한국전자통신학회논문지 (The Journal of the Korea institute of electronic communication sciences)

한국전자통신학회 (Korea Institute of Electronic Communication Science)
권호 표지
DOI QR코드

DOI QR Code

선형회귀 및 ARIMA 모델을 이용한 배터리 사용자 패턴 변화 추적 연구

A study of Battery User Pattern Change tracking method using Linear Regression and ARIMA Model

  • 박종용 (서울과학기술대학교 정보통신미디어공학과) ;
  • 유민혁 (서울과학기술대학교 정보통신미디어공학과) ;
  • 노태민 (서울과학기술대학교 미디어IT공학과) ;
  • 신대견 (서울과학기술대학교 정보통신미디어공학과) ;
  • 김성권 (서울과학기술대학교 정보통신미디어공학과)
  • 투고 : 2022.04.07
  • 심사 : 2022.06.17
  • 발행 : 2022.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

전기자동차는 운전자가 바뀌거나 운전자의 주행습관이 바뀜에 따라 SOH가 급격하게 감소할 수 있고, 이러한 운전습관은 배터리에 과부하를 주어 배터리 수명의 단축 및 안전 문제를 일으킬 수 있다. 본 논문에서는 전기자동차의 계기판에 사용자 패턴 변화에 따른 SOH의 변화를, 실시간으로 나타내기 위하여, NASA에서 제공하는 배터리 데이터 세트를 학습하고, 기계학습 모델을 구축 후, 변화된 사용자 패턴을 포함한 배터리에 대해 선형회귀와 ARIMA 모델로 예측하는 실험을 진행하였다. 그 결과, 변화된 사용자 패턴에 따른 변경된 수명을 예측하는 경우, 배터리 데이터가 많이 확보되었다면 선형회귀가 유용하고, 데이터가 많이 확보되지 않은 경우는 ARIMA 모델이 대안이 될 수 있다는 연구결과를 얻을 수 있었다.

This paper addresses the safety concern that the SOH of batteries in electric vehicles decreases sharply when drivers change or their driving patterns change. Such a change can overload the battery, reduce the battery life, and induce safety issues. This paper aims to present the SOH as the changes on a dashboard of an electric vehicle in real-time in response to user pattern changes. As part of the training process I used battery data among the datasets provided by NASA, and built models incorporating linear regression and ARIMA, and predicted new battery data that contained user changes based on previously trained models. Therefore, as a result of the prediction, the linear regression is better at predicting some changes in SOH based on the user's pattern change if we have more battery datasets with a wide range of independent values. The ARIMA model can be used if we only have battery datasets with SOH data.

키워드

과제정보

이 연구는 서울과학기술대학교 교내 일반과제 연구비 지원으로 수행되었습니다.

참고문헌

  1. J. Joo, Y. Lee, K. Park, and J. Oh, "ESS optimization and stable operation for battery level calculation and failure prediction algorithm," Journal of the Korea Institute of Electronic Communication Sciences, vol. 15, no. 1, 2020, pp. 71-78. https://doi.org/10.13067/JKIECS.2020.15.1.71
  2. S. Park and J. Lee, "Design of Smart Off-Board Charge System for Neighborhood Electric Vehicle," Journal of the Korea Institute of Electronic Communication Sciences, vol. 8, no. 10, 2013, pp. 1499-1504. https://doi.org/10.13067/JKIECS.2013.8.10.1499
  3. P. Lee, S. Kwon, D. Kang, S. Han, and J. Kim, "SOH Estimation and Feature Extraction using Principal Component Analysis based on Health Indicator for High Energy Battery Pack," The Korean Institute of Power Electronics, vol. 25, no. 5, Oct. 2020, pp. 376-384.
  4. S. Kim, J. Park, and J. Kim, "Prediction Algorithm for Lithium Ion Battery SOH Based on ARIMA Model," Proceedings of the KIPE Conference, Yesan, Korea, July 2019, pp. 56-58.
  5. D. Andre, C. Appel, T. Soczka-Guth, and D. U. Sauer, "Advanced mathematical methods of SOC and SOH estimation for lithium-ion batteries," Journal of power sources. vol. 224, Feb 2013, pp. 20-27. https://doi.org/10.1016/j.jpowsour.2012.10.001
  6. H. Go, S. Lee, and E. Kim, "LSTM Model-Based SOH Prediction for Lithium-Ion Battery," Digital Contents Society, vol. 22, no. 4, Apr. 2021, pp. 697-703. https://doi.org/10.9728/dcs.2021.22.4.697
  7. S. Kwon, D. Han, S. Park, and J. Kim, "Long Short Term Memory-Based State-of-Health Prediction Algorithm of a Rechargeable Lithium-Ion Battery for Electric Vehicle," The Trans. of the Korean Institute of Electrical Engineers(KIEE), vol. 68, no. 10, pp. 1214-1221. https://doi.org/10.5370/kiee.2019.68.10.1214
  8. K. M. Adib, C. Angela, and W. Lim, N. J. Nkechinyere, "SOH and RUL Prediction of Lithium-Ion Batteries Based on LSTM with Ensemble Health Indicators," KICS Summer Conference 2020 Proceedings, Pyeongchang, Korea, vol. 72, Aug. 2020, pp. 317-318.
  9. B. Kim and J. Kim, "An Optimal Design Method of a Linear Generator for Conversion of Wave Energy," Journal of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 6, Dec. 2021, pp. 1195-1204. https://doi.org/10.13067/JKIECS.2021.16.6.1195
  10. J. Choi, "Performance Comparison of Machine Learning in the Prediction for Amount of Power Market," Journal of the Korea Institute of Electronic Communication Sciences, vol. 14, no. 5, 2019, pp. 943-950. https://doi.org/10.13067/JKIECS.2019.14.5.943
  11. G. Bak and C. Bae, "Performance Comparison of Machine Learning in the Various Kind of Prediction," Journal of the Korea Institute of Electronic Communication Sciences, vol.14, no.1, 2019, pp. 169-178. https://doi.org/10.13067/JKIECS.2019.14.1.169
  12. K. Goebel, B. Saha, and A. Saxena, "Prognostics in battery health management," IEEE Trans. Instrum. Meas, vol. 11, no. 4, Nov. 2008, pp. 33-40. https://doi.org/10.1109/MIM.2008.4579269
  13. T. Qin, S. Zeng, J. Guo, and Z. Skaf, "A rest time-based prognostic framework for state of health estimation of lithium-ion batteries with regeneration phenomena," Energies, vol. 9 no. 11, 2016, pp. 896. https://doi.org/10.3390/en9110896
  14. S. Kang, T. Noh, and B. Lee, "Machine Learning-based SOH Estimation Algorithm Using a Linear Regression Analysis," The Trans. of the Korean Institute of Power Electronics, vol. 26, no. 4, 2021, pp. 241-248. https://doi.org/10.6113/TKPE.2021.26.4.241