极端条件下基于特征层面信号融合的电励磁双凸极电机匝间短路故障诊断研究

doi:10.19595/j.cnki.1000-6753.tces.220516

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1700 KB)
输出: BibTeX | EndNote (RIS)

摘要

电励磁双凸极电机（Wound-Field Doubly Salient Machine,WFDSM）具有结构简单、可靠性高等优点,适用于航空航天等环境恶劣领域。当发生小匝数短路故障时,由于其电流、振动等信号不会产生明显的变化,难以用传统的检测手段区分。因此本文提出一种基于特征层面多源信号融合和改进神经网络的WFDSM匝间短路故障诊断方法,用于诊断极端环境下WFDSM早期匝间短路故障。本文首先对电流信号进行经验模态分解,获得本征模态函数,同时对振动信号进行小波包变换,并对分解后的各个频段提取峭度和裕度特征,同时计算能量占比;然后将上述特征矩阵处理后输入改进卷积神经网络训练模型中;最后通过实验表明：采取特征融合的计算方法诊断准确率可达98%,较数据层面和结果层面的融合计算方法有明显的准确率提升,并且对极端运行环境下的噪声,该方法具有很强的抗干扰能力。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	赵耀
	沈翀
	李东东
	林顺富
	杨帆

关键词 ：电励磁双凸极电机, 经验模态分解, 特征层融合, 改进卷积神经网络, 极端环境

Abstract：

The Wound-Field Doubly Salient Machine (WFDSM) has the advantages of the simple structure and high reliability. It is suitable for aerospace and other applications in harsh environments. When an inter-turn short-circuit fault occurs, it is difficult to be distinguished by traditional diagnosis methods due to slight changes of currents and vibration. Therefore, a novel WFDSM inter-turn short circuit diagnosis method is proposed in this paper based on multi-signal fusion at feature level and improved Convolutional Neural Network(CNN).
Firstly, current and vibration data are collected from the 8-10 WFDSM. The 75 sets of four-phase current signals are processed by Empirical Mode Decomposition (EMD), and Intrinsic Mode Function (IMF) of length 101 are taken from each phase current. Thus, each condition of current feature matrix is 300 sets of length 101. At the same time, the wavelet packet transform is applied to the vibration signal, and each sensor gets kurtosis, margin and energy ratio of length 256. Thus, each condition of vibration feature matrix is 300 sets of length 768. Interval scaling, normalization, missing value processing and other feature processing are taken after two sets were arranged in parallel. Each group is randomly divided into training set and test set in the ratio of 4:1. After the input matrix is convolved and pooled, the data features are effectively preserved by batch normalization layer, next the flatten layer is laminated and finally passed to SoftMax classifier for diagnosis. The dropout layer is also applied in the diagnosis, while the learning rate is optimized to ensure the high classification efficiency and no overfitting occurs in the model.
The diagnosis results of different detection quantities show that, when only current signals are used, the accuracy can only reach 82.8% on 800r/min and 83.7% on 1000r/min; when only vibration signals are used, the accuracy can only reach 85.7% and 84.3%. In contrast, when the multi-signal fusion at feature level method is adopted, the accuracy can reach up to 98.3%, while the model convergence speed accelerates significantly. In order to simulate the extreme conditions, different degrees of white Gaussian noise are added to experiment. The accuracy of the fusion at feature level method barely changed when the SNR >20dB, which is still above 95%. Meanwhile, when SNR=10dB, the accuracy can still maintain 87.8%. By considering the accuracy and solving efficiency, the fusion at feature level method is superior to method of fusion at the data level or the result level.
The following conclusions can be drawn from the analysis of model theory and experimental data：1)The magnetic field of WFDSM will be distorted with additional harmonics generated when a short-circuit fault occurs, which also indirectly leads to the change of the current and vibration. 2)Compared with the single signal diagnosis method, the accuracy and convergence speed of the proposed model are greatly improved. 3)The proposed model performs better and has a strong anti-interference ability under the extreme conditions. 4) The features extracted by EMD and wavelet packet transform play a important role in fault identification, and the improved CNN also has a good classification effect.

Key words： Wound-field doubly salient machine empirical mode decomposition feature fusion improved convolutional neural network extreme conditions

PACS:

TM352

基金资助:

国家自然科学基金（51977128）,上海市青年科技启明星计划资助（21QC1400200）,上海市自然科学基金（21ZR1425400）

通讯作者: 李东东男,1976年生,博士,教授,博士生导师,研究方向为电力设备故障诊断、风力发电与电力系统稳定控制、智能用电。E-mail：powerldd@163.com

作者简介: 赵耀男,1987年生,博士,副教授,硕士生导师,研究方向为电力设备故障诊断、新能源发电。E-mail：nihaozhaoyao@163.com

引用本文:

赵耀, 沈翀, 李东东, 林顺富, 杨帆. 极端条件下基于特征层面信号融合的电励磁双凸极电机匝间短路故障诊断研究[J]. 电工技术学报, 0, (): 8-8. Zhao Yao, Shen Chong, Li Dongdong, Lin Shunfu, Yang Fan. Research on Inter-turn Short circuit Diagnosis of Wound-Field Doubly Salient Machine Based on Multi-signal Fusion on Feature Level under Extreme Conditions. Transactions of China Electrotechnical Society, 0, (): 8-8.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.220516 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/8

[1] 于立, 张卓然, 张健, 等. 多电发动机内装式高速起动发电机研究与实践[J]. 中国电机工程学报, 2020, 40(14): 4615-4628, 4740.
Yu Li, Zhang Zhuoran, Zhang Jian, et al.Study and implementation on high-speed starter/generator for more electric engine application[J]. Proceedings of the CSEE, 2020, 40(14): 4615-4628, 4740.
[2] 王逸洲, 王慧贞, 刘伟峰, 等. 新型电励磁双凸极电机发电系统建模研究[J]. 中国电机工程学报, 2017, 37(17): 5162-5170, 5236.
Wang Yizhou, Wang Huizhen, Liu Weifeng, et al.A novel modeling method for power generator systems of wound-excited doubly salient machines[J]. Proceedings of the CSEE, 2017, 37(17): 5162-5170, 5236.
[3] 陈云云, 朱孝勇, 全力, 等. 基于参数敏感度的双凸极永磁型双定子电机的优化设计和性能分析[J]. 电工技术学报, 2017, 32(8): 160-168.
Chen Yunyun, Zhu Xiaoyong, Quan Li, et al.Parameter sensitivity optimization design and performance analysis of double-salient permanent-magnet double-stator machine[J]. Transactions of China Electrotechnical Society, 2017, 32(8): 160-168.
[4] 张健, 朱锡庆, 张卓然, 等.电励磁双凸极无刷直流发电机热网络建模与热特性研究[J]. 中国电机工程学报, 2023,43(1):318-329.
Zhang Jian, Zhu Xiqing, Zhang Zhuoran, et al.Thermal network modeling and thermal characteristics analysis of doubly salient brushless DC generator with stator field winding[J]. Proceedings of the CSEE, 2023,43(1):318-329.
[5] 闫文举, 陈昊, 马小平, 等. 不同转子极数下磁场解耦型双定子开关磁阻电机的研究[J]. 电工技术学报, 2021, 36(14): 2945-2956.
Yan Wenju, Chen Hao, Ma Xiaoping, et al.Development and investigation on magnetic field decoupling double stator switched reluctance machine with different rotor pole numbers[J]. Transactions of China Electrotechnical Society, 2021, 36(14): 2945-2956.
[6] 郭佳强, 刘旭, 李珊瑚. 计及电枢和零序回路电阻压降的可变磁通磁阻电机弱磁控制[J]. 电工技术学报, 2021, 36(18): 3911-3921.
Guojia Qiang, Liu Xu, Li Shanhu.Flux weakening control of variable flux reluctance machine considering resistive voltage drops in armature and zero-sequence loop[J]. Transactions of China Electrotechnical Society, 2021, 36(18): 3911-3921.
[7] 丁文, 李可, 付海刚. 一种12/10极模块化定子混合励磁开关磁阻电机分析[J]. 电工技术学报, 2022, 37(8): 1948-1958.
Ding Wen, Li Ke, Fu Haigang.Analysis of A 12/10-pole modular-stator hybrid-excited switched reluctance machine[J]. Transactions of China Electrotechnical Society, 2022, 37(8): 1948-1958.
[8] 孙毅, 蔡顺, 林迎前, 等. 永磁辅助同步磁阻电机顶层优化设计[J]. 电工技术学报, 2022, 37(9): 2306-2318.
Sun Yi, Cai Shun, Lin Yingqian, et al.Top-level design pattern of PM-assisted synchronous reluctance machines[J]. Transactions of China Electrotechnical Society, 2022, 37(9): 2306-2318.
[9] 王瑾, 李岩, 于占洋, 等. 永磁同步磁阻电动机全负载区域功率因数特性分析[J]. 电工技术学报, 2021, 36(增刊2): 451-459.
Wang Jin, Li Yan, Yu Zhanyang, et al.Analysis of power factor characteristics of permanent magnet synchronous reluctance motor in whole load range[J]. Transactions of China Electrotechnical Society, 2021, 36(S2): 451-459.
[10] Zhang Minjie, Ali N, Gao Qiang.Winding inductance and performance prediction of a switched reluctance motor with an exterior-rotor considering the magnetic saturation[J]. CES Transactions on Electrical Machines and Systems, 2021, 5(3): 212-223.
[11] Gan Chun, Chen Yu, Qu Ronghai, et al.An overview of fault-diagnosis and fault-tolerance techniques for switched reluctance machine systems[J]. IEEE Access, 2019, 7: 174822-174838.
[12] Park J K, Babetto C, Berardi G, et al.Comparison of fault characteristics according to winding configurations for dual three-phase synchronous reluctance motor[J]. IEEE Transactions on Industry Applications, 2021, 57(3): 2398-2406.
[13] Chen Hao, Han Guoqiang, Shi Xianqiang, et al.Phase Current digital analysis of power converter for freewheeling diode fault diagnosis on switched reluctance motor drive[J]. IEEE Transactions on Industrial Electronics, 2019, 66(8): 6613-6624.
[14] 夏一文, 张卓然, 张健, 等. 基于反电势电流的电励磁双凸极电机驱动电路单管开路故障诊断研究[J]. 电工技术学报, 2020, 35(23): 4888-4897.
Xia Yiwen, Zhang Zhuoran, Zhang Jian, et al.Research on single power switch open circuit fault diagnosis of doubly salient eletromagnetic motor drive circuit based on the back electromotive force current[J]. Transactions of China Electrotechnical Society, 2020, 35(23): 4888-4897.
[15] Alam M, Shah V, Payami S.Online fault diagnosis of static and dynamic eccentricity in switched reluctance motors using parks vector algorithm[C]//The 10th International Conference on Power Electronics, Machines and Drives (PEMD 2020), Online Conference, 2021: 885-889.
[16] Fonseca D S B, Marques Cardoso A J. On-line inter-turn short-circuit fault diagnosis in switched reluctance motors[C]//2019 IEEE International Electric Machines & Drives Conference (IEMDC), San Diego, CA, USA, 2019: 198-202.
[17] Arafat A, Choi S, Baek J.Open-phase fault detection of a five-phase permanent magnet assisted synchronous reluctance motor based on symmetrical components theory[J]. IEEE Transactions on Industrial Electronics, 2017, 64(8): 6465-6474.
[18] Gan Chun, Wu Jianhua, Yang Shiyou, et al.Wavelet packet decomposition-based fault diagnosis scheme for SRM drives with a single current sensor[J]. IEEE Transactions on Energy Conversion, 2016, 31(1): 303-313.
[19] 何玉灵, 孙凯, 王涛, 等. 基于变分模态分解与精细复合多尺度散布熵的发电机匝间短路故障诊断[J]. 电力自动化设备, 2021, 41(3): 164-172.
He Yuling, Sun Kai, Wang Tao, et al.Fault diagnosis of generator interturn short circuit fault based on variational mode decomposition and refined composite multiscale dispersion entropy[J]. Electric Power Automation Equipment, 2021, 41(3): 164-172.
[20] 肖雄, 肖宇雄, 张勇军, 等. 基于二维灰度图的数据增强方法在电机轴承故障诊断的应用研究[J]. 中国电机工程学报, 2021, 41(2): 738-749.
Xiao Xiong, Xiao Yuxiong, Zhang Yongjun, et al.Research on the application of the data augmentation method based on 2D gray pixel images in the fault diagnosis of motor bearing[J]. Proceedings of the CSEE, 2021, 41(2): 738-749.
[21] 李梦诗, 余达, 陈子明, 等. 基于深度置信网络的风力发电机故障诊断方法[J]. 电机与控制学报, 2019, 23(2): 114-122.
Li Mengshi, Yu Da, Chen Ziming, et al.Fault diagnosis and isolation method for wind turbines based on deep belief network[J]. Electric Machines and Control, 2019, 23(2): 114-122.
[22] 李垣江, 张周磊, 李梦含, 等. 采用深度学习的永磁同步电机匝间短路故障诊断方法[J]. 电机与控制学报, 2020, 24(9): 173-180.
Li Yuanjiang, Zhang Zhoulei, Li Menghan, et al.Fault diagnosis of inter-turn short circuit of permanent magnet synchronous motor based on deep learning[J]. Electric Machines and Control, 2020, 24(9): 173-180.
[23] Wang Xiaoxian, Lu Siliang, Chen Kang, et al.Bearing fault diagnosis of switched reluctance motor in electric vehicle powertrain via multisensor data fusion[J]. IEEE Transactions on Industrial Informatics, 2022, 18(4): 2452-2464.
[24] 施耀华, 冯延晖, 任铭, 等. 融合电流和振动信号的永磁同步风电系统变流器故障诊断方法研究[J]. 中国电机工程学报, 2020, 40(23): 7750-7760.
Shi Yaohua, Feng Yanhui, Ren Ming, et al.Study on fault diagnosis method of converter in permanent magnet synchronous wind power system by fusion of current and vibration signals[J]. Proceedings of the CSEE, 2020, 40(23): 7750-7760.
[25] Irhoumah M, Pusca R, Lefevre E, et al.Information fusion with belief functions for detection of interturn short-circuit faults in electrical machines using external flux sensors[J]. IEEE Transactions on Industrial Electronics, 2018, 65(3): 2642-2652.
[26] 陈勇, 梁洪, 王成栋, 等. 基于改进小波包变换和信号融合的永磁同步电机匝间短路故障检测[J]. 电工技术学报, 2020, 35(增刊1): 228-234.
Chen Yong, Liang Hong, Wang Chengdong, et al.Detection of stator inter-turn short-circuit fault in PMSM based on improved wavelet packet transform and signal fusion[J]. Transactions of China Electrotechnical Society, 2020, 35(S1): 228-234.
[27] 杨洁, 万安平, 王景霖, 等. 基于多传感器融合卷积神经网络的航空发动机轴承故障诊断[J/OL]. 中国电机工程学报,2022:1-9. http://kns.cnki.net/kcms/detail/11.2107.TM.20211101.1325.007.html
Yang Jie, Wan Anping, Wang Jinglin, et al. Aeroengine bearing fault diagnosis based on convolutional neural network for multi-sensor information fusion[J/OL]. Proceedings of the CSEE, 2022:1-9.http://kns.cnki.net/kcms/detail/11.2107.TM.20211101.1325.007.html
[28] Zhao Yao, Teng Denghui, Li Dongdong, et al.Comparative research on four-phase dual armature-winding wound-field doubly salient generator with distributed field magnetomotive forces for high-reliability application[J]. IEEE Access, 2021, 9: 12579-12591.
[29] 刘素贞, 魏建, 张闯, 等. 基于FPGA的超声信号自适应滤波与特征提取[J]. 电工技术学报, 2020, 35(13): 2870-2878.
Liu Suzhen, Wei Jian, Zhang Chuang, et al.Adaptive filtering and feature extraction of ultrasonic signal based on FPGA[J]. Transactions of China Electrotechnical Society, 2020, 35(13): 2870-2878.
[30] 王栋悦, 谷怀广, 魏书荣, 等. 基于机电信号融合的DFIG定子绕组匝间短路故障诊断[J]. 电力系统自动化, 2020, 44(9): 171-178.
Wang Dongyue, Gu Huaiguang, Wei Shurong, et al.Diagnosis of inter-turn short-circuit fault in stator windings of DFIG based on mechanical and electrical signal fusion[J]. Automation of Electric Power Systems, 2020, 44(9): 171-178.