A Kolmogorov-Arnold neural networks approach to state of charge estimation and confidence assessment for Li-ion batteries

This study aims to thoroughly examine the potential of the Kolmogorov-Arnold Network (KAN) and its application to improving energy management efficiency, particularly in lithium-ion batteries. The study employs a novel method that utilizes one-dimensional adaptive activation functions parameterized by splines, in contrast to traditional neural networks, where activation functions are fixed. Traditional methods for activation function selection are based on empirical approaches and do not guarantee accurate approximation, potentially leading to suboptimal results. This approach enables the KAN to flexibly adapt to complex data structures, ensuring precise state-of-charge estimation. To objectively evaluate the algorithm's effectiveness, experiments were conducted on real datasets, focusing on analyzing the accuracy of state-of-charge estimation at confidence intervals of 95%, 90%, and 85%. The test results for various charge-discharge cycles demonstrated that the proposed method achieves high accuracy and maintains stability throughout the operation. The proposed method reduces the maximum error by at least 4.26% and significantly improves key performance metrics such as Mean Absolute Error, Root Mean Square Error. Thus, the obtained results confirm the efficiency and innovative nature of the KAN in energy management. This method holds great potential for energy management and can be effectively implemented in areas requiring precise time-series forecasting, including smart home systems, electric vehicles, and industrial devices. Future research will optimize the network architecture and expand its practical applications. Signifi-cantly, this method can be flexibly adapted to different types of batteries and energy systems, broadening its applicability in real-world conditions.

1. Chen Zhilong, He Ting, Mao Yingzhe, Zhu Wenlong, Xiong Yifeng, Wang Shen, et al. State of charge estimation method of energy storage battery based on multiple incremental features. Journal of The Electrochemical Society. 2024;171(7):070522. https://doi.org/10.1149/1945-7111/ad5efa.

2. Hu Xiaosong, Jiang Jiuchun, Cao Dongpu, Egardt B. Battery health prognosis for electric vehicles using sample entropy and sparse bayesian predictive modeling. IEEE Transactions on Industrial Electronics. 2016;63(4):2645-2656. https://doi.org/10.1109/TIE.2015.2461523.

3. Bockrath S., Rosskopf A., Koffel S., Waldhör S., Srivastava K., Lorentz V.R.H. State of charge estimation using recurrent neural networks with long short-term memory for lithium-ion batteries. In: IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society. 14–17 October 2019, Lisbon. Lisbon: IEEE; 2019, p. 2507-2511. https://doi.org/10.1109/IECON.2019.8926815.

4. Tian Jinpeng, Chen Cheng, Shen Weixiang, Sun Fengchun, Xiong Rui. Deep learning framework for lithium-ion battery state of charge estimation: recent advances and future perspectives. Energy Storage Materials. 2023;61:102883. https://doi.org/10.1016/j.ensm.2023.102883.

5. Dreglea A., Foley A., Häger U., Sidorov D., Tomin N. Hybrid renewable energy systems, load and generation forecasting, new grids structure, and smart technologies. In: Solving Urban Infrastructure Problems Using Smart City Technologies. 2021;475-484. https://doi.org/10.1016/B978-0-12-816816-5.00022-X.

6. Dao M.H., Liu F., Sidorov D.N. Kolmogorov–Arnold Neural Networks Technique for the state of charge estimation for li-ion batteries. Bulletin of the South Ural State University. Series: Mathematical Modelling, Programming and Computer Software. 2024;14(4):22-31. https://doi.org/10.14529/mmp240402.

7. Kolmogorov A.N. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Doklady Akademii Nauk SSSR. 1957;114(5):953-956.

8. Arnold V.I. On the representation of continuous functions of three variables as superpositions of continuous functions of two variables. Doklady Akademii Nauk SSSR. 1957;114(4):679-681.

9. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Networks. 1989;2(5):359-366. https://doi.org/10.1016/0893-6080(89)90020-8.

10. Liu Ziming, Wang Yixuan, Vaidya S., Ruehle F., Halverson J., Soljačić M., et al. KAN: Kolmogorov-Arnold networks. In: arXiv:2404.19756. 2024. https://doi.org/10.48550/arXiv.2404.19756.

11. Peng Yanhong, Wang Yuxin, Hu Fangchao, He Miao, Mao Zebing, Huang Xia, et al. Predictive modeling of flexible EHD pumps using Kolmogorov-Arnold networks. Biomimetic Intelligence and Robotics. 2024;4(4):100184. https://doi.org/10.1016/j.birob.2024.100184.

12. Yang Xingyi, Wang Xinchao. Kolmogorov-Arnold transformer. arXiv:2409.10594. 2024. https://doi.org/10.48550/arXiv.2409.10594.

13. De Boor C. A practical guide to splines. Mathematics of Computation. 1980;34(149):325-326. https://doi.org/10.2307/2006241.

14. Fakhoury D., Fakhoury E., Speleers H. ExSpliNet: an interpretable and expressive spline-based neural network. Neural Networks. 2022;152:332-346. https://doi.org/10.1016/j.neunet.2022.04.029.

15. Sapra H.D., Elfimova O., Upadhya S., Desorcy L., Wagner M., Venkataraman S., et al. Battery SoC estimation: updated artifact. Zenodo. 2023;1:0522. https://doi.org/10.5281/zenodo.7553043.

16. Dao M.H., Sidorov D.N. Estimation of the state of charge of energy storage devices using Kolmogorov–Arnold networks. In: Dynamic Systems and Computer Sciences: Theory and Applications (DYSC 2024): Proceedings of the 6th International Conference. 2024;206-209. https://doi.org/10.26516/978-5-9624-23098.2024.1-224.

17. Vo Van Truong, Sidorov D.N. Prediction interval for solar photovoltaic power using arimax model. In: Dynamic Systems and Computer Sciences: Theory and Applications (DYSC 2023): Proceedings of the 5th International Conference. 22 September 2023, Irkutsk. Irkutsk: Irkutsk State University; 2023, р. 225-228. https://doi.org/10.26516/978-5-9624-2182-7.2023.1-228.

18. Hundman R.J., Athanasopolos G. Forecasting: principles and practice. 2nd ed. Monash University, 2018. Available from: https://otexts.com/fpp2/ [Accessed 17th September 2024].

19. Shrestha D.L., Solomatine D.P. Machine learning approaches for estimation of prediction interval for the model output. Neural Networks. 2006;19(2):225-235. https://doi.org/10.1016/j.neunet.2006.01.012.

20. Kolmogorov A.N., Arnold V.I. Kolmogorov-Arnold networks (KANs). GitHub. Available from: https://github.com/KindXiaoming/pykan [Accessed 17th September 2024].