Journal of Power Electronics

  • 제24권8호
  • /
  • Pages.1329-1339
  • /
  • 2024
  • /
  • 1598-2092(pISSN)
  • /
  • 2093-4718(eISSN)
전력전자학회 (The Korean Institute of Power Electronics)
권호 표지
DOI QR코드

DOI QR Code

Combined EKF-LSTM algorithm-based enhanced state-of-charge estimation for energy storage container cells

  • Zidi Yu (School of Electrical and Information Engineering, Wuhan Institute of Technology) ;
  • Jian Liu (School of Electrical and Information Engineering, Wuhan Institute of Technology) ;
  • Yuchen Lu (School of Electrical and Information Engineering, Wuhan Institute of Technology) ;
  • Chengzhi Feng (School of Electrical and Information Engineering, Wuhan Institute of Technology) ;
  • Letian Li (School of Electrical and Information Engineering, Wuhan Institute of Technology) ;
  • Qi Wu (School of Electrical and Information Engineering, Wuhan Institute of Technology)
  • 투고 : 2023.06.27
  • 심사 : 2024.03.15
  • 발행 : 2024.08.20
⟨ 이전 논문 다음 논문 ⟩

초록

The core equipment of lithium-ion battery energy storage stations is containers composed of thousands of batteries in series and parallel. Accurately estimating the state of charge (SOC) of batteries is of great significance for improving battery utilization and ensuring system operation safety. This article establishes a 2-RC battery model. First, the Extended Kalman Filter (EKF) algorithm is used to obtain preliminary SOC estimates. Then, the updated error values of the Kalman matrix, the state variables obtained from the EKF algorithm, and the battery data during system operation are used as the training and test dataset for the Long Short-Term Memory (LSTM) neural network algorithm. Finally, the algorithm was compared and analyzed with commonly used EKF estimation methods and LSTM algorithms. It was found that the root-mean-square error of the SOC of the EKF-LSTM algorithm under different operating conditions was less than 0.8%, and the average absolute error was less than 0.5%. The estimation accuracy is higher than either the EKF algorithm or LSTM algorithm alone.

키워드

과제정보

This project was supported by National Key Technology Research and Development Program of China (2014BAA04B00) and National Natural Science Foundation of China (51207117).

참고문헌

  1. Zhao Dongmei, X.U., Chenyu, T.R., et al.: Review on flexible regulation of multivariate distributed energy storage on distribution side of new power system. Chin. J. Electr. Eng. 99, 1-23 (2022)
  2. Kebede, A., Kalogiannis, T., Mierlo, J., Berecibar, M.: A comprehensive review of stationary energy storage devices for large scale renewable energy sources grid integration. Renew. Sustain. Energy Rev. 159, 112213 (2022). https://doi.org/10.1016/j.rser.2022. 112213
  3. Lee, S., Kim, J., Lee, J., Cho, B.H.: State-of-charge and capacity estimation of lithium-ion battery using a new open-circuit voltage versus state-of-charge. Power Sources 185, 1367-1373 (2008). https://doi.org/10.1016/j.jpowsour.2008.08.103
  4. Zhang, S., Guo, X., Dou, X., et al.: A data-driven coulomb counting method for state of charge calibration and estimation of lithium-ion battery. Sustain. Energy Technol. Assess. 40, 100752 (2020)
  5. Zhao, Bo., Juan, Hu., Shouping, Xu., et al.: Estimation of the SOC of energy-storage lithium batteries based on the voltage increment. IEEE Access 8, 198706-198713 (2020) https://doi.org/10.1109/ACCESS.2020.3031327
  6. Orchard, M.E., Hevia-Koch, P., Zhang, B., Tang, L.: Risk measures for particle-filtering-based state-of-charge prognosis in lithium-ion batteries. IEEE Trans. Ind. Electron. 60, 5260-5269 (2013). https://doi.org/10.1109/TIE.2012.2224079
  7. Tulsyan, A., Tsai, Y., Gopaluni, R.B., Braatz, R.D.: State-of-charge estimation in lithium-ion batteries: a particle filter approach. Power Sources 331, 208-223 (2016) https://doi.org/10.1016/j.jpowsour.2016.08.113
  8. Plett, G.L.: Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs. Part 3. State and parameter estimation. Power Sources 134, 277-292 (2004) https://doi.org/10.1016/j.jpowsour.2004.02.033
  9. Campestrini, C., Heil, T., Kosch, S., Jossen, A.: A comparative study and review of different Kalman filters by applying an enhanced validation method. Energy Storage 8, 142-159 (2016). https://doi.org/10.1016/j.est.2016.10.004
  10. Liu, Y.F., Li, J.Q., Zhang, G., Hua, B., Xiong, N.: State of charge estimation of lithium-ion batteries based on temporal convolutional network and transfer learning. IEEE Access 9, 34177-34187 (2021). https://doi.org/10.1109/ACCESS.2021.3057371
  11. Yidan, Xu., Minghui, Hu., Chunyun, Fu., et al.: State of charge estimation for lithium-ion batteries based on temperaturedependent second-order RC model. Electronics 8, 1012 (2019). https://doi.org/10.3390/electronics8091012
  12. Chung, D.-W., Ko, J.-H., Yoon, K.-Y.: State-of-charge estimation of lithium-ion batteries using LSTM deep learning method. J. Electr. Eng. Technol. 17, 1931-1945 (2022) https://doi.org/10.1007/s42835-021-00954-8
  13. Deng, Ye., Yueli, Hu., Cao, Y.: An improved algorithm of SOC testing based on open-circuit voltage-ampere hour method. Intell. Comput. Smart Grid Electr. Veh. 463, 258-267 (2014)
  14. Luo, Y., Qi, P., Kan, Y., et al.: State of charge estimation method based on the extended Kalman filter algorithm with consideration of time-varying battery parameters. Int. J. Energy Res. 44(13), 10538-10550 (2020). https://doi.org/10.1002/er.5687
  15. Liaw, B.Y., Nagasubramanian, G., Jungst, R.G., Doughty, D.H.: Modeling of lithium ion cells-a simple equivalentcircuit model approach. Solid State Ion. 175(1-4), 835-839 (2004) https://doi.org/10.1016/j.ssi.2004.09.049
  16. Wang, Qi., Li, F., Tang, Yi., Yan, Xu.: Integrating model-driven and data-driven methods for power system frequency stability assessment control. IEEE Trans. Power Syst. 34(6), 4557 (2019). https://doi.org/10.1109/TPWRS.2019.29195 22
  17. Plett, G.L.: Extended Kalman filtering for battery management systems of LiPB-based HEV battery packs. part 1. Background. J. Power. Sources 134(2), 252-261 (2004) https://doi.org/10.1016/j.jpowsour.2004.02.031
  18. Song, Z., Wu, X., Li, X., et al.: Current profile optimization for combined state of charge and state of health estimation of lithium ion battery based on Cramer-Rao bound analysis. IEEE Trans. Power Electron. 34(7), 7067-7078 (2019) https://doi.org/10.1109/TPEL.2018.2877294
  19. Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1753-1780 (1997) https://doi.org/10.1162/neco.1997.9.8.1735
  20. Zaremba, W., Sutskever, I., Vinyals, O. "Recurrent neural network regularization,"arXiv preprint arXiv: 1409.2329 (2014)