Journal of Power Electronics

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

DOI QR Code

Online lithium battery SOC estimation based on adversarial domain adaptation under a small sample dilemma

  • Xiang Bao (School of Information Engineering, Inner Mongolia University of Science and Technology) ;
  • Yuefeng Liu (School of Information Engineering, Inner Mongolia University of Science and Technology) ;
  • Bo Liu (School of Information Engineering, Inner Mongolia University of Science and Technology) ;
  • Haofeng Liu (School of Information Engineering, Inner Mongolia University of Science and Technology) ;
  • Yue Wang (Institute of Network Technology, ICT(YANTAI))
  • Received : 2023.07.14
  • Accepted : 2023.12.02
  • Published : 2024.05.20
⟨ Previous Next ⟩

Abstract

In practical applications, a large amount of real labeling data are difficult to obtain because of the differences in the distribution of monitoring data from different batteries, thus resulting in the model's inability to obtain an accurate estimate of the state of charge. Therefore, we propose for the first time the use of an adversarial domain adaptation network (LSTM-DA, Long Short-Term Memory domain adaptation) to extract battery monitoring data and obtain the mapping relationship of the battery charge state. The model is first pretrained using the source domain data. Then, the feature extractor and domain discriminator are made to form an adversarial relationship through the gradient reversal layer (GRL). The simultaneous max-min operation allows the model to be trained for adversarial domain adaptation using source and target domain data. In this study, offline training and online prediction scenarios under incomplete discharge cycles are simulated using Panasonic and LG datasets, and the mean absolute error and root mean square error values of the estimation results on the target domain are 4.71% and 6.59%, respectively. The estimation accuracies under sparse sample conditions are higher than the existing benchmarks of deep learning methods and migration learning methods.

Keywords

Acknowledgement

This research was funded by the Natural Science Foundation of Inner Mongolia Autonomous Region, China grant number 2022MS06008.

References

  1. Qin, J., Du, J., Li, J.: Adaptive finite-time trajectory tracking event-triggered control scheme for underactuated surface vessels subject to input saturation. IEEE Trans. Intell. Transp. Syst. 24(8), 8809-8819 (2023)  https://doi.org/10.1109/TITS.2023.3256094
  2. Bai, H., Yu, B., Gu, W.: Research on position sensorless control of rdt motor based on improved SMO with continuous hyperbolic tangent function and improved feedforward PLL. J. Mar. Sci. Eng. 11(3), 642 (2023) 
  3. Marom, R., Amalraj, S.F., Leifer, N., et al.: A review of advanced and practical lithium battery materials. J. Mater. Chem. 21(27), 9938-9954 (2011)  https://doi.org/10.1039/c0jm04225k
  4. Hossain Lipu, M.S., Hannan, M.A., Hussain, A., Ayob, A., Saad, M.H.M., Karim, T.F., How, D.N.T.: Data-driven state of charge estimation of lithium-ion batteries: algorithms, implementation factors, limitations and future trends. J. Clean. Prod. 277, 124110 (2020) 
  5. Li, Y., Guo, H., Qi, F., Li, M.: Comparative study of the influence of open circuit voltage tests on state of charge online estimation for lithium-ion batteries. IEEE Access 8(01), 17535-17547 (2020)  https://doi.org/10.1109/ACCESS.2020.2967563
  6. Sun, X., Cao, Y., Zheng, L., et al.: A comparative investigation on peak current solution methods for lithium-ion battery peak power capability prediction. IEEE Trans. Energy Convers. 38(3), 1961-1700 (2023) 
  7. Sun, X., Xu, N., Chen, Q., et al.: State of power capability prediction of lithium-ion battery from the perspective of electrochemical mechanisms considering temperature effect. IEEE Trans. Transport. Electrif. 9(2), 2453-2463 (2022) 
  8. Lashway, C.R., Mohammed, O.A.: Adaptive battery management and parameter estimation through physics-based modeling and experimental verification. IEEE Trans. Transport. Electrif. 2(4), 454-464 (2016)  https://doi.org/10.1109/TTE.2016.2558843
  9. Guo, B., Zhang, P., Wang, W., Wang, F.: SOC estimation study of iron phosphate lithium batteries based on OCV-SOC curve clusters. Power Technol. 43(7), 1125-1128+1139 (2019) 
  10. Zhang, Z., Guo, T., Gao, M., He, Z., Dong, Z.: A review of the research on methods for estimating the state of charge of lithium-ion batteries for electric vehicles. J. Electron. Inform. 43(07), 1803-1815 (2021) 
  11. Shrivastava, P., Soon, T.K., Idris, M.Y.I.B., Mekhilef, S.: Overview of model-based online state-of-charge estimation using Kalman filter family for lithium-ion batteries. Renew. Sustain. Energy Rev. 113, 109233 (2019) 
  12. Hidalgo-Reyes, J.I., Gomez-Aguilar, J.F., Alvarado-Martinez, V.M., Lopez-Lopez, M.G., Escobar-Jimenez, R.F.: Battery state-of-charge estimation using fractional extended Kalman filter with Mittag-Leffler memory. Alex. Eng. J. 59(4), 1919-1929 (2020)  https://doi.org/10.1016/j.aej.2019.12.006
  13. Chemali, E., Kollmeyer, P.J., Preindl, M., Ahmed, R., Emadi, A.: Long short-term memory networks for accurate state-of-charge estimation of li-ion batteries. IEEE Trans. Ind. Electron. 65(8), 6730-6739 (2018)  https://doi.org/10.1109/TIE.2017.2787586
  14. Li, S., Ju, C., Li, J., Fang, R., et al.: State-of-Charge estimation of lithium-ion batteries in the battery degradation process based on recurrent neural network. Energies 14(2), 306 (2021) 
  15. Yang, B., Wang, Y., Zhan, Y.: Lithium battery state-of-charge estimation based on a bayesian optimization bidirectional long short-term memory neural network. Energies 15(13), 4670 (2022) 
  16. Zhang, Z., Dong, Z., Lin, H., He, Z., Wang, M., He, Y., Gao, X., Gao, M.: An improved bidirectional gated recurrent unit method for accurate state-of-charge estimation. IEEE Access 9, 11252-11263 (2021)  https://doi.org/10.1109/ACCESS.2021.3049944
  17. Bhattacharjee, A., Verma, A., Mishra, S., Saha, T.K.: Estimating state of charge for xEV batteries using 1D convolutional neural networks and transfer learning. IEEE Trans. Veh. Technol. 70(4), 3123-3135 (2021)  https://doi.org/10.1109/TVT.2021.3064287
  18. Liu, Y., Li, J., 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
  19. Hannan, M.A., How, D.N.T., Lipu, M.S.H., Mansor, M., Ker, P.J., Dong, Z.Y., Sahari, K.S.M., Tiong, S.K., Muttaqi, K.M., Mahlia, T.M.I., Blaabjerg, F.: Deep learning approach towards accurate state of charge estimation for lithium-ion batteries using self-supervised transformer model. Sci. Rep. 11(1), 19541 (2021) 
  20. Li, Y., Li, K., Liu, X., Wang, Y., Zhang, L.: Lithium-ion battery capacity estimation a pruned convolutional neural network approach assisted with transfer learning. Appl. Energy 285, 116410 (2021)
  21. Shen, S., Sadoughi, M., Li, M., Wang, Z.C.: Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries. Appl. Energy 260, 114296 (2020) 
  22. Wang, Y.X., Chen, Z., Zhang, W.: Lithium-ion battery state-of-charge estimation for small target sample sets using the improved GRU-based transfer learning. Energy 244, 123178 (2022) 
  23. Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199-210 (2011)  https://doi.org/10.1109/TNN.2010.2091281
  24. Fernando, B., Habrard, A., Sebban, M, et al.: Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2960-2967 (2013) 
  25. Li, W., Duan, L., Xu, D., Tsang, I.W.: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1134-1148 (2014)  https://doi.org/10.1109/TPAMI.2013.167
  26. Tzeng, E., Hofman, J., Saenko, K., et al.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167-7176 (2017) 
  27. Han, T., Wang, Z., Meng, H.: End-to-end capacity estimation of Lithium-ion batteries with an enhanced long short-term memory network considering domain adaptation. J. Power. Sources 520, 230823 (2022) 
  28. Oyewole, I., Chehade, A., Kim, Y.: A controllable deep transfer learning network with multiple domain adaptation for battery state-of-charge estimation. Appl. Energy 312, 118726 (2022) 
  29. Fu, S., Zhang, Y., Lin, L., et al.: Deep residual LSTM with domain-invariance for remaining useful life prediction across domains. Reliab. Eng. Syst. Saf. 216, 108012 (2021) 
  30. Ganin, Y., Ustinova, E., Ajakan, H., et al.: Domain-adversarial training of neural Networks. J. Mach. Learn. Res. 17(1), 2096-2030 (2016) 
  31. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. International conference on machine learning. In: PMLR, pp. 1180-1189 (2015) 
  32. Kollmeyer, P.: Panasonic 18650PF Li-ion battery data. Mendeley Data V1. (2018). https://doi.org/10.17632/wykht8y7tg.1 
  33. Phillip, K., Mina, N., Michael, S.: LG 18650HG2 Li-ion battery data. Mendeley Data V2, (2020), https://doi.org/10.17632/b5mj79w5w9.2.