DOI QR코드

DOI QR Code

Online health estimation strategy with transfer learning for operating lithium-ion batteries

  • Fang Yao (State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology) ;
  • Defang Meng (State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology) ;
  • Youxi Wu (School of Artificial Intelligence, Hebei University of Technology) ;
  • Yakun Wan (Fengfan Co., Ltd.) ;
  • Fei Ding (State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology)
  • Received : 2022.09.29
  • Accepted : 2023.01.26
  • Published : 2023.06.20

Abstract

Complex power supply operation conditions complicate the degradation process of lithium batteries, which makes the charge-discharge cycle incomplete and the maximum available capacity not easily accessible. Besides, data-driven methods suffer from limited adaptation and possible overfitting. This paper proposes an online health estimation strategy with transfer learning for estimating the state of health (SOH) of batteries under varying charge-discharge depths and current rates. It aims to alleviate the difficulty in estimating SOH for operating batteries, and broaden the application range of the training model. The core of this strategy is a two-domain transfer CNN-LSTM model that estimates targets by transferring the battery degradation trends of multiple constant conditions. First, health indicators (HIs) with relatively high correlations and wide application ranges are extracted from the voltage and current data of the daily charge process. Then HI-based source domain selection criteria are designed. Since the battery experiences full and incomplete-discharged cases leading to various aging rates, a two-domain transfer CNN-LSTM model is designed. Each subnet includes a CNN and an LSTM to accomplish feature adaptation and time series forecasting. The weights of the sub-nets are updated online to track the drift of the time series covariates. Finally, the proposed strategy is verified on target batteries with varying cut-of voltages and currents, which demonstrates notable accuracy and reliability.

Keywords

Acknowledgement

This work was supported by Natural Science Foundation of Hebei Province, Grant No. E202202056.

References

  1. Zhang, Y., Liu, Y., Wang, J., et al.: State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression. Energy 239, 121986 (2022)
  2. Hu, X., Deng, Z., Lin, X., et al.: Research directions for next-generation battery management solutions in automotive applications. Renewable Sustain. Energy 152, 111695 (2021)
  3. Park, S., Ahn, J., Kang, T., et al.: Review of state-of-the-art battery state estimation technologies for battery management systems of stationary energy storage systems. J. Power Electron. 20, 1526-1540 (2020) https://doi.org/10.1007/s43236-020-00122-7
  4. Bian, X., Liu, L., Yan, J.: A model for state-of-health estimation of lithium-ion batteries based on charging profiles. Energy 177, 57-65 (2019) https://doi.org/10.1016/j.energy.2019.04.070
  5. Liu, B., Tang, X., Gao, F.: Joint estimation of battery state-of-charge and state-of-health based on a simplified pseudo-two-dimensional model. Electrochim Acta 344, 136098 (2020)
  6. Yang, J., Xia, B., Huang, W., et al.: Online state-of-health estimation for Lithium-ion-ion batteries using constant-voltage charging current analysis. Appl. Energy 212, 1589-1600 (2018) https://doi.org/10.1016/j.apenergy.2018.01.010
  7. Zhang, S., Hu, X., Xie, S., et al.: Adaptively coordinated optimization of battery aging and energy management in plug-in hybrid electric buses. Appl. Energy 256, 113891 (2019)
  8. Tian, X., Cai, Y., Sun, X., et al.: A novel energy management strategy for plug-in hybrid electric buses based on model predictive control and estimation of distribution algorithm. IEEE/ASME Transact. Mechatron. 27, 4350 (2022)
  9. Wei, Z., Zhao, J., Ji, D., et al.: A multi-timescale estimator for battery state of charge and capacity dual estimation based on an online identified model. Appl. Energy 204, 1264-1274 (2017) https://doi.org/10.1016/j.apenergy.2017.02.016
  10. Wei, Z., Hu, J., He, H., et al.: Embedded distributed temperature sensing enabled multi-state joint observation of smart lithium-ion battery. IEEE Transact. Industrial Electron. 70, 555 (2022)
  11. Wang, D., Zhang, Q., Huang, H., et al.: An electrochemical-thermal model of lithium-ion battery and state of health estimation. J. Energy Storage 47, 103528 (2022)
  12. Wei, Z., Zhao, J., He, H., et al.: Future smart battery and management: Advanced sensing from external to embedded multidimensional measurement. J. Power Sources 489, 229462 (2021)
  13. Li, A.G., West, A.C., Preindl, M.: Towards unified machine learning characterization of lithium-ion-ion battery degradation across multiple levels: a critical review. Appl. Energy 316, 119030 (2022)
  14. Richardson, R.R., Osborne, M.A., Howey, D.A.: Battery health prediction under generalized conditions using a Gaussian process transition model. J. Energy Storage 23, 320-328 (2019) https://doi.org/10.1016/j.est.2019.03.022
  15. Severson, K.A., Attia, P.M., Jin, N., et al.: Data-driven prediction of battery cycle life before capacity degradation. Nat. Energy 4(5), 383-391 (2019) https://doi.org/10.1038/s41560-019-0356-8
  16. Zhang, Y., Peng, Z., Guan, Y., et al.: Prognostics of battery cycle life in the early-cycle stage based on hybrid model. Energy 221, 119901 (2021)
  17. Sun, T., Xu, B., Cui, Y., et al.: A sequential capacity estimation for the Lithium-ion-ion batteries combining incremental capacity curve and discrete Arrhenius fading model. J. Power Sources 484, 229248 (2021)
  18. Liu, H., Wang, P., Cheng, Z.: A novel method based on encoder-decoder framework for li-ion battery state of health estimation. Proc. CSEE 5, 1851-1859 (2021)
  19. Wei, Z., Ruan, H., Li, Y., et al.: Multistage state of health estimation of lithium-ion battery with high tolerance to heavily partial charging. IEEE Trans. Power Electron. 37(6), 7432-7442 (2022) https://doi.org/10.1109/TPEL.2022.3144504
  20. von Bulow, F., Mentz, J., Meisen, T.: State of health forecasting of Lithium-ion batteries applicable in real-world operational conditions. J. Energy Storage 44, 103439 (2021)
  21. Li, Y., Sheng, H., Cheng, Y., et al.: State-of-health estimation of Lithium-ion-ion batteries based on semi-supervised transfer component analysis. Appl. Energy 277, 115504 (2020)
  22. Ma, J., Xu, S., Shang, P., et al.: Cycle life test optimization for different Li-ion power battery formulations using a hybrid remaining-useful-life prediction method. Appl. Energy 262, 114490 (2020)
  23. Ma, J., Shang, P., Zou, X., et al.: A hybrid transfer learning scheme for remaining useful life prediction and cycle life test optimization of different formulation Li-ion power batteries. Appl. Energy 282, 116167 (2021)
  24. Che, Y., Deng, Z., Lin, X., et al.: Predictive battery health management with transfer learning and online model correction. IEEE Trans. Veh. Technol 70(2), 1269-1277 (2021) https://doi.org/10.1109/TVT.2021.3055811
  25. Sheng, H., Zhou, Y., Bai, L., et al.: Transfer state of health estimation based on cross-manifold embedding. J. Energy Storage 47, 103555 (2022)
  26. Deng, Z., Lin, X., Cai, J., et al.: Battery health estimation with degradation pattern recognition and transfer learning. J. Power Sources 525, 231027 (2022)
  27. Deng, Z., Hu, X., Lin, X., et al.: General discharge voltage information-enabled health evaluation for lithium-ion batteries. IEEE/ASME Trans. Mechatron. 26(3), 1295-1306 (2020) https://doi.org/10.1109/TMECH.2020.3040010
  28. Wu, Q., Wu, H., Zhou, X., et al.: Online transfer learning with multiple homogeneous or heterogeneous sources. IEEE Trans. Knowl. Data Eng. 29(7), 1494-1507 (2017) https://doi.org/10.1109/TKDE.2017.2685597
  29. Ye, R., Dai, Q.: A novel transfer learning framework for time series forecasting. Knowl.-Based Syst. 156, 74-99 (2018) https://doi.org/10.1016/j.knosys.2018.05.021
  30. Dai, Y., Wang, S., Chen, X.: Generative adversarial networks based on Wasserstein distance for knowledge graph embeddings. Knowl.-Based Syst. 190, 105165 (2020)
  31. Li, Y., Wang, N., Shi, J., et al.: Adaptive Batch Normalization for practical domain adaptation. Pattern Recogn. 80, 109-117 (2018) https://doi.org/10.1016/j.patcog.2018.03.005
  32. Du, Y., Wang, J., Feng, W., et al., AdaRNN: adaptive learning and forecasting of time series. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 402-411 (2021)
  33. Yu C, Wang J, Chen Y, et al. Transfer learning with dynamic adversarial adaptation network. 2019 IEEE International Conference on Data Mining (ICDM). IEEE, 778-786 (2019)
  34. Tang, Y., Qu, A., Chow, A., et al.: Domain adversarial spatial-temporal network: a transferable framework for short-term traffic forecasting across. Cities (2022). https://doi.org/10.48550/arXiv.2202.03630