Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Photovoltaic DC arc fault detection method based on deep residual shrinkage network

  • Penghe Zhang (China Electric Power Research Institute) ;
  • Yang Xue (China Electric Power Research Institute) ;
  • Runan Song (China Electric Power Research Institute) ;
  • Xiaochen Ma (Department of Electrical Engineering, Hebei University of Technology) ;
  • Dejie Sheng (Department of Electrical Engineering, Hebei University of Technology)
  • Received : 2023.12.13
  • Accepted : 2024.04.25
  • Published : 2024.11.20
⟨ Previous Next ⟩

Abstract

Distributed photovoltaic systems have encountered unprecedented opportunities for development given their environmentally friendly nature and flexible power generation characteristics. However, numerous connecting lines and taps within the distributed photovoltaic system can be subject to insulation issues, which will consequently cause direct current (DC) arc faults and severe electrical fire hazards. Moreover, the power semiconductor devices in the photovoltaic inverter can introduce common-mode noises to the DC current, resulting in unwanted tripping of the DC arc fault detector. The study proposes an arc fault detection method utilizing a deep residual shrinkage network (DRSN) to address this issue, thereby precisely detecting DC arc faults. A test platform for series arc faults in photovoltaic systems is built. The arc current data are collected for characteristic analysis in time and frequency domains to determine which bandwidth is preferred for the algorithm. The model's depth is increased by introducing residual connections, enhancing its feature extraction, and improving noise reduction capabilities. The residual shrinkage network has been enhanced to prevent a computation increase from increased network depth. Introducing a convolutional auto-encoder for data dimension reduction has decreased neural network parameters, thereby improving training speed. A prototype for detecting photovoltaic DC arc faults was constructed using Raspberry Pi 4B, validating the practical application value of the proposed method. Experimental results demonstrate that the prototype for detecting photovoltaic DC arc faults successfully fulfills the real-time detection standard of the conduction test.

Keywords

References

  1. Pillai, D.S., Blaabjerg, F., Rajasekar, N.: A comparative evaluation of advanced fault detection approaches for PV systems. IEEE J. Photovolt. 9(2), 513-527 (2019) https://doi.org/10.1109/JPHOTOV.2019.2892189
  2. Jing, L., Xia, L., Zhao, T., Zhou, J.: An improved arc fault location method of DC distribution system based on EMD-SVD decomposition. Appl. Sci. 13, 9132 (2023) https://doi.org/10.3390/app13169132
  3. Wu, Q., Zhang, J., Ran, T., et al.: Simulation study on steady-state heat transfer characteristics of DC arc fault. J. Electr. Technol. 36(13), 2697-2709 (2021)
  4. Dang, H.-L., Kwak, S., Choi, S.: Empirical filtering-based artificial intelligence learning diagnosis of series DC arc faults in time domains. Machines 11, 968 (2023) https://doi.org/10.3390/machines11100968
  5. Weerasekara M, Vilathgamuwa M, Mishra Y. Modelling of DC arcs for photovoltaic system faults. In: 2016 IEEE 2nd Annual Southern Power Electronics Conference (SPEC), Auckland, New Zealand, pp. 1-4 (2016)
  6. Cho, K.-C., Park, M.-K., Lim, S.-H.: Analysis of the DC fault current limiting characteristics of a DC superconducting fault current limiter using a transformer. Energies 13, 4210 (2020) https://doi.org/10.3390/en13164210
  7. Qing, X., Ji, S., Lu, W., et al.: Amplitude and frequency characteristics of electromagnetic radiation of series DC arc fault under low pressure. Chin. J. Electr. Eng. 37(04), 1071-1080 (2017)
  8. Xiong, X., Ji, et al.: DC arc detection method based on electromagnetic radiation characteristics. High Volt. Technol. 43(09), 2967-2975 (2017)
  9. Liu, S.Y., Dong, L., Liao, X.Z., et al.: Application of the variational mode decomposition-based time and time-frequency domain analysis on series DC arc fault detection of photovoltaic arrays. IEEE Access 7, 126177-126190 (2019) https://doi.org/10.1109/ACCESS.2019.2938979
  10. Qing, X., Liu, X., Guo, Z., et al.: Arc fault detection and location of photovoltaic system based on current spectrum integral difference. High Volt. Technol. 47(05), 1625-1633 (2021)
  11. Wu, X., Li, et al.: Research on DC arc fault detection method and anti-interference of photovoltaic system. Chin. J. Electr. Eng. 38(12), 3546-3555+14 (2018)
  12. Wang, L., Lodhi, E., Yang, P., Qiu, H., Rehman, W.U., Lodhi, Z., Tamir, T.S., Khan, M.A.: Adaptive local mean decomposition and multiscale-fuzzy entropy-based algorithms for the detection of DC series arc faults in PV systems. Energies 15, 3608 (2022) https://doi.org/10.3390/en15103608
  13. Meng, Yu., Chen, S., Zihao, Wu., et al.: Research on enhancing the detection characteristics of photovoltaic DC arc fault based on stochastic resonance method. Chin. J. Electr. Eng. 42(06), 2396-2407 (2022)
  14. Liu, X., Wang, et al.: Experimental study on detection algorithm and protection of series DC arc in photovoltaic power station. J. Solar Energy 43(01), 348-355 (2022)
  15. Lu, S.B., Sirojan, T., Phung, B.T., et al.: DA-DCGAN: an effective methodology for DC series arc fault diagnosis in photovoltaic systems. IEEE Access 7, 45831-45840 (2019) https://doi.org/10.1109/ACCESS.2019.2909267
  16. Miao, W.C., Xu, Q., Lam, K.H., et al.: DC arc-fault detection based on empirical mode decomposition of arc signatures and support vector machine. IEEE Sens. J. 21(5), 7024-7033 (2021) https://doi.org/10.1109/JSEN.2020.3041737
  17. Wu, Y., Wang, B.: DC series arc fault detection based on improved empirical mode decomposition. J. Jinan Univ. (Nat. Sci. Ed.) 38(01), 1-9 (2022)
  18. Tang, S., Diao, X., Li, C., et al.: Research on DC series weak arc fault detection method for photovoltaic power generation system. J. Instrum. 42(03), 150-160 (2021)
  19. Liu, B.: Research on leakage current suppression technology for three-phase non-isolated inverters. Nanjing University of Posts and Telecommunications (2018)
  20. Sung, Y., Yoon, G., Bae, J.-H., Chae, S.: TL-LEDarcNet: transfer learning method for low-energy series DC arc-fault detection in photovoltaic systems. IEEE Access 10, 100725-100735 (2022) https://doi.org/10.1109/ACCESS.2022.3208115
  21. Hui, J., Wei, G., Gengjie, Y.: An intelligent detection method for eries arc fault of photovoltaic array. Electr. Eng. Electr. 01, 43-47+66 (2023)