Yapay Sinir Ağları ile Batarya Kapasite Durumu Tahmini Yapılması

Abstract

Li-ion bataryalar, günümüzde çeşitli elektronik cihazlarda ve elektrikli araçlarda sıklıkla kullanılan batarya türlerindendir. Bu bataryaların kapasitesi zaman içinde azalabilmekte ve cihazların ömrünü etkileyebilmektedir. Bu nedenle, Li-ion bataryaların kapasite durumunun tahmin edilmesi önemlidir ve yapay sinir ağları, bu tahmini yapmada kullanılabilecek etkili bir araçtır. Çeşitli girdi verilerine dayanarak tahminler yapabilme yeteneğine sahip olan bu ağ yapısı, Li-ion bataryaların kapasite durumu tahmini yapmak için de kullanılabilmektedir. Bu çalışmada, Li-ion bataryaların kapasite durumunun yapay sinir ağları kullanarak tahmini için bir çalışma yapılmıştır. Bu amaçla, Li-ion bataryaların kapasite durumunun tahmini için veri toplama, veri ön işleme ve yapay sinir ağları kullanımı gibi aşamalar işlenmiştir. Literatür taraması yapılmış ve ilgili makaleler incelendiğinde, yapay sinir ağlarının Li-ion bataryaların kapasite durumunun tahmini için etkili bir araç olabileceği görülmüştür.

Keywords

• Yapay Sinir Ağları
• Li-ion Batarya
• Batarya Kapasite Tahmini
• RNN
• LSTM
• GRU
• SOC

Predicting battery capacity with artificial neural networks

Abstract

Li-ion batteries are a commonly used type of battery in various electronic devices and electric vehicles. The capacity of these batteries can decrease over time and affect the lifespan of the device. Therefore, predicting the capacity status of Li-ion batteries is important, there are several ways to estimate the SOC of a battery. When the literature was reviewed and relevant articles were examined, it was observed that artificial neural networks could be an effective tool for predicting the capacity status of Li-ion batteries. In this study, a study was conducted to predict the capacity status of Li-ion batteries using artificial neural networks. For this purpose, data collection, data preprocessing, and the use of artificial neural networks were carried out in stages for the prediction of the capacity status of Li-ion batteries. When the results obtained were examined, it was seen that artificial neural networks were able to correctly predict the capacity status of Li-ion batteries. The comparative analysis among various ANN models, including RNN, LTSM, and GRU highlights the superiority of GRU in performance, with RNN exhibiting comparable performance and LSTM lagging. These predictions can be used to extend the lifespan of Li-ion batteries and optimize the performance of the device. In addition, efforts such as expanding the data set and optimizing the network structure can be made to increase the accuracy of these predictions. This research presents an exemplary study of predicting Li-ion battery capacity using ANNs and has been successfully conducted using NASA datasets.

Keywords

• Artificial Neural Network
• Li-ion Battery
• Battery Capacity Prediction
• RNN
• LSTM
• GRU State of Capacity
• SOC

References

1. Aliberti, A., et al. (2022). Comparative Analysis of Neural Networks Techniques for Lithium-ion Battery SOH Estimation. 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), 1355–1361. doi: 10.1109/COMPSAC54236.2022.00214.
2. Baccouche, I., Jemmali, S., Manai, B., Omar, N., & Amara, N. (2017). Improved OCV model of a li-ion NMC battery for online SOC estimation using the extended Kalman filter. Energies, 10(6), 764.
3. Blomgren, G. E. (2016). The development and future of lithium-ion batteries. J. Electrochem. Soc., 164(1), A5019. Chau, K. T., & Chan, C. C. (2007). Emerging energy-efficient technologies for hybrid electric vehicles. Proceedings of the IEEE, 95(4), 821–835. https://doi.org/10.1109/JPROC.2006.890114
4. Chitnis, M. S., Pandit, S. P., & Shaikh, M. N. (2018). Electric Vehicle Li-Ion Battery State of Charge Estimation Using Artificial Neural Network. 2018 International Conference on Inventive Research in Computing Applications (ICIRCA), 992-995. doi: 10.1109/ICIRCA.2018.8597234.
5. Cui, Z., Wang, L., Li, Q., Wang, K., et al. (2022). A comprehensive review on the state of charge estimation for lithium-ion battery based on neural network. Int. J. Energy Res., 46(5), 5423–5440.
6. Cuma, M.U., & Koroglu, T. (2015). A comprehensive review on estimation strategies used in hybrid and battery electric vehicles. Renewable and Sustainable Energy Reviews, 42, 517–531. Available at: https://doi.org/10.1016/j.rser.2014.10.047.
7. Das, K., Behera, R. N. (2017). A survey on machine learning: concept, algorithms and applications. Int. J. Innovat. Res. Comput. Commun. Eng., 5(2), 1301e1309.
8. Dubarry, M., Baure, G., & Anseán, D. (2020). Perspective on state-of-health determination in lithium-ion batteries. J. Electrochem. Energy Convers. Storage, 17(4).

9. Guo, Y., Yang, Z., Liu, K., Zhang, Y., & Feng, W. (2021). A compact and optimized neural network approach for battery state-of-charge estimation of energy storage system. Energy, 219, 119529. doi: 10.1016/J.ENERGY.2020.119529.
10. Hamar, J. C., et al. (2021). State-of-health estimation using a neural network trained on vehicle data. J Power Sources, 512, 230493. doi: 10.1016/J.JPOWSOUR.2021.230493.
11. Hannan, M. A., Lipu, M. S. H., Hussain, A., & Mohamed, A. (2017). A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: Challenges and recommendations. Renew. Sustain. Energy Rev., 78, 834–854.
12. Hao, T., Ding, J., & Tu, T. (2022). A hybrid Kalman filter for SOC estimation of lithium-ion batteries. 41st Chinese Control Conference (CCC), 5222–5227. doi: 10.23919/CCC55666.2022.9901537.
13. How, D. N., Hannan, M., Lipu, M. H., & Ker, P. J. (2019). State of charge estimation for lithium-ion batteries using model-based and data-driven methods: A review. IEEE Access, 7, 136116–136136.
14. Jain, A. K., Mao, J., & Mohiuddin, K. M. (1996). Artificial neural networks: a tutorial. Computer, 29(3), 31-44. doi: 10.1109/2.485891.
15. Jiang, B., Liu, Y., & Tang, J. (2022). Lithium-ion battery state of health estimation with recurrent convolution neural networks. 11th International Conference on Power Electronics, Machines and Drives (PEMD 2022), 479–484. doi: 10.1049/icp.2022.1097.
16. Kim, T., Song, W., Son, D.-Y., Ono, L. K., & Qi, Y. (2019). Lithium-ion batteries: Outlook on present, future, and hybridized technologies. Journal of Materials Chemistry A, 7(7), 2942–2964.
17. Li, S., Ju, C., Li, J., Fang, R., Tao, Z., Li, B., & Zhang, T. (2021). State-of-charge estimation of lithium-ion batteries in the battery degradation process based on recurrent neural network. Energies, 14(2), 306.
18. Li, Y., et al. (2019). Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review. Renewable and sustainable energy reviews, 113, 109254.
19. Lu, L., Han, X., Li, J., Hua, J., & Ouyang, M. (2013). A review on the key issues for lithium-ion battery management in electric vehicles. Journal of power sources, 226, 272-288.
20. Lyu, C., Han, Y., Guo, Q., Wang, L., & Song, Y. (2020). State-of-Charge Estimation of Lithium-ion Batteries Based on Deep Neural Network. 2020 Global Reliability and Prognostics and Health Management (PHM-Shanghai), 1–7. doi: 10.1109/PHM-Shanghai49105.2020.9280940.
21. Malkoç, H. C. (2017). Lityum Tabanlı Bataryaların Ömür Tahmini için Bir Model Geliştirme. (Master's Thesis) Gebze Technical University, Institute of Science, Kocaeli.
22. Manoharan, A., et al. (2022). Artificial Neural Networks, gradient boosting and support vector machines for Electric Vehicle Battery State Estimation: A Review. Journal of Energy Storage, 55, 105384. https://doi.org/10.1016/j.est.2022.105384
23. Ng, M.-F., Zhao, J., Yan, Q., Conduit, G. J., & Seh, Z. W. (2020). Author correction: Predicting the state of charge and health of batteries using data-driven machine learning. Nature Mach. Intell., 2, 1–10.
24. Ren, G., Ma, G., & Cong, N. (2015). Review of electrical energy storage system for vehicular applications. Renewable and Sustainable Energy Reviews, 41, 225-236.
25. Saha, B., & Goebel, K. (2007). Battery Data Set. NASA Ames Prognostics Data Repository (http://ti.arc.nasa.gov/project/prognostic-data-repository), NASA Ames Research Center, Moffett Field, CA.
26. Schneider, E. L., Dresch, R. F. V., Brito, R. M., & Loureiro, L. T. R. (2017). Analysis Method of Mobile Phone Batteries Remaining State of Charge. IEEE Latin America Transactions, 15(5), 854-860. doi: 10.1109/TLA.2017.7910198.
27. Vidal, C., Kollmeyer, P., Chemali, E., & Emadi, A. (2019). Li-ion Battery State of Charge Estimation Using Long Short-Term Memory Recurrent Neural Network with Transfer Learning. 2019 IEEE Transportation Electrification Conference and Expo (ITEC), 1–6. doi: 10.1109/ITEC.2019.8790543.
28. Wu, F., Chu, F., & Xue, Z. (2022). Lithium-Ion Batteries. Encyclopedia of Energy Storage: Volume 1-4, 1–4, 5–13. https://doi.org/10.1016/B978-0-12-819723-3.00102-5
29. Xu, M., Wu, W., Zhou, W., Ma, Y., Shi, X., & Li, J. (2020). State of Charge Estimation of Low-speed Electric Vehicle Battery using Back Propagation Neural Network. 2020 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 1438–1443. doi: 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00215.
30. Yang, X., Hu, J., Hu, G., & Guo, X. (2022). Battery state of charge estimation using temporal convolutional network based on electric vehicles operating data. J Energy Storage, 55, 105820. doi: 10.1016/J.EST.2022.105820.
31. Zhu, D., Cho, G., & Campbell, J. J. (2021). Neural Networks Battery Applications: A Review. 2021 IEEE International Conference on Electro Information Technology (EIT), 1–8. doi: 10.1109/EIT51626.2021.9491835.