Integration of wavelet packet transform, residual convolution neural network, and support vector machine for series arc fault detection
Source abstract
Abstract
Series arc fault (SAF) poses a great challenge to the safe and stable operation of civil low-voltage distribution systems. For the accurate and rapid detection of SAF, this article proposes an SAF detection method using wavelet packet transform (WPT), residual convolution neural network (RCNN), and support vector machine (SVM). First, the raw current signal is decomposed into four wavelet components based on WPT. Then, the 1-D wavelet components are converted into 2-D matrices. Afterward, the matrices are input into RCNN through different channels. Finally, the detection results can be yielded by SVM. The effectiveness of the proposed method is verified based on offline experiments. The average detection accuracy of the proposed method is 99.72%, which is higher than that of the eight comparison methods. Moreover, the results of online experiments indicate that the detection time of the proposed method is less than 100 ms and can satisfy the requirement of standard 1699.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Electrical Fault Detection and Protection · Integrated Circuits and Semiconductor Failure Analysis · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Electrical, Energy and Power Engineering, Yangzhou University , Yangzhou 225127, China
Funding
National Natural Science Foundation of China
References (33)
Show source-provided references
1. Recurrence plots based method for detecting series arc faults in photovoltaic systems10.1109/tie.2021.3095819 ↗
2. ArcNet: Series AC arc fault detection based on raw current and convolutional neural network10.1109/tii.2021.3069849 ↗
3. Design of a DC series arc fault detector for photovoltaic system protection10.1109/tia.2019.2894992 ↗
4. Series arc fault identification for photovoltaic system based on time-domain and time-frequency-domain analysis10.1109/jphotov.2017.2694421 ↗
5. Hurst-exponent-based detection of high-impedance DC arc events for 48-V systems in vehicles10.1109/tpel.2020.3020587 ↗
6. Research on arc-fault detection based on difference-root mean square method10.16628/j.cnki.2095-8188.2013.01.013 ↗
7. Detection of serial arc fault on low-voltage indoor power lines by using radial basis function neural network10.1016/j.ijepes.2016.04.013 ↗
8. Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network10.1109/tii.2018.2885945 ↗
9. Real-time deep neural networks for internet-enabled arc-fault detection10.1016/j.engappai.2018.05.009 ↗
10. Series arc fault detection based on random forest and deep neural network10.1109/jsen.2021.3082294 ↗
11. Research on feature enhancement of DC arc fault detection in photovoltaic systems10.13334/j.0258-8013.pcsee.210471 ↗
12. Research on series arc fault detection and phase selection feature extraction method10.1109/tim.2021.3080376 ↗
13. Intelligent fault diagnosis of rotary machines: Conditional auxiliary classifier GAN coupled with meta learning using limited data10.1109/tim.2021.3082264 ↗
14. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification10.1016/j.aei.2017.02.005 ↗
15. Series arc fault diagnosis and line selection method based on recurrent neural network10.1109/access.2020.3027002 ↗
16. Series AC arc fault detection method based on high-frequency coupling sensor and convolution neural network10.3390/s20174910 ↗
17. Intever public database for arcing event detection: Feature analysis, benchmark test, and multi-scale CNN application10.1109/tim.2021.3082998 ↗
18. A novel series arc fault detection method for photovoltaic system based on multi-input neural network10.1016/j.ijepes.2022.108018 ↗
19. Extreme learning machine-based classifier for fault diagnosis of rotating machinery using a residual network and continuous wavelet transform10.1016/j.measurement.2021.109864 ↗
20. Standard for Safety Arc-Fault Circuit-Interrupters · 2011
21. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox10.1109/tie.2018.2844805 ↗
22. Conditional GAN and 2-D CNN for bearing fault diagnosis with small samples10.1109/tim.2021.3119135 ↗
23. A new convolutional neural network-based data-driven fault diagnosis method10.1109/tie.2017.2774777 ↗
24. Fault diagnosis of rotating machinery based on recurrent neural networks10.1016/j.measurement.2020.108774 ↗
25. Batch normalization: Accelerating deep network training by reducing internal covariate shift
26. Deep residual learning for image recognition
27. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals10.3390/s17020425 ↗
28. D. P. Kingma and J.Ba, “Adam: A method for stochastic optimization,” arXiv:1412.6980 (2014).
29. A novel transfer learning method for bearing fault diagnosis under different working conditions10.1016/j.measurement.2020.108767 ↗
30. Compressed residual-VGG16 CNN model for big data places image recognition
31. An intelligent recognition method of a short-gap arc in aviation cables based on feature weight enhancement10.1109/jsen.2022.3232571 ↗
32. A series arc fault diagnosis method in DC distribution systems based on multiscale features and random forests10.1109/jsen.2022.3228551 ↗
33. Extreme learning machine-based classifier for fault diagnosis of rotating machinery using a residual network and continuous wavelet transform10.1016/j.measurement.2021.109864 ↗