Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Data quality augmentation and parallel network modeling for residual life prediction of lithium-ion batteries

  • Shuai Huang (College of Mechanical and Vehicle Engineering, Taiyuan University of Technology) ;
  • Junxia Li (College of Mechanical and Vehicle Engineering, Taiyuan University of Technology) ;
  • Lei Wu (College of Mechanical and Vehicle Engineering, Taiyuan University of Technology) ;
  • Wei Zhang (College of Mechanical and Vehicle Engineering, Taiyuan University of Technology)
  • Received : 2023.08.31
  • Accepted : 2024.01.14
  • Published : 2024.06.20
⟨ Previous Next ⟩

Abstract

Research on the data-driven health state estimation of lithium-ion batteries has gained significant attention in recent years. However, the practical implementation of obtaining one data point in one cycle has resulted in poor data quality, leading to low accuracy and prediction instability. To overcome this challenge, a two-step approach is proposed. First, available data are enriched using Akima spline curve interpolation, and the overall degradation trend of the battery is extracted as a Sigmoid function, enhancing the data quality. Second, a parallel network model that combines the strengths of the convolutional neural network (CNN) and the long short-term memory network (LSTM) is introduced. This model leverages the ability of one-dimensional convolutional neural network (1DCNN) to effectively capture local features and proficiency of the LSTM in capturing long-term dependencies. By employing this hybrid model, a better understanding and prediction of the remaining battery life is achieved. Finally, based on the NASA public battery dataset, expanded and decomposed data are trained and predicted by the parallel network model. Experimental results demonstrate that the proposed method exhibits high accuracy and strong generalization capability.

Keywords

Acknowledgement

This work is supported by the National Natural Science Foundation of China (52174147), the Central Guidance on Local Science and Technology Development Fund of Shanxi Province (YDZJSX2021A023), and the Key Scientific and Technological Research and Development Plan of JinZhong City (Y211017). The authors are grateful to the NASA Research Center's Idaho National Laboratory for sharing the lithium battery data.

References

  1. Luo, F., Huang, H.H., Wang, H.X.: Fast prediction of charge state and health status of retired power batteries based on electrochemical impedance spectroscopy. J. Instrum. 42(9), 172-180 (2021)
  2. Ke, K., Yuedong, S., Dongsheng, R., et al.: An efficient modeling approach for electrochemical-thermal coupling of automotive lithium-ion batteries. J. Mech. Eng. 57(14), 10-22 (2021)
  3. Liu, J., Wang, W., Ma, F., et al.: A data-model-fusion prognostic framework for dynamic system state forecasting. Eng. Appl. Artif. Intell. 25(4), 814-823 (2012)
  4. Liu, Z.Y., Zhu, C.C., You, Y., Yao, L.Y.: A combined model for lithium-ion batteries accounting for temperature and cycle number for SOC estimation[J]. J. Instrum. 40(11), 117-127 (2019)
  5. Lee, C. H., Chen, M. Y., Hsu, S. H., et al.: Implementation of an SOC-based four-stage constant current charger for Li- ion batteries. J. Energy Storage, 2018.
  6. Ran, W., Qulin, H., Ruyu, S. Yanxiang, Z. Xiong, H.: A residual life prediction method for lithium batteries based on variational modal decomposition and integrated depth model. J. Instrumentation, 42(04):111-120 (2021)
  7. He, Y., Shen, J., Shen, J., et al.: State of health estimation of lithium?ion batteries: A multiscale Gaussian process regression modeling approach. Aiche J, 61(5) (2015).
  8. Wu, Y., Xue, Q., Shen, J., et al.: State of health estimation for lithium-ion batteries based on healthy features and long short-term memory. IEEE Access, PP (99):1-1 (2020).
  9. Yanmei, L., Huihan, L., Chaolong, Z., Laijin, L. A double Gaussian model-based method for predicting the remaining service life of lithium batteries. J. Electr. Eng.:1-9.
  10. Jinyue, P., Yuntong, M. Datong, L. Peng, Y.: Indirect prediction method for remaining life of lithium-ion batteries. China Sci. Technol. Paper, 9(01):28-36 (2014).
  11. Jiang, Y., Liu, Z., Luo, H., et al. An indirect ELM prediction method for the remaining life of lithium batteries. J. Electron. Measure. Instrumentation, 30(2):7 (2016).
  12. Yang, S.-Y., Tian, Y., Tian, J.-D.: SOH estimation for lithium-ion batteries based on iCEEMDAN and migration learning. J. Electr. Eng.:1-9.
  13. Fan, L., Wang, P., Cheng, Z.: A remaining capacity estimation approach of lithium-ion batteries based on partial charging curve and health feature fusion. J. Energy Storage, 2021(Nov.):43.
  14. Yanru, Y. Wen, J., Yuanhao, S. et al.: Remaining life prediction of lithium-ion batteries based on CEEMDAN and SVR. J. Electron. Measure. Instrumentation, 2020.
  15. Gao, D., Huang, M.: Prediction of remaining useful life of lithium-ion battery based on multi-kernel support vector machine with particle swarm optimization. J. Power Electron., 2017, 17(5):https://doi.org/10.6113/JPE.2017.17.5.1288.
  16. Zhang, K., Zhao, P., Sun, C.: Remaining useful life prediction of aircraft lithium-ion batteries based on F-distribution particle filter and kernel smoothing algorithm[J]. Chin. J. Aeronaut. 33(5), 15 (2020)
  17. Lu, C., Tao, L., Fan, H.: Li-ion battery capacity estimation: a geometrical approach. J. Power Sources, 261(sep.1):https://doi.org/10.1016/j.jpowsour.2014.03.058. (2014)
  18. Ullah, M.S., Seo, K.: Prediction of lithium-ion battery capacity by functional principal component analysis of monitoring data, Appl. Sci.-Basel, 2: https://doi.org/10.3390/app12094296. (2022)
  19. Chen, D., Zhang, J., Jiang, S.: Forecasting the short-term metro ridership with Seasonal and Trend decomposition using Loess and LSTM neural networks. IEEE Access, PP (99):1-1. (2020)
  20. Hao, H., Yu, F., Li, Q.: Soil temperature prediction using convolutional neural network based on ensemble empirical mode decomposition. IEEE Access, PP (99):1-1. (2020)
  21. Kesiman, M., Maysanjaya, I. M. D.: A model for post transliteration suggestion for balinese palm leaf manuscript with text generation and LSTM model. J. Phys., 1810(1):012011 (9pp), (2021)
  22. Sun, H., Zhao, S. Fault diagnosis for bearing based on 1DCNN and LSTM. Hindawi Limited, 2021.
  23. Razavian, A. S., Azizpour, H., Sullivan, J., et al.: CNN Features of-the-shelf: an astounding baseline for recognition. In: 2014 IEEE conference on computer vision and pattern recognition workshops. IEEE, 2014.
  24. Hussein, A. A., Batarseh, I.: A review of charging algorithms for nickel and lithium battery chargers, IEEE Trans. Veh. Technol. 60 (March (no. 3)) (2011) 480-838.
  25. Shen, W., Vo, T.T., Kapoor, A.: Charging algorithms of lithium-ion batteries: an overview. In: Proceedings of IEEE Conference on Ind. Electron. and Appl. Singapore, July 18-20, 2012.