.
[17] 曹景胜, 于洋, 王琦, 等. 基于优化VMD-CNN- BiLSTM的电机轴承智能故障诊断研究[J]. 现代电子技术, 2024, 47(12): 115-121.
[18] 谢锋云, 王阳, 孙恩广, 等. 基于GMFDE与Singer- ELM的三相异步电机故障诊断[J]. 铁道科学与工程学报, 2024, 21(10): 4357-4369.
[19] 周凯, 王晓东, 王刚, 等. 基于注意力机制的永磁同步风电机组早期匝间短路故障诊断方法[J]. 电器与能效管理技术, 2023(6): 1-8.
[20] 张建峰, 岳文亭, 李永刚, 等. 基于ITD-ELM的发电机转子绕组轻微匝间短路故障诊断[J]. 电力系统及其自动化学报, 2023, 35(4): 116-123.
[21] 马明晗, 侯岳佳, 李永刚, 等. 基于MSK-CNN和多源机电信息融合的同步发电机故障诊断方法[J]. 电机与控制学报, 2023, 27(1): 1-11.
[22] 刘云鹏, 罗世豪, 王博闻, 等. 基于Mel时频谱-卷积神经网络的变压器铁芯夹件松动故障声纹模式识别[J]. 华北电力大学学报(自然科学版), 2020, 47(6): 52-60, 67.
[23] Lambamo W, Srinivasagan R, Jifara W.Analyzing noise robustness of cochleogram and Mel spectrogram features in deep learning based speaker recognition[J]. Applied Sciences, 2023, 13(1): 569.
[24] 姜涛, 刘博涵, 李雪, 等. 基于多元同步压缩变换的电力系统强迫振荡源定位[J]. 中国电机工程学报, 2024, 44(1): 46-58.
[25] 万可力, 马宏忠, 崔佳嘉, 等. 基于Mel-GADF与ConvNeXt-T的变压器铁心松动故障诊断方法[J]. 电力自动化设备, 2024, 44(3): 217-224.
[26] 李亦佳, 王静, 王正方, 等. 基于多重同步压缩变换的微震信号去噪方法研究[J]. 应用基础与工程科学学报, 2022, 30(2): 486-500.
[27] Zhao Minghang, Zhong Shisheng, Fu Xuyun, et al.Deep residual shrinkage networks for fault diag- nosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7): 4681-4690.
[28] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 770-778.
[29] 李世晓, 杜锦华, 龙云. 基于一维卷积神经网络的机电作动器故障诊断[J]. 电工技术学报, 2022, 37(增刊1): 62-73.