SOC Estimation for Battery of Electric Vehicles

Öz

Accurate estimation of the state of charge of batteries is critical for the reliable operation of battery packs, not only in electric vehicles, but also in hybrid electric vehicles, unmanned aerial vehicles and smart grid systems. In this study, a model based on the Bagging-Random Forest approach is proposed to predict the value of the state of charge of electric vehicle batteries. With the proposed method, the charge value of the battery is associated with the instantaneous current, voltage and temperature of the battery. In the study, 32067 data obtained from real driving of the battery of the BMW i3 vehicle were used. In order to demonstrate the effectiveness of the proposed method, tests were also carried out using popular machine learning methods including Linear Regression and Support Vector Machine. The experimental results based on the Root Mean Square Error and Mean Absolute Error Metrics revealed that the proposed model is superior to the other methods in the literature.

Anahtar Kelimeler

• Battery State of Charge Estimation
• Electric vehicle
• Bagging
• Random Forest
• Machine Learning

Elektrikli Araç Bataryalarının Şarj Durumu Tahmini İçin Bir Model

Öz

Bataryaların şarj durumunun doğru tahmini, yalnızca elektrikli araçlarda değil, aynı zamanda hibrit elektrikli araçlarda, insansız hava araçlarında ve akıllı şebeke sistemlerinde yer alan batarya paketlerinin güvenilir çalışması için kritik öneme sahiptir. Bu çalışmada, elektrikli araç bataryalarının şarj durumunun değerini tahmin etmek için Torbalama-Rastgele Orman yaklaşımına dayalı bir model önerilmiştir. Önerilen yöntem ile bataryaya ait şarj değeri, bataryanın anlık akım, gerilim ve sıcaklığı ile ilişkilendirilmiştir. Çalışmada BMW i3 aracının bataryasına ait gerçek sürüşlerden elde edilen 32067 adet veri kullanılmıştır. Önerilen yöntemin etkinliğini göstermek amacıyla, popüler makine öğrenmesi yöntemlerinden Doğrusal Regresyon ve Destek Vektör Makinesi yaklaşımlarıyla da testler gerçekleştirilmiştir. Kök Ortalama Kare Hata ve Ortalama Mutlak Hata metriklerine dayanan deneysel sonuçlar, önerilen modelin literatürdeki diğer yöntemlere göre daha üstün olduğu ortaya koyulmuştur.

Anahtar Kelimeler

• Batarya Şarj Durum Tahmini
• Elektrikli Araç
• Torbalama-Rastgele Orman
• Makine Öğrenmesi
• Battery State of Charge Estimation
• Electric vehicle
• Bagging
• Random Forest
• Machine Learning

Kaynakça

1. Alvarez Anton, J. C., Garcia Nieto, P. J., Blanco Viejo, C. ve Vilan Vilan, J. A. (2013), Support vector machines used to estimate the battery state of charge, IEEE Transactions on Power Electronics, 28(12), 5919–5926.
2. Battery and Heating Data in Real Driving Cycles | IEEE DataPort. (2022), https://ieee-dataport.org/open-access/battery-and-heating-data-real-driving-cycles. Erişim tarihi: 2022
3. Breiman, L. (1996), Bagging predictors, Machine Learning, 24(2), 123–140.
4. Breiman, L. (2001), Random Forests. Machine Learning, 45(1), 5–32.
5. Chen, L. ve Zhou, S. (2018), Sparse algorithm for robust LSSVM in primal space, Neurocomputing, 275, 2880–2891.
6. Chemali, E., Kollmeyer, P. J., Preindl, M., Ahmed, R. ve Emadi, A. (2018), Long short-term memory networks for accurate state-of-charge estimation of Li-ion batteries, IEEE Transactions on Industrial Electronics, 65(8), 6730–6739.
7. Han, S. S. ve Chen, W. Z. (2008). The algorithm of dynamic battery SOC based on Mamdani fuzzy reasoning, Proceedings of 5th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2008, 1, 439–443.
8. Hauser, M., Yue L., Jihang L. Ve Ray, A. (2016), Real-time combustion state identification via image processing: A dynamic data-driven approach, 2016 American Control Conference (ACC), 3316–3321.

9. He, W., Williard, N., Chen, C. ve Pecht, M. (2014), State of charge estimation for Li-ion batteries using neural network modeling and unscented Kalman filter-based error cancellation, International Journal of Electrical Power & Energy Systems 62, 783–791.
10. Hu, X., Li, S. E. ve Yang, Y. (2016), Advanced machine learning approach for Lithium-Ion battery state estimation in electric vehicles, IEEE Transactions on Transportation Electrification, 2(2), 140–149.
11. Hutter, M. C. (2011), Determining the degree of randomness of descriptors in Linear regression equations with respect to the data Size. Journal of Chemical Information and Modeling, 51(12), 3099–3104.
12. Ipek, E., Kerem Eren, M. ve Yilmaz, M. (2019), State-of-Charge Estimation of Li-ion Battery Cell using Support Vector Regression and Gradient Boosting Techniques. Proceedings of 2019 International
13. Aegean Conference on Electrical Machines and Power Electronics, ACEMP 2019 and 2019 International Conference on Optimization of Electrical and Electronic Equipment, OPTIM 2019, 604–609.
14. Jeong, Y. M., Cho, Y. K., Ahn, J. H., Ryu, S. H. ve Lee, B. K. (2014), Enhanced coulomb counting method with adaptive SOC reset time for estimating OCV, 2014 IEEE Energy Conversion Congress and Exposition, ECCE 2014, 4313–4318.
15. Kohavi, R. (1995). A Study of cross-validation and bootstrap for accuracy estimation and model selection. http//roboticsStanfordedu/%22ronnyk, Erişim tarihi:2022.
16. Mall, R. ve Suykens, J. A. K. (2015), Very sparse LSSVM reductions for large-scale data. IEEE Transactions on Neural Networks and Learning Systems, 26(5), 1086–1097.
17. Nogay, H. (2022), Estimating the aggregated available capacity for vehicle to grid services using deep learning and nonlinear autoregressive neural network, Sustainable Energy, Grids and Networks, 29, 100590.
18. Nuhic, A., Terzimehic, T., Soczka-Guth, T., Buchholz, M. ve Dietmayer, K. (2013), Health diagnosis and remaining useful life prognostics of lithium-ion batteries using data-driven methods, Journal of Power Sources, 239, 680–688.
19. Petzl, M. ve Danzer, M. A. (2013), Advancements in OCV measurement and analysis for lithium-ion batteries, IEEE Transactions on Energy Conversion, 28(3), 675–681.
20. Ray, A. (2004), Symbolic dynamic analysis of complex systems for anomaly detection, Signal Processing, 84(7), 1115–1130.
21. Saranya, C. ve Manikandan, G. (2013), A Study on normalization techniques for privacy preserving data mining.
22. Satyan, P. A. ve Sutar, R. (2020), A Survey on data-driven methods for state of charge estimation of battery, 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), 996–1004.
23. Xiao, B., Liu, Y. ve Xiao, B. (2019), Accurate state-of-charge estimation approach for lithium-ıon batteries by gated recurrent unit with ensemble optimizer, IEEE Access, 7, 54192–54202.
24. Zhang, C., Li, K., Pei, L. ve Zhu, C. (2015), An integrated approach for real-time model-based state-of-charge estimation of lithium-ion batteries, Journal of Power Sources, 283, 24–36.