Journal of Power Electronics

  • 제21권12호
  • /
  • Pages.1900-1909
  • /
  • 2021
  • /
  • 1598-2092(pISSN)
  • /
  • 2093-4718(eISSN)
전력전자학회 (The Korean Institute of Power Electronics)
권호 표지
DOI QR코드

DOI QR Code

DC series arc diagnosis based on deep-learning algorithm with frequency-domain characteristics

  • Jeong, Jae‑Yoon (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Kim, Jae‑Chang (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Kwak, Sangshin (School of Electrical and Electronics Engineering, Chung-Ang University)
  • 투고 : 2021.09.08
  • 심사 : 2021.10.22
  • 발행 : 2021.12.20
⟨ 이전 논문 다음 논문 ⟩

초록

A series arc produces both light and heat, which results in a risk of fire. Hence, its prompt detection is very important. The series arc has different frequency characteristics depending on the operating conditions of the inverter and the line impedance. As a result, it is difficult to detect with conventional methods that use specific frequency bands. In this study, series arcs generated by three-phase pulse-width-modulated and three-phase model-predictive-control inverter loads, operating under various conditions, were detected using a deep-learning algorithm. To detect a series arc fault, the frequency characteristics were analyzed using all the frequency bands of a fast Fourier transform (FFT) result. To use all the frequency bands, a deep neural network (DNN), which is a deep-learning algorithm, was used. DNNs can learn quickly from large amounts of data and model complex nonlinear relationships. The DNN model proposed in this paper was designed to use all the frequency bands, and three cases were tested by changing the current magnitude and switching frequency. The arc current detection accuracy was calculated for three test cases and the obtained results were analyzed in detail based on the percentages of true/false and mean absolute error metrics. The analysis confirmed that the arc current was accurately detected, which validates the suitability of the DNN for series arc detection.

키워드

과제정보

This work was supported by the Korea Electric Power Corporation (Grant number: R21XA01-3) and "The Competency Development Program for Industry Specialists" of the Korean Ministry of Trade, Industry and Energy (MOTIE), operated by the Korea Institute for Advancement of Technology (KIAT) (No. P0012453, Next-generation Display Expert Training Project for Innovation Process and Equipment, Materials Engineers).

참고문헌

  1. Miao, W., Xu, Q., Lam, K.H., Pong, P.W.T., Poor, H.V.: DC arc fault detection based on empirical mode decomposition of arc signatures and support vector machine. IEEE. Sensors. 21(5), 7023-7033 (2021) https://doi.org/10.3390/s21217023
  2. Chen, S., Li, X., Xiong, J.: Series arc fault identification for photovoltaic system based on time-domain and time-frequency-domain analysis. IEEE. Photovoltaics. 7(4), 1105-1114 (2017) https://doi.org/10.1109/JPHOTOV.2017.2694421
  3. Johnson, J., Pahl, B., Luebke, C., Pier, T., Miller, T., Strauch, J., Kuszmaul, S., Bower, W.: Photovoltaic DC-arc-fault detector testing at sandia national laboratories. In: IEEE Photovoltaic Specialists Conference Seattle, WA, USA, 003614-003619 (2011)
  4. Dini, D. A., Brazis, P. W., Yen, K. H.: Development of arc-fault-circuit interrupter requirements for photovoltaic system. In: IEEE Photovoltaic Specialists Conference Seattle, WA, USA, 001790- 001794 (2011)
  5. UL1699B: Standard for photovoltaic DC arc-fault circuit protection. underwriters laboratories (2018)
  6. Naidu, M., Schoepf, T.J., Gopalakrishnan, S.: Arc fault detection scheme for 42-V automotive DC networks using current shunt. IEEE. Trans. Power Electron. 21(3), 633 (2006)
  7. Streck, M., Nothnagel, F., Berger, F.: Parameters' Values of small signal equivalent circuit of electric arc gaps in DC network, pp. 1-6. IEEE. Int. Power Engineering. Conf, Stoke on Trent, UK (2015)
  8. Kim, J.C., Kwak, S.S.: Frequency-Domain Characteristics of Series DC Arcs in Photovoltaic Systems with Voltage-Source Inverters. MDPI. Applied Sciences. 10(22), 8042 (2020) https://doi.org/10.3390/app10228042
  9. Park, H.P., Chae, S.: DC series arc fault detection algorithm for distributed energy resources using arc fault impedance modeling. IEEE. Access. 8, 179039-179046 (2020) https://doi.org/10.1109/access.2020.3027869
  10. Kim, J.C., Kwak, S.S., Choi, S.D.: DC series arc detection algorithm based on adaptive moving average technique. IEEE. Access. 9, 94426-94437 (2021) https://doi.org/10.1109/ACCESS.2021.3093980
  11. Le, V., Yao, X., Miller, C., Tsao, B.H.: Series DC arc fault detection based on ensemble machine learning. IEEE. Trans. Power Electron. 35(8), 7826-7839 (2020) https://doi.org/10.1109/tpel.2020.2969561
  12. Siegel, J., Pratt, S., Sun, Y., Sarma, S.E.: Real-time deep neural networks for internet-enabled arc-fault detection. Eng. Appl. Int. 74, 35-42 (2018)
  13. Karmakar, S., Lala, H.: Detection and experimental validation of high impedance arc fault in distribution system using empirical mode decomposition. IEEE. System. 14(3), 3494-3505 (2020) https://doi.org/10.1109/JSYST.2020.2969966
  14. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436-444 (2015) https://doi.org/10.1038/nature14539
  15. Momoh, J.A., Button, R.: Design and analysis of aerspace DC arcing faults using fast fourier transformation and artificial neural network. In: IEEE Power Engineering Conference Toronto, ON, Canada (2003)
  16. Dahl, G. E., Sainath, T. N., Hinton G.E.: Improving deep neural networks for LVCSR using rectified linear units and dropout. IEEE International Conference, Vancouver, BC, Canada, pp. 8609-8613 (2013)
  17. Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. Int. Conf. Artif. Intell. Stat. 15, 315-323 (2011)
  18. Johnson, J., Kang, J.: Arc-fault detector algorithm evaluation method utilizing prerecorded arcing signatures. In: IEEE Photovoltaic Specialists Conference, Austin, TX, USA, pp. 1-5 (2011)