DC ARC FAULT DIAGNOSIS IN THREE-PHASE INVERTERS USING MACHINE LEARNING MODELS COMBINED WITH FREQUENCY COMPONENT EXTRACTION TECHNIQUE
DOI:
https://doi.org/10.62985/j.huit_ojs.vol26.no1E.353Keywords:
DC series arc fault, frequency component extraction, machine learning.Abstract
DC series arc faults pose a significant concern due to their potential to cause fires and inflict detrimental consequences on power systems if left undetected. However, their detection in real-world power systems remains challenging, primarily attributed to the low arc current magnitude, the absence of zero-crossing periods, and the manifestation of diverse abnormal behaviors influenced by a variety of loads and power controllers. Notably, conventional protective measures, particularly fuses, may not effectively operate to trigger timely responses in the event of DC series arc faults. The repercussions of undetected arc faults are severe, potentially leading to malfunctioning operations in power systems, thereby increasing the risk of property damage and human casualties. In response to these pressing demands, developing an effective detection mechanism targeting DC series arc faults in DC systems emerges as a paramount task. In this study, the integration of frequency component extraction and machine learning techniques is employed for DC arc fault diagnosis. The diagnostic results demonstrate the efficacy of the proposed detection mechanism and enhance the accuracy of arc fault identification.
References
[1] H. -P. Park and S. Chae, “DC series arc fault detection algorithm for distributed energy resources using arc fault impedance modeling”, IEEE Access, vol. 8, 2020, 179039-179046, doi: http://doi.org/10.1109/ACCESS.2020.3027869.
[2] R. Ferrero, M. Collotta, M.V. Bueno-Delgado, and H.-C. Chen, “Smart management energy systems in industry 4.0”, Energies, vol. 13, no. 2, 2020, 382. https://doi.org/10.3390/en13020382
[3] L. Frosini, “Novel diagnostic techniques for rotating electrical machines—A review”, Energies, vol. 13, no. 19, 2020, 5066, doi: https://doi.org/10.3390/en13195066
[4] S. Dhar, R. K. Patnaik, and P. K. Dash, “Fault detection and location of photovoltaic based DC microgrid using differential protection strategy”, IEEE Trans. Smart Grid, vol. 9, no. 5, 2018, 4303–4312. http://doi.org/10.1109/TSG.2017.2654267
[5] V. Psaras et al., “Review of DC series arc fault testing methods and capability assessment of test platforms for more-electric aircraft,” in IEEE Transactions on Transportation Electrification, vol. 8, no. 4, pp. 4654-4667, Dec. 2022, doi: http://doi.org/10.1109/TTE.2022.3189970
[6] UL 1699B, “Outline of Investigation for Photovoltaic (PV) DC Arc-Fault Circuit Protection, Issue 2; Underwriters Laboratories, Inc.: Northbrook, IL, USA, (2013).
[7] T. Cover and P. Hart, “Nearest neighbor pattern classification”, IEEE Transactions on Information Theory, vol. 13, no. 1, 1967, 21-27. http://doi.org/10.1109/TIT.1967.1053964.
[8] L. Breiman, J. Friedman, R. Olshen, and C. Stone, “Classification and Regression Trees. Belmont, CA: Wadsworth and Brooks, (1984). https://doi.org/10.1201/9781315139470
[9] L. Breiman, “Random forests”, Mach. Learn., vol. 45, 2001, 5–32. https://doi.org/10.1023/A:1010933404324
[10] P. Langley, W. Iba, and K. Thompson, “An analysis of Bayesian classifiers,” in Proceedings of the 10th National Conference on Artificial Intelligence (AAAI), 1992, pp. 223–228.
