DOI QR코드

DOI QR Code

Anomaly Detection System for Solar Power Distribution Panels utilizing Thermal Images

  • Kwang-Seong Shin (Department of Computer Engineering, Sunchon National University) ;
  • Jong-Chan Kim (Department of Computer Engineering, Sunchon National University) ;
  • Seong-Yoon Shin (School of Computer Science and Engineering, Kunsan National University)
  • Received : 2024.04.29
  • Accepted : 2024.05.11
  • Published : 2024.06.30

Abstract

This study aimed to develop an advanced anomaly-detection system tailored for solar power distribution panels using thermal imaging cameras to ensure operational stability. It addresses the imperative shift toward digitalized safety management in electrical facilities, transcending the limitations of conventional empirical methodologies. Our proposed system leverages a faster R-CNN-based artificial intelligence model optimized through meticulous hyperparameter tuning to efficiently detect anomalies in distribution panels. Through comprehensive experimentation, we validated the efficacy of the system in accurately identifying anomalies, thereby propelling safety protocols forward during the fourth industrial revolution. This study signifies a significant stride toward fortifying the integrity and resilience of solar power distribution systems, which is pivotal for adapting to emerging technological paradigms and evolving safety standards in the energy sector. These findings offer valuable insights for enhancing the reliability and efficiency of safety management practices and fostering a safer and more sustainable energy landscape.

Keywords

References

  1. M. Panthi, "Anomaly detection in smart grids using machine learning techniques," in 2020 First International Conference on Power, Control and Computing Technologies (ICPC2T), pp. 220-222, 2020. DOI: 10.1109/ICPC2T48082.2020.9071434.
  2. J. Mulongo, M. Atemkeng, T. Ansah-Narh, R. R. Rockefeller, G. M. Nguegnang, and M. A. Garuti, "Anomaly detection in power generation plants using machine learning and neural networks," Applied Artificial Intelligence, vol. 34, no. 1, pp. 64-79, 2020. DOI: https://doi.org/10.1080/08839514.2019.1691839.
  3. A. Gholami and A. K. Srivastava, "Comparative analysis of ml techniques for data-driven anomaly detection, classification and localization in distribution system," in 2020 52nd North American Power Symposium (NAPS) IEEE, pp. 1-6, 2021. DOI: 10.1109/NAPS50074.2021.9449712.
  4. M. Ibrahim, A. Alsheikh, F. M. Awaysheh, and M. D. Alshehri, "Machine learning schemes for anomaly detection in solar power plants," Energies, vol. 15, no. 3, pp. 1082, 2022. DOI: https://doi.org/10.3390/en15031082.
  5. A. G. Imenes, N. S. Noori, O. A. N. Uthaug, R. Kroni, F. Bianchi, and N. Belbachir, "A deep learning approach for automated fault detection on solar modules using image composites," in 2021 IEEE 48th Photovoltaic Specialists Conference (PVSC) IEEE, pp. 1925-1930, 2021. DOI: 10.1109/PVSC43889.2021.9518540.
  6. N.H. Ishak, M. A. I. Halim, and I. S. Isa, "Detection of Power Distribution Fault in Thermal Images Using CNN," in Intelligent Multimedia Signal Processing for Smart Ecosystems, Cham: Springer International Publishing, pp. 267-287, 2023. DOI: https://doi.org/10.1007/978-3-031-34873-0_11.
  7. B. V. Charitha and T. Ananthan, "Machine learning based fault detection in induction motor using thermal imaging," in 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC) IEEE, pp. 929-936, 2022. DOI: 10.1109/ICESC54411.2022.9885282.
  8. C. Wei, "Power grid facility thermal fault diagnosis via object detection with synthetic infrared imagery," in 2021 3rd International Conference on Electrical Engineering and Control Technologies (CEECT) IEEE, pp. 217-221, 2021. DOI: 10.1109/CEECT53198.2021.9672631.
  9. J. H. Syu, J. C. W. Lin, and G. Srivastava, "AI-Based Electricity Grid Management for Sustainability, Reliability, and Security," IEEE Consumer Electronics Magazine, 2023. DOI: 10.1109/MCE.2023.3264884.
  10. Y. Himeur, K. Ghanem, A. Alsalemi, F. Bensaali, and A. Amira, "Artificial intelligence-based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives," Applied Energy, vol. 287, pp. 116601, 2021. DOI: https://doi.org/10.1016/j.apenergy.2021.116601.
  11. C. Park, J. Lee, Y. Kim, J. G. Park, H. Kim, and D. Hong, "An enhanced AI-based network intrusion detection system using generative adversarial networks," IEEE Internet of Things Journal, vol. 10, no. 3, pp. 2330-2345, 2022. DOI: 10.1109/JIOT.2022.3211346.
  12. S. Voronov, "Machine learning models for predictive maintenance," Doctoral dissertation, Linkoping University Electronic Press, 2020. DOI: 10.3384/diss.diva-162649.
  13. V. Vita, G. Fotis, V. Chobanov, C. Pavlatos, and V. Mladenov, "Predictive maintenance for distribution system operators in increasing transformers' reliability," Electronics, vol. 12, no. 6, pp. 1356, 2023. DOI: https://doi.org/10.3390/electronics12061356.
  14. L. I. Alvarez Quinones, C. A. Lozano-Moncada, and D. A. Bravo Montenegro, "Machine learning for predictive maintenance scheduling of distribution transformers," Journal of Quality in Maintenance Engineering, vol. 29, no. 1, pp. 188-202, 2023. DOI: https://doi.org/10.1108/JQME-06-2021-0052.
  15. R. Bin Mofidul, M. M. Alam, M. H. Rahman, and Y. M. Jang, "Realtime energy data acquisition, anomaly detection, and monitoring system: Implementation of a secured, robust, and integrated global IIoT infrastructure with edge and cloud AI," Sensors, vol. 22, no. 22, pp. 8980, 2022. DOI: https://doi.org/10.3390/s22228980.
  16. A. Vijayakumar and S. Vairavasundaram, "YOLO-based Object Detection Models: A Review and its Applications," Multimedia Tools and Applications, pp. 1-40, 2024. DOI: https://doi.org/10.1007/s11042-024-18872-y.
  17. D. G. Choe and D. K. Kim, "Deep learning-based image data processing and archival system for object detection of endangered species," Journal of Information and Communication Convergence Engineering, vol. 18, no. 4, pp. 267-277, 2020. DOI: https://doi.org/10.6109/jicce.2020.18.4.267.
  18. R. Rijayanti, R. F. Muhammad, and M. Hwang, "Vehicle waiting time information service using vehicle object detection at fuel charging station," Journal of Information and Communication Convergence Engineering, vol. 18, no. 3, pp. 147-154, 2020. DOI: https://doi.org/10.6109/jicce.2020.18.3.147.