Journal of Power Electronics

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

DOI QR Code

Risk assessment of aviation DC series arc based on reconstructed CBAM-CNN

  • Haoqi Yang (College of Civil Aviation, Nanjing University of Aeronautics and Astronautics) ;
  • Cong Gao (College of Civil Aviation, Nanjing University of Aeronautics and Astronautics) ;
  • Hongjuan Ge (College of Civil Aviation, Nanjing University of Aeronautics and Astronautics) ;
  • Yiqin Sang (College of Civil Aviation, Nanjing University of Aeronautics and Astronautics) ;
  • Yongshuai Wang (College of Automation Engineering, Nanjing University of Aeronautics and Astronautics)
  • Received : 2022.07.26
  • Accepted : 2022.11.30
  • Published : 2023.05.20
⟨ Previous Next ⟩

Abstract

The hazards of sustained arc and un-sustained arc are different. However, during the stage of arc development, there is a lack of effective methods to identify them, which is not conducive to the timely accurate assessment of arc risk. Therefore, this paper proposes a risk assessment method for aviation DC series arc based on a reconstructed CBAM-CNN. First, in the process of generating the feature set, a feature evaluation function is defined to screen the features. Then the existing convolution block attention module (CBAM) is improved by adding a reshaped layer and redefining spatial attention, which results in the reconstructed CBAM-CNN. Finally, the reconstructed CBAM-CNN takes the feature set as its input and output arc risk assessment results on the basis of enhancing the attention of important features. The validity of the reconstructed CBAM-CNN method is verified on an aviation DC arc generation platform. It is found that the proposed method has a higher training efficiency and evaluation accuracy than the CNN method and CBAM-CNN method. In addition, the reconstructed CBAM-CNN involves fewer parameters to be measured, which can reduce its dependence on computing resources.

Keywords

Acknowledgement

This work was supported by the National Natural Science Foundation of China (Grant U2233205 and U1933115).

References

  1. Yang, X., Zhou, D.J., Song, W., et al.: Path planning method for cable harness considering complex constraints. J Xidian University. 48(3), 197-204 (2021)
  2. Wu, Ch. H., Zheng, Y. X., Wang, F., et al. (2020) Simulation study on the impact of microgrids on DC arc. 2020 5th International on Power and Renewable Energy, ICPRE. 272-277
  3. Ajaml, C.N.M., Raghavendra, I.V., Naik, S., et al.: A modifed hybrid DC circuit breaker with reduced arc for low voltage DC grids. IEEE Access. 9, 132267-132277 (2021) https://doi.org/10.1109/ACCESS.2021.3115456
  4. Chung, H.-B., Lee, K.-H., Park, W.-J., et al. (2022) Arc extinction structure of air circuit breaker for improvement of direct current breaking perfor- mance. ICEPE-ST 2022-2022 6th International Conference on Electric Power Equipment-Switching Technology. 237-240
  5. Cho, Y., Lim, J., Seo, H., et al.: A series arc fault detection strategy for single-phase boost PFC rectifers. J Power Electr. 15(6), 1664-1672 (2015) https://doi.org/10.6113/JPE.2015.15.6.1664
  6. Vu, H.D., Calderon, E., Schweitzer, P., et al.: Multi criteria series arc fault detection based on supervised feature selection. Int. J. Electr. Power Energy Syst. 113, 23-34 (2019) https://doi.org/10.1016/j.ijepes.2019.05.012
  7. Park, C.-J., Dang, H.-L., Kwak, S., et al.: Deep learning-based series AC arc detection algorithms. J of Power Electr. 21(10), 1621-1631 (2021) https://doi.org/10.1007/s43236-021-00299-5
  8. Parise, G., Martirano, L., Laurini, M.: Simplifed arc-fault model: The reduction factor of the arc current. IEEE Trans. Ind. Appl. 49(4), 1703-1710 (2013) https://doi.org/10.1109/TIA.2013.2256452
  9. Kim, JCh., Kwak, SSh.: Detection and identifcation technique for series and parallel DC arc faults. IEEE Access. 10, 60474-60485 (2022) https://doi.org/10.1109/ACCESS.2022.3180750
  10. Ma, Sh.H., Bao, J.Q., Cai, Zh.Y., et al.: A novel arc fault identifcation method based on information dimension and current zero. Proc Chin Soc Electr Eng. 36(9), 2572-2579 (2016)
  11. Huang, K.Y., Sun, H., Niu, Ch.P., et al.: Simulation of arcs for DC relay considering diferent impacts. Plasma Sci. Technol (2020). https://doi.org/10.1088/2058-6272/ab5ba2
  12. Wu, Q.R., Zhang, RCh., Tu, R., et al.: Simulation study on steadystate transfer characteristics of DC arc fault. Trans Chin Electrotech Soc. 36(13), 2697-2709 (2021)
  13. Xiong, Q., Chen, W.J., Ji, S.C., et al.: Review of research progress on characteristics, detection and localization approaches of fault arc in low voltage DC system. Proc Chin Soc Electr Eng. 40(18), 6015-6026
  14. Chen, S.W., Ge, H.J., Li, H., et al.: Hierarchial deep convolution neural networks based on transfer learning for transformer rectifer unit fault diagnosis. Measurement (2021). https://doi.org/10.1016/j.measurement.2020.108257
  15. Cui, P.Y., Li, G.L., Zhang, Q., et al.: A fault arc detection method of a small current grounding system based on VMD-CNN. Power System Protect Control. 49(23), 18-25 (2021)
  16. Li, S. N., Yan, Y. (2021) Fault arc detection based on time and frequency domain analysis and random forest. Proceedings - 2021 International Conference on Computer Network, Electronic and Automation, ICCNEA 2021. 248-252
  17. Li, ZhZh., Qu, N., Li, X.X., et al.: Partial discharge of insulated conductors based on CNN-LSTM of attention mechanisms. J Power Electr. 21(07), 1030-1040 (2021) https://doi.org/10.1007/s43236-021-00239-3
  18. Li, H., Ge, H.J., Yang, H.Q., et al.: An Abnormal trafc aetection model combined bilndrnn with global attention. IEEE access. 10, 30899-30912 (2022) https://doi.org/10.1109/ACCESS.2022.3159550
  19. Sui, H.G., Huang, L.H., Liu, Ch.X.: Detecting building damage caused by earthquake using CBAM-Improved mask R-CNN. Geomat Inform Sci Wuhan Univ. 45(11), 1660-1668 (2020)