Batarya sağlık durumunun makine öğrenmesi ile kestirimi

Öz

Bu çalışmada batarya sağlık durumunun belirlenmesi için makine öğrenmesi yöntemi kullanılmıştır. Bu amaçla bataryanın deşarj olması esnasında elde edilen akım, kapasite azalması, gerilim gibi değerler kullanılmıştır. Literatürdeki diğer yöntemlerden farklı olarak, deşarj gerilim grafiğindeki diz-dirsek noktaları belirlenerek gerilimdeki değişimler daha ayrıntılı olarak dikkate alınmıştır. Belirlenen giriş verileri kullanılarak batarya sağlık durumunun belirlenebilmesi için k-En Yakın Komşu yöntemi ve Rastgele Orman Regresyon yöntemi olmak üzere iki farklı makine öğrenmesi algoritması oluşturulmuştur. Gerçekleştirilen sağlık durumu belirleme yazılımı için PYHTON dili kullanılmıştır. Batarya sağlık durumunun belirlenmesi için kullanılan yöntemlerin başarısı iki farklı senaryo ile değerlendirilmiştir. İlk senaryo tüm batarya verilerinin karışık olarak değerlendirilip, tüm bataryalara ait verilerden oluşan eğitim ve test verilerinin oluşturulması ile gerçekleştirilmiştir. Diğer senaryo ise elde bulunan 12 bataryadan 11’ini eğitim verisini kalan 1 bataryanın ise test verisini oluşturduğu durumdur. Burada 12 bataryanın her biri ayrı ayrı test verisi olarak değerlendirilmiştir.

Anahtar Kelimeler

• Batarya sağlığı
• k-En Yakın Komşu yöntemi
• Rastgele Orman Regresyon yöntemi

Determining battery health with machine learning

Abstract

In this study, machine learning method was used to determine the battery health. For this purpose, values such as current, capacity decrease, voltage obtained during the discharge of the battery were used. Unlike other methods in the literature, the knee-elbow points in the discharge voltage graph are determined and the changes in voltage are taken into account in more detail. Two different machine learning algorithms, namely the k-Nearest Neighbor method and the Random Forest Regression method, were used in order to determine the battery health status by using the specified input data. PYHTON was used for the implemented health status determination software. The success of the methods used to determine the battery health status was evaluated with two different scenarios. The first scenario was carried out by evaluating all battery data in a mixed manner and creating training and test data consisting of data for all batteries. The other scenario is where 11 of the 12 batteries are the training data and the remaining 1 battery is the test data. Here, each of the 12 batteries is evaluated separately as test data.

Keywords

• Battery health
• k-Nearest neighbor method
• Random forest method regression method

Kaynakça

1. D. Linden and T. Reddy, Handbook of Batteries, Third Eddition, McGraw-Hill. 2002.
2. Y. Zhang, R. Xiong, H. He and M. G. Pecht, Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries, IEEE Transactions on Vehicular Technology, 67 (7), 5695-5705, 2018. http://doi.org/10.1109/TVT.2018.2805189.
3. Y. Song, D. Liu, C. Yang, Y. Peng, Data-driven hybrid remaining useful life estimation approach for spacecraft lithium-ion battery, Microelectronics Reliability. 75, 142-153, 2017. http://doi.org/10.1016/j.microrel.2017. 06.045.
4. R. Xiong, Y. Zhang, H. He, X. Zhou and M. G. Pecht, A Double-Scale, Particle-Filtering, Energy State Prediction Algorithm for Lithium-Ion Batteries, IEEE Transactions on Industrial Electronics, 65 (2), 1526-1538, 2018. http://doi.org/10.1109/TIE.2017.2733475.
5. C. Unterrieder, R. Priewasser, S. Marsili and M. Huemer, Battery State Estimation Using Mixed Kalman/Hinfinity, Adaptive Luenberger and Sliding Mode Observer, IEEE Vehicle Power and Propulsion Conference (VPPC), pp. 1-6, Beijing, China, 2013.
6. D. Saji, P. S. Babu and K. Ilango, SoC Estimation of Lithium Ion Battery Using Combined Coulomb Counting and Fuzzy Logic Method, 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), pp. 948-952, Bangalore, India, 2019.
7. X. Hu, C. Zou, C. Zhang and Y. Li, Technological Developments in Batteries: A Survey of Principal Roles, Types, and Management Needs, IEEE Power and Energy Magazine, 15 (5). 20-31, 2017. http://doi.org/10.1109/ MPE.2017.2708812.
8. M. A. Hannan, M. M. Hoque, S. E. Peng and M. N. Uddin, Lithium-Ion Battery Charge Equalization Algorithm for Electric Vehicle Applications, IEEE Transactions on Industry Applications, 53 (3), 2541-2549, 2017. http://doi.org/10.1109/TIA.2017.2672674.

9. T. Kim, W. Song, D. Son, L.K. Ono, and Y. Qi, Lithium-ion batteries: outlook on present, future, and hybridized technologies. Journal of Materials Chemistry A., Lithium-ion batteries: outlook on present, future, and hybridized technologies. Journal of materials chemistry A. 7 (7), 2942-2964, 2019. http://doi.org/10.1039/C8TA 10513H
10. R. Xiong, J. Cao, Q. Yu, Reinforcement learning-based real-time power management for hybrid energy storage system in the plug-in hybrid electric vehicle, Applied energy, 211, 538-548, 2017. http://doi.org/10.1016/ j.apenergy. 2017.11.072.
11. C. Zou, C. Manzie and D. Nešić, Model Predictive Control for Lithium-Ion Battery Optimal Charging, IEEE/ASME Transactions on Mechatronics, 23 (2), 947-957, 2018. http://doi.org/10.1109/TMECH.2018.27989 30.
12. H. Ren, Y. Zhao, S. Chen, T. Wang, Design and implementation of a battery management system with active charge balance based on the SOC and SOH online estimation, Energy, 166, 908-917, 2019. http://doi.org/ 10.1016/j.energy.2018.10.133.
13. X. Tang, Y. Wang, C. Zou, K. Yao, Y. Xia, A novel framework for Lithium-ion battery modeling considering uncertainties of temperature and aging, Energy conversion and management, 80, 162-170, 2019. http:// doi.org/10.1016/j.enconman.2018.10.082.
14. M. Berecibar, I. Gandiaga, I. Villarreal, N. Omar, J. Van Mier, Critical review of state of health estimation methods of Li-ion batteries for real applications, Renewable and Sustainable Energy Reviews, 56, 572-587, http://doi.org/doi.org/10.1016/j.rser.2015.11.042.
15. X. Hu, J. Jiang, D. Cao and B. Egardt, Battery Health Prognosis for Electric Vehicles Using Sample Entropy and Sparse Bayesian Predictive Modeling, IEEE Transactions on Industrial Electronics, 63 (4), 2645-2656, 2016. http://doi.org/10.1109/TIE.2015.2461523.
16. L. Ungurean,G. Cârstoiu,M. V. Micea, Battery state of health estimation: a structured review of models, methods and commercial devices, International Journal of Energy Research, 41 (2), 151-181, 2016. http://doi.org / 10.1002/er.3598.
17. S. Zhang, X. Guo, X. Dou, X. Zhang, A rapid online calculation method for state of health of lithium-ion battery based on coulomb counting method and differential voltage analysis. Journal of Power Sources, 479, 228740, 2020. http://doi.org/10.1016/j.jpowsour. 2020.228740.
18. J. Yu, Health Degradation Detection and Monitoring of Lithium-Ion Battery Based on Adaptive Learning Method, IEEE Transactions on Instrumentation and Measurement, 63 (7), 1709-1721, 2014. http://doi.org/ 10.1109/TIM.2013.2293234.
19. J. S. Goud, K. R and B. Singh, An Online Method of Estimating State of Health of a Li-Ion Battery, in IEEE Transactions on Energy Conversion, 36 (1), 111-119, 2021. http://doi.org/10.1109/TEC.2020.3008937.
20. Z. Wang, C. Yuan and X. Li, Lithium Battery State-of-Health Estimation via Differential Thermal Voltammetry With Gaussian Process Regression, IEEE Transactions on Transportation Electrification, 7(1), 16-25, 2021, http://doi: 10.1109/TTE.2020.3028784.
21. J. Bi, T. Zhang, H. Yu, Y. Kang, State-of-health estimation of lithium-ion battery packs in electric vehicles based on genetic resampling particle filter, Applied Energy, 182, 558-568, 2016. http://doi.org/ 10.1016/j.apenergy.2016.08.138.
22. A. Allam, S. Onori, S. Marelli and C. Taborelli, Battery Health Management System for Automotive Applications: A retroactivity-based aging propagation study, American Control Conference (ACC), pp. 703-716, 2015.
23. G. Sierra, M. Orchard, K. Goebel, C. Kulkarni, Battery health management for small-size rotary-wing electric unmanned aerial vehicles: An efficient approach for constrained computing platforms, Reliability Engineer ing & System Safety, 182. 166-178, 2018. http://doi .org/10.1016/j.ress.2018.04.030.
24. J. Yu, State-of-Health Monitoring and Prediction of Lithium-Ion Battery Using Probabilistic Indication and State-Space Model, IEEE Transactions on Instrum entation and Measurement,64 (11), 2937-2949, 2015. http://doi: 10.1109/TIM.2015.2444237.
25. Y. Gao, K. Liu, C. Zhu, X. Zhang and D. Zhang, Co-Estimation of State-of-Charge and State-of- Health for Lithium-Ion Batteries Using an Enhanced Electrochemical Model, IEEE Transactions on Industrial Electronics, 69 (3), 2684-2696, 2022. http://doi.org/doi: 10.1109/TIE.2021.3066946.
26. Z. Ma, R. Yang, Z. Wang, A novel data-model fusion state-of-health estimation approach for lithium-ion batteries, Applied energy, 237, 836-847, 2018. http://doi.org/10.1016/j.apenergy.2018.12.071.
27. G. You, S. Park, D. Oh, Oh, Real-time state-of-health estimation for electric vehicle batteries: A data-driven approach, Applied energy, 176: 92-103, 2016. http://d oi.org/10.1016/j.apenergy.2016.05.051.
28. K.M. Tsang, W.L. Chan, Chan, State of health detection for Lithium ion batteries in photovoltaic system, Energy conversion and management, 65, 7-12, 2012. http://doi. org/10.1016/j.enconman.2012.07.006.
29. X. Shu, G. Li, Y. Zhang, J. Shen, Z. Chen, Y. Liu, Online diagnosis of state of health for lithium-ion batteries based on short-term charging profiles, Journal of Power Sources, 471, 228478, 2020. http:// doi.org/10.1016/j.jp owsour. 2020.228478.
30. X. Feng, C. Weng, X. He, X. Han, L. Lu, and D. Ren, Online Stateof-Health Estimation for Li-Ion Battery Using Partial Charging Segment Based on Support Vector Machine, IEEE Transactions on Vehicular Technology, 68, 8583-8592, 2019. http://doi.org/10.11 09/TVT.2019.2927120.
31. C. Weng, J. Sun and H. Peng, Model Parametrization and Adaptation Based on the Invariance of Support Vectors With Applications to Battery State-of-Health Monitoring, IEEE Transactions on Vehicular Technology, 64 (9), 3908-3917, 2015. http:// doi:10.11 09/TVT.2014.2364554.
32. C.P. Lin, J. C., F. Yang, M. H. Ling, K. L. Tsui, S.J. Bae, Battery state of health modeling and remaining useful life prediction through time series model, Applied Energy, 275, 115338, http://doi.org/10.1016/j.apenergy.2020.11 5338.
33. Li, Y., et al., State-of-health estimation of lithium-ion batteries based on semi-supervised transfer component analysis, Applied Energy, 277, 115504, 2020. http://doi .org/10.1016/j.apenergy.2020.115504.
34. Y. Li, H. Sheng, Y. Cheng, D. I. Stroe, R. Teodorescu, Novel battery state-of-health online estimation method using multiple health indicators and an extreme learning machine. Energy, 160, 466-477, 2020. http:// doi.org/10. 1016/j.apenergy.2020.115504.
35. P. Shen, M. Ouyang, L. Lu, J. Li and X. Feng, The Co-estimation of State of Charge, State of Health, and State of Function for Lithium-Ion Batteries in Electric Vehicles, IEEE Transactions on Vehicular Technology, 67 (1), 92-103, 2018. http://doi.org/10.1109/TVT.2017. 2751613.
36. X. Hu, H. Yuan, C. Zou, Z. Li and L. Zhang, Co-Estimation of State of Charge and State of Health for Lithium-Ion Batteries Based on Fractional-Order Calculus, IEEE Transactions on Vehicular Technology, 67 (11), 10319-10329, 2018. http://doi: 10.1109/TVT. 2018.2865664.
37. D. Liu, X. Yin, Y. Song, W. Liu and Y. Peng, An On-Line State of Health Estimation of Lithium-Ion Battery Using Unscented Particle Filter, IEEE Access, 6, 40990-41001, 2018. http://doi.org/10.1109/ACCESS.2018. 285 4224.
38. H. Chaoui and C. C. Ibe-Ekeocha, State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks, IEEE Transactions on Vehicular Technology, 66 (10), 8773-8783, 2017. http://doi: 10.1109/TVT.2017.2715333.
39. N. Khan, F. U. M. Ullah, Afnan, A. Ullah, M. Y. Lee and S. W. Baik, Batteries State of Health Estimation via Efficient Neural Networks With Multiple Channel Charging Profiles, IEEE Access, 9, 7797-7813, 2021. http://doi.org/10.1109/ACCESS.2020.3047732.
40. P. E. Pascoe and A. H. Anbuky, Standby power system VRLA battery reserve life estimation scheme, IEEE Transactions on Energy Conversion, 20 (4), 887-895, 2005. http://doi.org/10.1109/TEC.2005.853749.
41. K. Goebel, B. Saha, and A. Saxena, A comparison of three data-driven techniques forprognostics, 62nd Meeting of the Society for Machinery Failure Prevention Technology (MFPT), pp. 119–131, Virginia Beach, VA, 2008
42. J. Wu, Y. Wang, X. Zhang, Z. Chen, A novel state of health estimation method of Li-ion battery using group method of data handling, Journal of Power Sources, 327, 457-464, 2016. http://doi.org/10.1016/j.jpowsour.2016. 07.065.
43. Group, C.B. https://web.calce.umd.edu/ batteries/data. Htm#, Erişim Zamanı:12.05.2021.
44. D. A. Pola et al., Particle-Filtering-Based Discharge Time Prognosis for Lithium-Ion Batteries With a Statistical Characterization of Use Profiles, IEEE Transactions on Reliability, 64 (2), 710-720, 2015. http://doi: 10.1109/TR.2014.2385069.
45. S. S. Sheikh, M. Anjum, M. A. Khan, S. A. Hassan, H. A. Khalid, A. Gastli, L. A. Ben-Brahim, Battery Health Monitoring Method Using Machine Learning: A Data-Driven Approach,Energies 13, 3658. https://doi.org/10. 3390/en13143658
46. S. Elasan, Veri Madenciliğinde Farklı Karar Ağaçları ve K-En Yakın Komşuluk Yöntemlerinin İncelenmesi: Kadın Hastalıkları ve Doğum Verisinde Bir Uygulama. Doktora Tezi, Van Yüzüncü Yıl Üniversitesi Sağlık Bilimleri Enstitüsü, Türkiye, 2019.
47. R. Goyal, P. Chandra, Y. Singh, Suitability of KNN regression in the development of interaction based software fault prediction models, Ieri Procedia, 6, 15-21, 2014. http://doi.org/10.1016/j.ieri.2014.03.004.
48. T. Hastie, R. Tibshirani and J. Friedman The Elements of Statistical Learning. Chapter 6, Springer Verlag, New York, 2001.
49. O. Anava and K. Levy, k*-nearest neighbors: From global to local, Advances in neural information processing systems, 29, 4923-4931, 2017.
50. D. Wettschereck and T. Dietterich, Locally adaptive nearest neighbor algorithms. Advances in Neural Information Processing Systems, 6, 184-191, 1993.
51. S. Sun and R. Huang, An adaptive k-nearest neighbor algorithm, Seventh International Conference on Fuzzy Systems and Knowledge Discovery, pp. 91-94, 2014.
52. S. Uğuz, Makine öğrenmesi teorik yönleri ve python uygulamaları ile bir yapay zeka ekolü, Nobel Yayıncılık. Ankara, 2019.
53. W. Sullivan, Machine Learning For Beginners Guide Algorithms: Supervised & Unsupervsied Learning, Decision Tree & Random Forest Introduction, Healthy Pragmatic Solutions Inc, 2017.
54. G. James, D. Witten, T. Hastie, and R. Tibshirani, An introduction to statistical learning, Springer, 112, 2013.
55. L. Breiman, Random forests. Machine learning, 45 (1), 5-32, 2001..
56. K. Özkan, Sınıflandırma ve regresyon ağacı tekniği (SRAT) ile ekolojik verinin modellenmesi, Süleyman Demirel Üniversitesi Orman Fakültesi Dergisi, 13 (1), 1-4, 2012.
57. M. Ercire ve A. Ünsal, Kisa Süreli Güç Kalitesi Bozulmalarinin Dalgacik Analizi ve Rastgele Orman Yöntemi ile Siniflandirilmasi, Uludağ University Journal of The Faculty of Engineering. 26 (3), 903-920, 2021. http://doi: 10.17482/uumfd.976342.
58. F. Rufus, S. Lee and A. Thakker, Health monitoring algorithms for space application batteries, International Conference on Prognostics and Health Management, pp. 1-8, 2008. http://doi: 10.1109/PHM.2008.4711430.