Aviation AC Series Arc Fault Detection Based on Improve Empirical Wavelet Transform Multi-Feature Fusion

被引：0
|
作者：
Cui R. [1 ,2 ]
Zhang Z. [1 ,2 ]
Tong D. [1 ,2 ]
Cui J. [3 ]
机构：
[1] State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin
[2] Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin
[3] Avic Tianjin Aviation Electro-Mechanical Co. Ltd, Tianjin
来源：
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | 2022年 / 37卷 / 12期
关键词：
Aviation arc fault; Empirical mode decomposition; Empirical wavelet transform; Extreme learning machine; Multi-feature fusion; Time-frequency analysis;
D O I：
10.19595/j.cnki.1000-6753.tces.201706
中图分类号：
学科分类号：
摘要：
An arc fault detection method based on improved empirical wavelet transform (IEWT) multi-feature fusion and extreme learning machine (ELM) was proposed to deal with the mode mixing phenomenon of the time-frequency domain analysis method (EMD). Firstly, the arc current signal was decomposed into five empirical mode components (EMFs) by IEWT, and the weight energy entropy of EMFs, sample entropy of EMF4, and root mean square value of EMF1 were extracted as characteristic variables. After data standardization, the three arc fault features were fused to form a multi-dimensional feature matrix, and finally the fault was identified by ELM. Comparing the IEWT and EMD decomposition, the results show that the IEWT method is superior to the signal processing of EMD, and it also avoids the misjudgment caused by a single feature under the multi-feature extraction. Combined with ELM, arc faults can be accurately identified, and the average accuracy is 97.85%. © 2022, Electrical Technology Press Co. Ltd. All right reserved.
引用
收藏
页码：3148 / 3161
页数：13
相关论文
共 26 条
  • [1] Zhang Dongshan, Chen Peishu, Analysis of fault arc in aviation electrical system, Practical Electronics, 22, pp. 27-28, (2017)
  • [2] Zhao Long, Zhou Yuhao, Chen Kunlong, Et al., Using spectrum of the light for high speed arcing fault detection, 2018 IEEE IAS Electrical Safety Work-shop (ESW), pp. 1-8, (2018)
  • [3] Liu Zhukui, Ding Xinzhi, Chen Fuming, Et al., Research on switchgear arc discharge fault and its measurement, Power System Technology, 41, 4, pp. 1345-1349, (2017)
  • [4] Wang Yao, Zhang Yanfeng, Niu Feng, Et al., Characteri-zation and measurement method of DC arc electro-magnetic radiation for photovoltaic systems, Transactions of China Electrotechnical Society, 34, 14, pp. 2913-2921, (2019)
  • [5] Zhang Guanying, Zhang Xiaoliang, Liu Hua, Et al., Online detection method for series arcing fault in low voltage system, Transactions of China Electro-technical Society, 31, 8, pp. 109-115, (2016)
  • [6] Kim J C, Neacsu D O, Lehman B, Et al., Series AC arc fault detection using only voltage waveforms, 2019 IEEE Applied Power Electronics Conference and Exposition (APEC), pp. 2385-2389, (2019)
  • [7] Syafi'i M A, Prasetyono E, Khafidli M K, Et al., Real time series DC arc fault detection based on fast fourier transform, 2018 International Electronics Symposium on Engineering Technology and Appli-cations, (IES-ETA), pp. 25-30, (2018)
  • [8] Artale G, Cataliotti A, Cosentino V, Et al., Arc fault detection method based on CZT low-frequency harmonic current analysis, IEEE Transactions on Instrumentation and Measurement, 66, 5, pp. 888-896, (2017)
  • [9] Zhang Shiwen, Zhang Feng, Wang Zijun, Et al., Series arc fault identification method based on energy produced by wavelet transformation and neural network, Transactions of China Electrotechnical Society, 29, 6, pp. 290-295, (2014)
  • [10] Guo Fengyi, Deng Yong, Wang Zhiyong, Et al., Arc fault characteristics based on gray level-gradient co-occurrence matrix, Transactions of China Electro-technical Society, 33, 1, pp. 71-81, (2018)
123