The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Battery thermal runaway cell detection using DBSCAN and statistical validation algorithms

DBSCAN과 통계적 검증 알고리즘을 사용한 배터리 열폭주 셀 탐지

  • 김진근 (가천대학교 IT융합학과) ;
  • 윤유림 (가천대학교 컴퓨터공학과)
  • Received : 2023.07.12
  • Accepted : 2023.09.05
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Lead-acid Battery is the oldest rechargeable battery system and has maintained its position in the rechargeable battery field. The battery causes thermal runaway for various reasons, which can lead to major accidents. Therefore, preventing thermal runaway is a key part of the battery management system. Recently, research is underway to categorize thermal runaway battery cells into machine learning. In this paper, we present a thermal runaway hazard cell detection and verification algorithm using DBSCAN and statistical method. An experiment was conducted to classify thermal runaway hazard cells using only the resistance values as measured by the Battery Management System (BMS). The results demonstrated the efficacy of the proposed algorithms in accurately classifying thermal runaway cells. Furthermore, the proposed algorithm was able to classify thermal runaway cells between thermal runaway hazard cells and cells containing noise. Additionally, the thermal runaway hazard cells were early detected through the optimization of DBSCAN parameters using a grid search approach.

납축전지는 가장 오래된 충전식 배터리 시스템으로 현재까지 충전식 배터리 분야에서 자리를 지키고 있다. 이 배터리는 다양한 이유로 열폭주 현상이 생기는데 이는 큰 사고로 이어질 가능성이 있다. 그렇기 때문에 열폭주 현상을 예방하는 것은 배터리 관리 시스템의 핵심부분이다. 최근에는 열폭주 위험 배터리 셀을 기계학습으로분류하는 연구가 진행 중이다. 본 논문에서는 비지도학습인 DBSCAN 클러스터링과 통계적 방법을 사용하여 열폭주 위험 셀 탐지 및 검증 알고리즘을 제안하였다. BMS에서 측정한 lead-acid 배터리의 저항 값만을 사용하여 열폭주 위험 셀 분류 실험을 진행하였고 본 논문에서 제안한 알고리즘이 열폭주 위험 셀을 정확히 검출해 냄을 보여주었다. 또한 본 논문에서 제안한 알고리즘을 사용하여 배터리 내 열폭주 위험이 있는 셀과 노이즈가 심한 셀을 분류할 수 있었으며 그리드 서치를 통한 DBSCAN 파라미터 최적화를 통해 열폭주 위험 셀을 초기에 검출해 낼 수 있었다.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No.2022R1F1A1066017)

References

  1. Wang, Z. H., Hendrick, Horng, G. J., Wu, H. T., & Jong, G. J., "A prediction method for voltage and lifetime of lead-acid battery by using machine learning," Energy Exploration & Exploitation, Vol. 38, No.1, pp.310-329, 2020. DOI :10.1177/01445987198811223
  2. Voronov, S., Frisk, E., Krysander, M., "Lead-acid battery maintenance using multilayer perceptron models," proc. of the 2018 ieee international conference on prognostics and health management (icphm), pp. 1-8, 2018. DOI : 10.1109/ICPH.2018.8448472
  3. Weighall, M. J., "Techniques for jar formation of valve-regulated lead-acid batteries," Journal of power sources, Vol.116, No.1-2, pp. 219-231, 2003. DOI : 10.1016/S0378-7753(02)00706-1
  4. Matrakova, M., Pavlov, D., "Thermal analysis of lead-acid battery pastes and active materials," Journal of power sources, Vol.158, No.2, pp. 1004-1011, 2006. DOI : 10.1016/j.jpowsour.2005.11.007
  5. Liu, X., & Wang, W., "VRLA battery system-reliability and proactive maintenance," proc. of the Intelec 2010 , pp. 1-7, 2010. DOI :10.1109/INTLEC.2010.5525726
  6. Rand, D. A. J., Holden, L. S., May, G. J., Newnham, R. H., Peters, K., "Valve-regulated lead/acid batteries,"Journal of Power Sources, Vol.59, No.1-2, pp. 191-197, 1996. DOI : 10.1016/0378-7753(96)02322-1
  7. Culpin, B., "Thermal runaway in valve-regulated lead-acid cells and the effect of separator structure," Journal of Power Sources, Vol.13 , No.1, pp. 79-86, 2004. DOI : 10.1016/j.jpowsour.2003.09.078
  8. McMenamin, D., "Thermal Runaway-A system solution for a system problem," proc. of the Fourteenth International Telecommunications Energy Conference-INTELEC'92, pp. 18-21, 1992. DOI : 10.1109/INTLEC.1992.268469
  9. Rutledge, W. T., Bowers, R. J., "Electrical energy distributions in VR battery applications that can trigger thermal runaway," proc. of the Intelec 94 , pp. 168-171, 1994. DOI : 10.1109/INTLEC.1994.396659
  10. Culpin, B., & Rand, D. A. J., "Failure modes of lead/acid batteries," Journal of power sources, Vol.36, No.4, pp. 415-438, 1991. DOI : 10.1016/0378-7753(91)80069-A
  11. Diao, W., Naqvi, I. H., Pecht, M., "Early detection of anomalous degradation behavior in lithium-ion batteries," Journal of Energy Storage, Vol. 32 pp. 101710. DOI : 10.1016/j.est.2020.101710
  12. Ossai, C. I., Egwutuoha, I. P., "Anomaly Detection and Extra Tree Regression for Assessment of the Remaining Useful Life of Lithium-Ion Battery," Proc. of the International Conference on Advanced Information Networking and Applications, pp. 1474-1488, 2020.
  13. Samanta, A., Chowdhuri, S., Williamson, S. S., "Machine learning-based data-driven fault detection/diagnosis of lithium-ion battery: A critical review," Electronics, Vol. 10, No.11, pp. 1309, 2021. DOI : 10.3390/electronics10111309
  14. Celik, M., Dadaser-Celik, F., Dokuz, A. S., "Anomaly detection in temperature data using DBSCAN algorithm," proc. of the 2011 international symposium on innovations in intelligent systems and applications, pp. 91-95, 2011.
  15. Chesnokov, M. Y., "Time series anomaly searching based on DBSCAN ensembles," Scientific and Technical Information Processing, Vol. 46, No.5, pp.299-305, 2019. https://doi.org/10.3103/S0147688219050010
  16. Li, D., Zhang, Z., Liu, P., Wang, Z., "DBSCAN-based thermal runaway diagnosis of battery systems for electric vehicles," Energies, Vol. 12, No. 15, pp. 2977, 2019. DOI : 10.3390/en12152977
  17. Feng, X., Zhang, X., Xiang, Y., "An inconsistency assessment method for backup battery packs based on time-series clustering," Journal of Energy Storage, Vol.31 pp. 101666, 2020. DOI : 10.1016/j.est.2020.101666
  18. Li, D., Zhang, Z., Liu, P., Wang, Z., & Zhang, L. "Battery fault diagnosis for electric vehicles based on voltage abnormality by combining the long short-term memory neural network and the equivalent circuit model," IEEE Transactions on Power Electronics, Vol. 36 No. 2, pp. 1303-1315. DOI : 10.1109/TTE.2021.3117841
  19. Haider, S. N., Zhao, Q., Li, X., "Data driven battery anomaly detection based on shape based clustering for the data centers class," Journal of Energy Storage, Vol. 29, pp. 101479, 2020. DOI : 10.1016/j.est.2020.101479
  20. Choi, H. S., Choi, J. W., Whangbo, T. K., "Design and Development of a Battery State of Health Estimation Model for Efficient Battery Monitoring Systems," Sensors, Vol. 22, No. 12, pp. 444, 2022. DOI : 10.3390/s22124444
  21. Ceraolo, M., "New dynamical models of lead-acid batteries," IEEE transactions on Power Systems, Vol. 15, No. 4, pp. 1184-1190, 2000. DOI : 10.1109/59.898088
  22. Moubayed, N., Kouta, J., El-Ali, A., Dernayka, H., Outbib, R., "Parameter identification of the lead-acid battery model," proc. of the 2008 33rd IEEE Photovoltaic Specialists Conference, pp. 1-6, 2008.
  23. Hyperphysics. [Online]. http://hyperphysics.phy-astr.gsu.edu/hbase/electric/leadacid.html, (download 2021, December 17)
  24. Samuel, A. L., "Some studies in machine learning using the game of checkers II-Recent progress," IBM Journal of research and development, Vol. 11, No. 6, pp. 601-617, 1967. DOI : 10.1147/rd.116.0601
  25. El Naqa, I., Murphy, M.J.. Machine Learning in Radiation Oncology, pp. 3-11, Newyork, 2015.
  26. Caruana, R., Niculescu-Mizil, A., "An empirical comparison of supervised learning algorithms," proc. of the 23rd international conference on Machine learning, pp. 161-168, 2006.
  27. Van Der Maaten, L., Postma, E., Van den Herik, J., "Dimensionality reduction: a comparative," J Mach Learn Res, Vol. 10, No. 66-71, pp. 13, 2009.
  28. Kumbhare, T. A., Chobe, S. V., "An overview of association rule mining algorithms," International Journal of Computer Science and Information Technologies, Vol. 5, No. 1, pp. 927-930,
  29. Ester, M., Kriegel, H. P., Sander, J., Xu, X., "A density-based algorithm for discovering clusters in large spatial databases with noise," proc. of the kdd, pp. 226-231, 1996.
  30. Khan, K., Rehman, S. U., Aziz, K., Fong, S., Sarasvady, S., "DBSCAN: Past, present and future," proc. of the fifth international conference on the applications of digital information and web technologies (ICADIWT 2014), pp. 232-238, 2014. DOI : 10.1109/ICADIWT.2014.6814687
  31. Duan, L., Xu, L., Guo, F., Lee, J., Yan, B., "A local-density based spatial clustering algorithm with noise," Information systems.
  32. Ankerst, M., Breunig, M. M., Kriegel, H. P., Sander, J., "OPTICS: Ordering points to identify the clustering structure," ACM Sigmod record, Vol. 28, No. 2, pp. 49-60, 1999. https://doi.org/10.1145/304181.304187
  33. Paparrizos, J., Gravano, L., "k-shape: Efficient and accurate clustering of time series," proc. of the 2015 ACM SIGMOD international conference on management of data, pp. 1855-1870, 2015.
  34. Lee, Y. H., Wei, C. P., Cheng, T. H., & Yang, C. T., "Nearest-neighbor-based approach to time-series classification," Decision Support Systems, Vol. 53, No. 1, pp. 207-217, 2012. DOI : 10.1016/j.dss.2011.12.014
  35. Niennattrakul, V., Ratanamahatana, C. A., "On clustering multimedia time series data using k-means and dynamic time warping," proc. of the 2007 International Conference on Multimedia and Ubiquitous Engineering (MUE'07), pp. 733-738, 2007.
  36. He, L., Agard, B., Trepanier, M., "A classification of public transit users with smart card data based on time series distance metrics and a hierarchical clustering method," Transportmetrica A: Transport Science, Vol. 16, No. 1, pp. 56-75, 2020. DOI : 10.1080/23249935.2018.1479722
  37. Guan, Y., Ghorbani, A. A., Belacel, N., "Y-means: a clustering method for intrusion detection," proc. of the CCECE 2003-Canadian Conference on Electrical and Computer Engineering, pp. 1083-1086, 2003. DOI : 10.1109/CCECE.2003.1226084