Battery State of Health and Charge Estimation Using Machine Learning Methods

Year 2021, Issue: 26 - Ejosat Special Issue 2021 (HORA), 389 - 394, 31.07.2021

Enes Malik Şahin , Savas Sahin , İbrahim Tanağardıgil

https://doi.org/10.31590/ejosat.959630

Cited By: 1

Abstract

In this study, state of health (SOH) and state of charge (SOC) estimation of series connected batteries were evaluated for their charge and discharge durations. For this purpose, an ARM-based electronics card module was developed for observing instantaneous batteries voltage, current and temperature values during the charge and discharge process. The implemented microcontroller based card module gathers data from the current, voltage, and temperature sensors and it transfers to the computer environment via serial communication port. A specific human machine interface is designed via app-designer. The obtained variables were used for estimating regression models of the machine-learning toolbox. Random forest, decision tree, polynomial, extreme gradient boosting, linear and gradient boosting regression models were used for instantaneous SOH and SOC estimation for batteries during the charge-discharge period. Root Mean Square Error (RMSE) and R^2score results were used for performance evaluation of regression models. When the RMSE and R^2 score results were compared, the decision tree regression model was the regression model that made the most accurate SOH and SOC estimation and the results were presented.

Keywords

State of Charge, State of Health, Microprocessor, Machine learning, Regression models.

Supporting Institution

Scientific and Technical Research Council of Turkey (TUBITAK) under 2209B – Research Project Support Programme for Undergraduate Students

Project Number

1139B412001117

Thanks

I would like to express my special thanks to my advisor Assoc. Prof. Savaş ŞAHİN for his patience, motivation and continuous support. My sincere thanks also goes to Mr. İbrahim TANAĞARDIGİL for his guidance and helping me with every step of the project. Finally, I would like to thank my family and friends for their endless support.

Makina Öğrenmesi Metotları Kullanılarak Batarya Sağlık ve Şarj Durumunun Kestirimi

Abstract

Bu çalışmada, seri bağlı pillerin sağlık durumu (SOH) ve şarj durumu (SOC) tahminleri şarj ve deşarj süreleri boyunca değerlendirilmiştir. Bu amaçla, şarj ve deşarj işlemi sırasında anlık akü voltajı, akım ve sıcaklık değerlerini gözlemlemek için ARM tabanlı bir elektronik kart modülü geliştirilmiştir. Uygulanan mikrodenetleyici tabanlı kart modülü akım, gerilim ve sıcaklık sensörlerinden verileri toplayarak seri haberleşme portu üzerinden bilgisayar ortamına aktarır. App-designer aracılığı ile belirli bir insan makine arayüzü tasarlanmıştır. Elde edilen değişkenler kullanılarak kestirim yapmak için, makine öğrenimi araç kutusunun regresyon modelleri kullanılır. Bataryalar için şarj-deşarj süresi boyunca anlık SOH ve SOC tahminlemesinin yapılması için, rasgele orman, karar ağacı, polinom, aşırı gradyan artırma, doğrusal ve gradyan artırıcı regresyon modelleri kullanıldı. Regresyon modellerinin performans değerlendirmesi için Kök Ortalama Kare Hatası (RMSE) ve R^2 skor sonuçları kullanılmıştır. RMSE ve R^2 skor sonuçları karşılaştırıldığında, karar ağacı regresyon modeli en doğru SOH ve SOC kestirim yapan regresyon modeli olmuştur ve sonuçlar sunulmuştur.

Keywords

Şarj Durumu, Sağlık Durumu, Mikroişlemci, Makine Öğrenmesi, Regresyon modelleri

Project Number

1139B412001117

References

• Badeda, Julia, Monika Kwiecien, Dominik Schulte, and Dirk Uwe Sauer. "Battery state estimation for lead-acid batteries under float charge conditions by impedance: Benchmark of common detection methods." Applied Sciences 8, no. 8 (2018): 1308.
• Brown, G. (2012). Discovering the STM32 microcontroller. Cortex, 3, 34.
• Cacciato, M., Nobile, G., Scarcella, G., & Scelba, G. (2016). Real-time model-based estimation of SOC and SOH for energy storage systems. IEEE Transactions on Power Electronics, 32(1), 794-803.
• El Hadi, M., Ouariach, A., Essaadaoui, R., El Moussaouy, A., & Mommadi, O. (2021). RC time constant measurement using an INA219 sensor: creating an alternative, flexible, low-cost configuration that provides benefits for students and schools. Physics Education, 56(4), 045015.
• Fahrmeir, L., Kneib, T., Lang, S., & Marx, B. (2013). Regression models. In Regression (pp. 21-72). Springer, Berlin, Heidelberg.
• Freedman, D.A., (2009), Statistical Models: Theory and Practice. Cambridge University Press. ISBN 978-1-139-47731-4.
• Hannan, Mohammad A., MS Hossain Lipu, Aini Hussain, and Azah Mohamed. "A review of lithium-ion battery state of charge estimation and management system in electric vehicle applications: Challenges and recommendations." Renewable and Sustainable Energy Reviews 78 (2017): 834-854.
• Stanimirescu, A., Egri, A., Soica, F. F., & Radu, S. M. (2020). Measuring the change of air temperature with 8 LM75A sensors in mining area. In MATEC Web of Conferences (Vol. 305, p. 00046). EDP Sciences.
• Valle, J. M. G., García, J. C. C., & Cadaval, E. R. (2017, May). Electric vehicle monitoring system by using MATLAB/App Designer. In 2017 International Young Engineers Forum (YEF-ECE) (pp. 65-68). IEEE.
• Yiğit Akü. (2021), [online] Available: https://www.yigitaku.com/wp-content/uploads/2016/12/YD-12-7-AH_AGM-brosur.pdf
• Yu, Li-Ren, Yao-Ching Hsieh, Wei-Chen Liu, and Chin-Sien Moo. "Balanced discharging for serial battery power modules with boost converters." In 2013 International Conference on System Science and Engineering (ICSSE), pp. 449-453. IEEE, 2013.