Syllogism of Li-FePO4 Battery Cell Voltage Parameter Guess Under Aperiodic Dynamic Current Profile by Some Data-Driven Techniques: A Error-Based Statistical Comparison Between Decision Tree, Support Vector, Bee Colony, and Neural Network

Abstract

The various procedures are used in the literature for defining battery parameter change such as direct measurement methods, model-based methods, and data-driven methods, which contain the algorithms used in this paper also. The main aim of this study is to present a powerful and highly correct way of parameter forecasting of the A123 Systems 26650 cylindrical type Li-FePO4 battery cell. A few of the goal of this paper is to show the guessing performance of the artificial bee colony algorithm, which has a very limited number of applications on the battery parameter of literature, under the non-periodic dynamic charge/ discharge current profile. Then, a comparison has been made between artificial bee colony, artificial neural networks, support vector machine, and decision tree algorithms used in the paper. The load-connected terminal voltage is defined by considering the 100%-60% state of charge range in the primary usage areas of the batteries. A statistical comparison has been made by considering the absolute errors, squared errors, and the regression values information regarding the results presented by the methods. Consequently, the regression values that give information about the consistency of the confidence interval and results, of the bee colony, neural network, support vector, and decision tree methods have been determined as 99.92%, 99.75%, 96.00% and 95.79%, respectively. Moreover, mean squared errors of the methods has been calculated as 0.00202%, 0.00648%, 0.00998%, and 0.11%, respectively. As a new generation algorithm, artificial bee colony, which gave the most successful results according to the results obtained in the study, has been compared with two different methods selected from the existing literature, eXtreme Gradient Boosting and Smoothed eXtreme Gradient Boosting.

Keywords

• Artificial intelligence
• Battery
• Machine learning
• Parameter
• Forecasting

References

1. Carkit T. 2022. Determination of output voltage of Li-FePO4 battery cells using artificial neural networks under variable current profile. Inter J Sci Engin Res, 13(12): 15-19.
2. Carkit T, Alci M. 2022. Comparison of the performances of heuristic optimization algorithms PSO, ABC and GA for parameter estimation in the discharge processes of Li-NMC battery. J Energy Systems, 6(3): 387-400.
3. Carkit T, Carkit S. 2022. Forecasting of terminal voltage of Li-FePO4 batteries in the context of dynamic current profile using machine learning and artificial intelligence: Decision tree algorithm and artificial bee colony algorithm. In: International Cumhuriyet Artificial Intelligence Applications Conference, December 8-9, Sivas, Türkiye, pp: 76-80.
4. CALCE. 2022. Center for advanced life cycle engineering battery research group. URL: https://web.calce. umd.edu/batterie s/data.htm (accessed date: November 30, 2022).
5. Chemali E, Kollmeyer P, Preindl M, Emad A. 2018. State-of-charge estimation of li-ion batteries using deep neural networks: A machine learning approach. J Power Sourc, 400: 242-255.
6. Dogan A. 2011. Application of optimization algorithms to provide optimum power flow on power systems. MSc thesis, Erciyes University, Kayseri, Türkiye, pp: 119.
7. Han J, Kamber M. 2000. Data mining concepts and techniques. Morgan Kaufmann, Waltham, USA, 3rd ed., pp: 740.
8. Han X, Feng X, Ouyang M, Lu L, Li J, Zheng Y, Li Z. 2019. A comparative study of charging voltage curve analysis and state of health estimation of lithium ion batteries in electric vehicle. Autom Innov, 2: 263-275.

9. Huotari M, Arora S, Malhi A, Framling K. 2021. A dynamic battery state-of-health forecasting model for electric trucks: Li-ion batteries case-study. In: International Mechanical Engineering Congress and Exposition, November 16-19, Virtual Conference, USA, pp: 10.
10. Ipek E, Eren MK, Yılmaz M. 2019. State-of-charge estimation of li-ion battery cell using support vector regression and gradient boosting techniques. In: IEEE International Aegean Conference on Electrical Machines and Power Electronics & International Conference on Optimization of Electrical and Electronic Equipment, August 27-29, Istanbul, Türkiye, pp: 604-609.
11. Ipek E, Yilmaz M. 2021. A novel method for SOC estimation of Li-ion batteries using a hybrid machine learning technique. Turkish J Elect Engin Comput Sci, 29(1): 18-31.
12. Karaboga D. 2014. Artificial intelligence optimization algorithms. Nobel Academic, Ankara, Türkiye, pp: 246.
13. Karaboga D, Basturk B. 2007. A powerful and efficient algorithm for numerical function optimization: Artificial bee colony (ABC) algorithm. J Global Optimiz, 39: 459-471.
14. Khaleghi S, Firouz Y, Berecibar M, Mierlo J. 2020. Ensemble gradient boosted tree for SoH estimation based on diagnostic features. Energies, 13(5): 1262.
15. Niri MF, Liu K, Apachitei G, Ramirez L, Lain M, Widanage D, Marco J. 2022. Quantifying key factors for optimised manufacturing of li-ion battery anode and cathode via artificial intelligence. Energy AI, 7: 1-16.
16. Panarese P. 2022. Approximation techniques with MATLAB. Software Approx, 15: 109-140.
17. Shu X, Shiquan S, Jiangwei S, Yuanjian Z, Li G, Chen Z, Liu Y. 2021. State of health prediction of lithium-ion batteries based on machine learning: Advances and Perspectives. iSci, 24: 03265.
18. Tian Y, Wen J, Yang Y, Shi Y, Zeng J. 2022. State-of-Health Prediction of Lithium-Ion Batteries Based on CNN-BiLSTM-AM. Batteries, 8(10): 155.
19. Timucin F, Aytekin A, Ayaz A. 2019. Decision tree algorithm in data mining. In: 5th International Social Research and Behavioral Sciences Symposium, October 11-12, Tbilisi, Georgia, pp: 350-356.
20. Yan L, Peng J, Gao D, Wu Y, Liu Y, Li H, Liu W, Huang Z. 2022. A hybrid method with cascaded structure for early-stage remaining useful life prediction of lithium-ion battery. Energy, 243: 123038.
21. Yang Y, Farid SS, Thornhill F. 2013. Prediction of biopharmaceutical facility fit issues using decision tree analysis. Computer Aided Chem Engin, 32: 61-66.
22. Yao L, Xu S, Tang A, Zhou F, Huo J, Xiao Y, Fu Z. 2021. A review of lithium-ion battery state of health estimation and prediction methods. World Elect Vehicle J, 12(3): 113.
23. Wang Y, Ni Y, Lu S, Wang J, Zhang X. 2019. Remaining useful life prediction of lithium-ion batteries using support vector regression optimized by artificial bee colony. IEEE Transact Vehic Technol, 68(10): 9543-9553.
24. Wang Y, Yang D, Zhang X, Chen Z. 2016. Probability based remaining capacity estimation using data-driven and neural network model. J Power Sourc, 315: 199-208.
25. Wei Y, Wu D. 2023. Prediction of state of health and remaining useful life of lithium-ion battery using graph convolutional network with dual attention mechanisms. Reliabilit Engin System Safety, 230: 108947.
26. Wu J, Wang Y, Zhang X, Chen Z. 2016. A novel state of health estimation method of li-ion battery using group method of data handling. J Power Sourc, 327: 457-464.