CPSO-UKF ile Lityum-iyon Pilin Sıcaklık Tahmini

Öz

Bu çalışma da lityum iyon bataryanın sıcaklık tahmini Chaos Particle Swarm Algorithm-Unscented Kalman Filter (UKF) tarafından yapılarak önerilmiştir. 18650 türü Lityum iyon bataryaların kompakt tasarımı, uzun ömürlü olması gibi nedenlerden ötürü elektrikli araçalarda kullanımı çok yaygındır. Bu bataryaların sıcaklık parametresinin sağlıklı olarak tahmini ise performansın dengelenmesi, kimyasal bozulma öngörüsü gibi nedenlerden ötürü kritik önemdedir. Bu nedenle bu çalışma da 18650 türü lityum iyon bataryanın sıcaklık parametresinin tahmini UKF tabanlı yöntemlerle yapılmıştır. UKF yönteminin parametre değrlerinin belrilenmeis yoğun ve matematiksel işlem yükü sebebiyle PSO yöntemleriyle belirlenerek tahmin performansları karşılaştırılmıştır. UKF yönteminin alpha, kappa, R matrisi gibi parametre değerleri Particle Swarm Optimization (PSO), Chaos Particle Swarm Optimization (CPSO), Comprehensive Learning Particle Swarm Optimization (CLPSO) ve deneme yanılma yoluyla belirlenen hiperparametre değerlerinin belrilenmiştir. Bu dört farklı yöntemin elde ettiği hiperparametre değerleri UKF yöntemine ayrı ayrı uygulanarak tahmin performansları karşılaştrıılmıştır. CPSO-UKF yöntemi R2 metriğine göre %99.99228 tahminde doğruluğa ulaşarak en baaşrılı yöntem olmuştur. Önerilen yöntemin baaşrısı dieğr regresyon metrikleriyle de verilmiştir.

Anahtar Kelimeler

• Elektrikli Araç
• Lityum-iyon
• Sıcaklık Tahmini
• Kokusuz Kalman Filtresi
• Kaos Parçacık Sürüsü Algoritması

Temperature Prediction of Lithium-ion Battery by CPSO-UKF

Abstract

In this study, the temperature estimation of lithium-ion batteries is proposed by Chaos Particle Swarm Algorithm-Unscented Kalman Filter (UKF). 18650-type lithium-ion batteries are widely used in electric vehicles due to their compact design and long life. The accurate estimation of the temperature parameter of these batteries is critical for reasons such as balancing the performance and predicting chemical degradation. Therefore, in this study, the temperature parameter estimation of an 18650-type lithium-ion battery is made by UKF-based methods. Due to the intensive and mathematical processing load of the UKF method, the parameter values are determined by Chaos Particle Swarm Optimization (PSO) methods, and their estimation performances are compared. The parameter values such as alpha, kappa, and R matrix of the UKF method are determined by Particle Swarm Optimization (PSO), Chaos Particle Swarm Optimization (CPSO), Comprehensive Learning Particle Swarm Optimization (CLPSO), and hyperparameter values determined by trial and error. The hyperparameter values obtained from these four different methods were applied to the UKF method separately and their estimation performances were compared. The CPSO-UKF method became the most successful method by reaching an accuracy of 99.99228% in estimation according to the R2 metric. The success of the proposed method is also given with other regression metrics.

Keywords

• Electric Vehicle
• Lithium-ion
• Temperature Prediction
• Unscented Kalman Filter
• Chaos Particle Swarm Algorithm

Kaynakça

1. [1] M. Li, J. Lu, Z. Chen, and K. Amine, “30 Years of Lithium-Ion Batteries,” Advanced Materials, vol. 30, no. 33, p. 1800561, 2018, doi: 10.1002/adma.201800561.
2. [2] B. Li et al., “A Review of Solid Electrolyte Interphase (SEI) and Dendrite Formation in Lithium Batteries,” Electrochem. Energy Rev., vol. 6, no. 1, p. 7, Mar. 2023, doi: 10.1007/s41918-022-00147-5.
3. [3] X. Chen et al., “Practical Application of All-Solid-State Lithium Batteries Based on High-Voltage Cathodes: Challenges and Progress,” Advanced Energy Materials, vol. 13, no. 35, p. 2301230, 2023, doi: 10.1002/aenm.202301230.
4. [4] S. M. Abu et al., “State of the art of lithium-ion battery material potentials: An analytical evaluations, issues and future research directions,” Journal of Cleaner Production, vol. 394, p. 136246, Mar. 2023, doi: 10.1016/j.jclepro.2023.136246.
5. [5] A. Senyshyn, M. J. Mühlbauer, O. Dolotko, and H. Ehrenberg, “Low-temperature performance of Li-ion batteries: The behavior of lithiated graphite,” Journal of Power Sources, vol. 282, pp. 235–240, May 2015, doi: 10.1016/j.jpowsour.2015.02.008.
6. [6] A. Belgibayeva et al., “Lithium-ion batteries for low-temperature applications: Limiting factors and solutions,” Journal of Power Sources, vol. 557, p. 232550, Feb. 2023, doi: 10.1016/j.jpowsour.2022.232550.
7. [7] X. Su et al., “Liquid electrolytes for low-temperature lithium batteries: main limitations, current advances, and future perspectives,” Energy Storage Materials, vol. 56, pp. 642–663, Feb. 2023, doi: 10.1016/j.ensm.2023.01.044.
8. [8] M. Waseem, M. Ahmad, A. Parveen, and M. Suhaib, “Battery technologies and functionality of battery management system for EVs: Current status, key challenges, and future prospectives,” Journal of Power Sources, vol. 580, p. 233349, Oct. 2023, doi: 10.1016/j.jpowsour.2023.233349.

9. [9] R. R. Kumar, C. Bharatiraja, K. Udhayakumar, S. Devakirubakaran, K. S. Sekar, and L. Mihet-Popa, “Advances in Batteries, Battery Modeling, Battery Management System, Battery Thermal Management, SOC, SOH, and Charge/Discharge Characteristics in EV Applications,” IEEE Access, vol. 11, pp. 105761–105809, 2023, doi: 10.1109/ACCESS.2023.3318121.
10. [10] G. Taş, C. Bal, and A. Uysal, “Performance comparison of lithium polymer battery SOC estimation using GWO-BiLSTM and cutting-edge deep learning methods,” Electr Eng, vol. 105, no. 5, pp. 3383–3397, Oct. 2023, doi: 10.1007/s00202-023-01934-z.
11. [11] M. Zhang et al., “Electrochemical Impedance Spectroscopy: A New Chapter in the Fast and Accurate Estimation of the State of Health for Lithium-Ion Batteries,” Energies, vol. 16, no. 4, Art. no. 4, Jan. 2023, doi: 10.3390/en16041599.
12. [12] B. Liu, X. Tang, and F. Gao, “Joint estimation of battery state-of-charge and state-of-health based on a simplified pseudo-two-dimensional model,” Electrochimica Acta, vol. 344, p. 136098, Jun. 2020, doi: 10.1016/j.electacta.2020.136098.
13. [13] J. Qiao, S. Wang, C. Yu, X. Yang, and C. Fernandez, “A chaotic firefly - Particle filtering method of dynamic migration modeling for the state-of-charge and state-of-health co-estimation of a lithium-ion battery performance,” Energy, vol. 263, p. 126164, Jan. 2023, doi: 10.1016/j.energy.2022.126164.
14. [14] C. Wang, S. Wang, J. Zhou, J. Qiao, X. Yang, and Y. Xie, “A novel back propagation neural network-dual extended Kalman filter method for state-of-charge and state-of-health co-estimation of lithium-ion batteries based on limited memory least square algorithm,” Journal of Energy Storage, vol. 59, p. 106563, Mar. 2023, doi: 10.1016/j.est.2022.106563.
15. [15] W. Li, M. Rentemeister, J. Badeda, D. Jöst, D. Schulte, and D. U. Sauer, “Digital twin for battery systems: Cloud battery management system with online state-of-charge and state-of-health estimation,” Journal of Energy Storage, vol. 30, p. 101557, Aug. 2020, doi: 10.1016/j.est.2020.101557.
16. [16] M. Rashid, M. Faraji-Niri, J. Sansom, M. Sheikh, D. Widanage, and J. Marco, “Dataset for rapid state of health estimation of lithium batteries using EIS and machine learning: Training and validation,” Data in Brief, vol. 48, p. 109157, Jun. 2023, doi: 10.1016/j.dib.2023.109157.
17. [17] DNKPOWER, “3.63V-4850mAh-18.20Wh-LG-M50-21700 Battery,” Lithium ion Battery Manufacturer and Supplier in China-DNK Power. Accessed: Aug. 03, 2024. [Online]. Available: https://www.dnkpower.com/lg-m5021700-m50t21700/
18. [18] Z. Ma, X. Yuan, S. Han, D. Sun, and Y. Ma, “Improved Chaotic Particle Swarm Optimization Algorithm with More Symmetric Distribution for Numerical Function Optimization,” Symmetry, vol. 11, no. 7, Art. no. 7, Jul. 2019, doi: 10.3390/sym11070876.
19. [19] N. M. M. Kalimullah, K. Shukla, A. Shelke, and A. Habib, “Stiffness tensor estimation of anisotropic crystal using point contact method and unscented Kalman filter,” Ultrasonics, vol. 131, p. 106939, May 2023, doi: 10.1016/j.ultras.2023.106939.
20. [20] J. Shen et al., “Alternative combined co-estimation of state of charge and capacity for lithium-ion batteries in wide temperature scope,” Energy, vol. 244, p. 123236, Apr. 2022, doi: 10.1016/j.energy.2022.123236.
21. [21] Z. Long, M. Bai, M. Ren, J. Liu, and D. Yu, “Fault detection and isolation of aeroengine combustion chamber based on unscented Kalman filter method fusing artificial neural network,” Energy, vol. 272, p. 127068, Jun. 2023, doi: 10.1016/j.energy.2023.127068.
22. [22] G. Taş, A. Uysal, and C. Bal, “A New Lithium Polymer Battery Dataset with Different Discharge Levels: SOC Estimation of Lithium Polymer Batteries with Different Convolutional Neural Network Models,” Arab J Sci Eng, vol. 48, no. 5, pp. 6873–6888, May 2023, doi: 10.1007/s13369-022-07586-8.