Machine Learning Approaches for Enhancing the SoH Estimation of LTO Batteries

Abstract

Lithium titanate oxide (LTO) batteries' practical application in modern technologies depends on accurately predicting their state of health (SoH). Using advanced machine learning (ML) techniques, our study examined how to estimate LTO batteries' SoH. For this purpose, we aged rechargeable LTO batteries for 3500 cycles with a battery analyzer and performed differential voltage analysis (DVA). To estimate SoH as a regression problem, we used three machine learn-ing methods: Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Gaussi-an Process Regressions (GPR). As a novel approach to SoH estimation, our research uses a feedforward neural network to solve the categorization problem. In analyzing and comparing the performance of all methods, we found that this categorization-based neural network ap-proach improved computational efficiency by 60.89% while achieving SoH estimation accura-cy of 93.18%. By advancing the field of battery health monitoring, these findings contribute to more reliable and efficient battery management algorithms. In addition to improving battery management systems' accuracy and computational efficiency, the categorization approach demonstrated here could also be used to extend the life and reliability of LTO batteries, includ-ing those used in electric vehicles and renewable energy storage systems. The results of this study illustrate the importance of applying innovative machine learning applications to en-hance battery SoH estimations, providing important implications for future research and prac-tice.

Keywords

• LTO batteries
• Machine learning
• State of Health estimation
• Differential voltage analysis
• Battery management algorithms

Supporting Institution

Inonu University

Project Number

FDK-2021-2645, FOA-2018-1358

Thanks

Prof. Dr. Serdar ALTIN

References

1. [1]   Whittingham MS. Electrical Energy Storage and Intercalation Chemistry. Science . 1976 Jun;192(4244):1126–7. https://doi.org/10.1126/SCIENCE.192.4244.1126.
2. [2]   Mizushima K, Jones PC, Wiseman PJ, Goodenough JB. LixCoO2 (0
3. [3]   Che Y, Deng Z, Lin X, Hu L, Hu X. Predictive Battery Health Management with Transfer Learning and Online Model Correction. IEEE Trans Veh Technol. 2021; 1;70(2):1269–77. https://doi.org/10.1109/TVT.2021.3055811.
4. [4]   Hosen MS, Jaguemont J, Van Mierlo J, Berecibar M. Battery lifetime prediction and performance assessment of different modeling approaches. iScience. 2021;19;24(2). https://doi.org/10.1016/J.ISCI.2021.102060.
5. [5]   Buğday N, Altın S, Karadağ T, Yaşar S. The production and electrochemical properties of N-doped porous carbon structure-based supercapacitor coin cells and flexible wristbands. J Energy Storage. 2022;1;48:103698. https://doi.org/10.1016/J.EST.2021.103698.
6. [6]   Nelson JP, Bolin WD. Basics and Advances in Battery Systems. IEEE Trans Ind Appl. 1995;31(2):419–28. https://doi.org/10.1109/28.370294.
7. [7]   Feder DO, Croda TG, Champlin KS, McShane SJ, Hlavac MJ. Conductance testing compared to traditional methods of evaluating the capacity of valve-regulated lead/acid batteries and predicting state-of-health. J Power Sources. 1992 Dec;40(1–2):235–50. https://doi.org/10.1016/0378-7753(92)80056-H.
8. [8]   Huet F. A review of impedance measurements for determination of the state-of-charge or state-of-health of secondary batteries. J Power Sources. 1998;70(1):59–69. https://doi.org/10.1016/S0378-7753(97)02665-7.

9. [9]   Bavand A, Khajehoddin SA, Ardakani M, Tabesh A. Online Estimations of Li-Ion Battery SOC and SOH Applicable to PartialCharge/Discharge. IEEE Trans Transp Electrif. 2022;8(3):3673–85. https://doi.org/10.1109/TTE.2022.3162164.
10. [10] Tian J, Xu R, Wang Y, Chen Z. Capacity attenuation mechanism modeling and health assessment oflithium-ion batteries. ENERGY. 2021 Apr;221. https://doi.org/10.1016/j.energy.2020.119682.
11. [11] Le D, Tang X. Lithium-ion Battery State of Health Estimation Using Ah-V Characterization. Annu Conf PHM Soc. 2011;3(1). https://doi.org/10.36001/PHMCONF.2011.V3I1.2073.
12. [12] Dai H, Wei X, Sun Z. A new SOH prediction concept for the power lithium-ion battery used on HEVs. 5th IEEE Veh Power Propuls Conf VPPC ’09. 2009;1649–53. https://doi.org/10.1109/VPPC.2009.5289654.
13. [13] Barré A, Deguilhem B, Grolleau S, Gérard M, Suard F, Riu D. A review on lithium-ion battery ageing mechanisms and estimations for automotive applications. J Power Sources. 2013 Nov 1;241:680–9. https://doi.org/10.1016/J.JPOWSOUR.2013.05.040.
14. [14] Shahriari M, Farrokhi M. Online state-of-health estimation of VRLA batteries using state of charge. IEEE Trans Ind Electron. 2013;60(1):191–202. https://doi.org/10.1109/TIE.2012.2186771.
15. [15] Pan S, Fulton LM, Roy A, Jung J, Choi Y, Gao HO. Shared use of electric autonomous vehicles: Air quality and health impacts of future mobility in the United States. Renew Sustain Energy Rev. 2021; 1;149:111380. https://doi.org/10.1016/j.rser.2021.111380.
16. [16] Yao L, Xu S, Tang A, Zhou F, Hou J, Xiao Y, et al. A Review of Lithium-Ion Battery State of Health Estimation and Prediction Methods. World Electr Veh J. 2021; 10;12(3):113. https://doi.org/10.3390/WEVJ12030113.
17. [17] Ge MF, Liu Y, Jiang X, Liu J. A review on state of health estimations and remaining useful lifeprognostics of lithium-ion batteries. MEASUREMENT. 2021 Apr;174. https://doi.org/10.1016/j.measurement.2021.109057.
18. [18] Zou Y, Lin Z, Li D, Liu Z. Advancements in Artificial Neural Networks for health management ofenergy storage lithium-ion batteries: A comprehensive review. J ENERGY STORAGE. 2023 Dec;73(C). https://doi.org/10.1016/j.est.2023.109069.
19. [19] Sui X, He S, Vilsen SB, Meng J, Teodorescu R, Stroe DI. A review of non-probabilistic machine learning-based state of healthestimation techniques for Lithium-ion battery. Appl Energy. 2021;300. https://doi.org/10.1016/j.apenergy.2021.117346.
20. [20] Basia A, Simeu-Abazi Z, Gascard E, Zwolinski P. Review on State of Health estimation methodologies for lithium-ionbatteries in the context of circular economy. CIRP J Manuf Sci Technol. 2021;32:517–28. https://doi.org/10.1016/j.cirpj.2021.02.004.
21. [21] Feng H, Shi G. SOH and RUL prediction of Li-ion batteries based on improved Gaussianprocess regression. J POWER Electron. 2021;21(12):1845–54. https://doi.org/10.1007/s43236-021-00318-5.
22. [22] Yang D, Zhang X, Pan R, Wang Y, Chen Z. A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve. J Power Sources. 2018;384:387–95. https://doi.org/10.1016/J.JPOWSOUR.2018.03.015.
23. [23] Yildiran N, Dikmen IC, Karadag T. State of Health Estimation of Lithium Titanate Oxide Batteries Through Data-Driven Techniques and Machine Learning. 8th Int Artif Intell Data Process Symp IDAP. 2024. https://doi.org/10.1109/IDAP64064.2024.10711165.
24. [24] Yang B, Qian Y, Li Q, Chen Q, Wu J, Luo E, et al. Critical summary and perspectives on state-of-health of lithium-ion battery. Renew Sustain Energy Rev. 2024;1;190:114077. https://doi.org/10.1016/J.RSER.2023.114077.
25. [25] Xiong W, Mo Y, Yan C. Online State-of-Health Estimation for Second-Use Lithium-Ion BatteriesBased on Weighted Least Squares Support Vector Machine. IEEE ACCESS. 2021;9:1870–81. https://doi.org/10.1109/ACCESS.2020.3026552.
26. [26] Zou B, Xiong M, Wang H, Ding W, Jiang P, Hua W, et al. A Deep Learning Approach for State-of-Health Estimation of Lithium-IonBatteries Based on a Multi-Feature and Attention Mechanism Collaboration. BATTERIES-BASEL. 2023; 9(6). https://doi.org/10.3390/batteries9060329.
27. [27] Zhou X, Hsieh SJ, Peng B, Hsieh D. Cycle life estimation of lithium-ion polymer batteries using artificialneural network and support vector machine with time-resolvedthermography. Microelectron Reliab. 2017;79:48–58. https://doi.org/10.1016/j.microrel.2017.10.013.
28. [28] Niraula A, Singh JG. Deep Learning-Based Approach for State-of-Health Estimation of Lithium-Ion Battery in the Electric Vehicles. 2023 Int Conf Power, Instrumentation, Energy Control PIECON 2023. https://doi.org/10.1109/PIECON56912.2023.10085757.
29. [29] Tang X, Zou C, Yao K, Chen G, Liu B, He Z, et al. A fast estimation algorithm for lithium-ion battery state of health. J Power Sources. 2018;31;396:453–8. https://doi.org/10.1016/J.JPOWSOUR.2018.06.036.
30. [30] Li Y, Dong B, Zerrin | Taner, Jauregui E, Wang X, Hua X, et al. State-of-health prediction for lithium-ion batteries via electrochemical impedance spectroscopy and artificial neural networks. https://doi.org/10.1002/EST2.186.Energy Storage. 2020; 1;2(5):e186.
31. [31] Huang S, Liu C, Sun H, Liao Q. State of health estimation of lithium-ion batteries based on theregional frequency. J Power Sources. 2022;518. https://doi.org/10.1016/j.jpowsour.2021.230773.
32. [32] Müller V, Scurtu RG, Memm M, Danzer MA, Wohlfahrt-Mehrens M. Study of the influence of mechanical pressure on the performance and aging of Lithium-ion battery cells. J Power Sources. 2019;15;440:227148. https://doi.org/10.1016/J.JPOWSOUR.2019.227148.
33. [33] Soltani M, Vilsen SB, Stroe AI, Knap V, Stroe DI. Degradation behaviour analysis and end-of-life prediction of lithium titanate oxide batteries. J Energy Storage. 2023;68. https://doi.org/10.1016/j.est.2023.107745.
34. [34] Chaoui H, Ibe-Ekeocha CC. State of Charge and State of Health Estimation for Lithium BatteriesUsing Recurrent Neural Networks. IEEE Trans Veh Technol. 2017; 66(10):8773–83. https://doi.org/10.1109/TVT.2017.2715333.
35. [35] Wang L, Pan C, Liu L, Cheng Y, Zhao X. On-board state of health estimation of LiFePO4 battery pack through differential voltage analysis. Appl Energy. 2016; 168:465–72. https://doi.org/10.1016/J.APENERGY.2016.01.125.
36. [36] Nemeth T, Schröer P, Kuipers M, Sauer DU. Lithium titanate oxide battery cells for high-power automotive applications – Electro-thermal properties, aging behavior and cost considerations. J Energy Storage. 2020;31:101656. https://doi.org/10.1016/j.est.2020.101656.
37. [37] Lotfi N, Li J, Landers RG, Park J. Li-ion Battery State of Health Estimation based on an improved Single Particle model. Proc Am Control Conf. 2017 29;86–91. https://doi.org/10.23919/ACC.2017.7962935.
38. [38] Tan CM, Singh P, Chen C. Accurate Real Time On-Line Estimation of State-of-Health and RemainingUseful Life of Li ion Batteries. Appl Sci. 2020; 10(21). https://doi.org/10.3390/app10217836.
39. [39] Bloom I, Christophersen J, Gering K. Differential voltage analyses of high-power lithium-ion cells 2. Applications. J Power Sources. 2005;139(1–2):304–13. https://doi.org/10.1016/J.JPOWSOUR.2004.07.022.
40. [40] Bloom I, Christophersen JP, Abraham DP, Gering KL. Differential voltage analyses of high-power lithium-ion cells. 3. Another anode phenomenon. J Power Sources. 2006;157(1):537–42. https://doi.org/10.1016/J.JPOWSOUR.2005.07.054.
41. [41] Bloom I, Walker LK, Basco JK, Abraham DP, Christophersen JP, Ho CD. Differential voltage analyses of high-power lithium-ion cells. 4. Cells containing NMC. J Power Sources. 2010;195(3):877–82. https://doi.org/10.1016/J.JPOWSOUR.2009.08.019.
42. [42] Bloom I, Jansen AN, Abraham DP, Knuth J, Jones SA, Battaglia VS, et al. Differential voltage analyses of high-power, lithium-ion cells: 1. Technique and application. J Power Sources. 2005;139(1–2):295–303. https://doi.org/10.1016/J.JPOWSOUR.2004.07.021.
43. [43] McCulloch WS, Pitts W. A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys. 1943;5(4):115–33. https://doi.org/10.1007/BF02478259.
44. [44] Dikmen IC, Karadag T. Electrical Method for Battery Chemical Composition Determination. IEEE Access. 2022;10:6496–504. https://doi.org/10.1109/ACCESS.2022.3143040.
45. [45] Zhang S, Zhai B, Guo X, Wang K, Peng N, Zhang X. Synchronous estimation of state of health and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural networks. J Energy Storage. 2019;26. https://doi.org/10.1016/J.EST.2019.100951.
46. [46] Cortes C, Vapnik V, Saitta L. Support-vector networks. Mach Learn. 1995;20(3):273–97. https://doi.org/10.1007/BF00994018.
47. [47] Cristianini N, Ricci E. Support Vector Machines. Encycl Algorithms. 2008;928–32. https://doi.org/10.1007/978-0-387-30162-4_415.
48. [48] Burges CJC. A Tutorial on Support Vector Machines for Pattern Recognition. Data Min Knowl Discov. 1998;2(2):121–67. https://doi.org/10.1023/A:1009715923555.
49. [49] Klass V, Behm M, Lindbergh G. A support vector machine-based state-of-health estimation method for lithium-ion batteries under electric vehicle operation. J Power Sources. 2014;270:262–72. https://doi.org/10.1016/J.JPOWSOUR.2014.07.116.
50. [50] Woldemariam W. A framework for transportation infrastructure cost prediction: a support vector regression approach. Transp Lett. 2022; https://doi.org/10.1080/19427867.2021.1985895.
51. [51] Li Q, Li D, Zhao K, Wang L, Wang K. State of health estimation of lithium-ion battery based on improved ant lion optimization and support vector regression. J Energy Storage. 2022;50:104215. https://doi.org/10.1016/J.EST.2022.104215.
52. [52] Zhang Y, Liu Y, Wang J, Zhang T. State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression. Energy. 2022;239:121986. https://doi.org/10.1016/J.ENERGY.2021.121986.
53. [53] M. PA, Wiener N. The Extrapolation, Interpolation and Smoothing of Stationary Time Series, with Engineering Applications. J R Stat Soc Ser A. 1950;113(3):413. https://doi.org/10.2307/2981007.
54. [54] Yu J. Online quality prediction of nonlinear and non-Gaussian chemical processes with shifting dynamics using finite mixture model based Gaussian process regression approach. Chem Eng Sci. 2012;82:22–30. https://doi.org/10.1016/J.CES.2012.07.018.
55. [55] Chen T, Ren J. Bagging for Gaussian process regression. Neurocomputing. 2009;72(7–9):1605–10. https://doi.org/10.1016/J.NEUCOM.2008.09.002.
56. [56] Bradford E, Imsland L. Stochastic Nonlinear Model Predictive Control Using Gaussian Processes. 2018 Eur Control Conf ECC 2018. 2018;1027–34. https://doi.org/10.23919/ECC.2018.8550249.
57. [57] Li F, Min Y, Zhang Y, Zhang Y, Zuo H, Bai F. State-of-health estimation method for fast-charging lithium-ionbatteries based on stacking ensemble sparse Gaussian process regression. Reliab Eng Syst Saf. 2024;242. https://doi.org/10.1016/j.ress.2023.109787.
58. [58] Su X, Sun B, Wang J, Zhang W, Ma S, He X, et al. Fast capacity estimation for lithium-ion battery based on online identification of low-frequency electrochemical impedance spectroscopy and Gaussian process regression. Appl Energy. 2022;322. https://doi.org/10.1016/j.apenergy.2022.119516.
59. [59] Zhou Y, Dong G, Tan Q, Han X, Chen C, Wei J. State of health estimation for lithium-ion batteries using geometric impedance spectrum features and recurrent Gaussian process regression. Energy. 2023; 262:125514. https://doi.org/10.1016/j.energy.2022.125514.
60. [60] Yang B, Qian Y, Li Q, Chen Q, Wu J, Luo E, et al. Critical summary and perspectives on state-of-health of lithium-ion battery. Renew Sustain Energy Rev. 2024;190:114077. https://doi.org/10.1016/j.rser.2023.114077.
61. [61] Dikmen IC, Yildiran N, Karadag T. Multi-Chemistry Battery Management System for Electric Vehicles. Eur J Res Dev. 2022;2(4):126–34. https://doi.org/10.56038/ejrnd.v2i4.176.
62. [62] Dikmen İC, Karadağ T. Onboard Battery Type Determination. In: 2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). 2021. p. 360–5. https://doi.org/10.1109/ISMSIT52890.2021.9604658.
63. [63] Karadağ T, Dikmen İC. Yeni Nesil, Modüler ve Akıllı Batarya Yönetim Sistemi. Avrupa Bilim ve Teknol Derg. 2021;(32):1103–12. https://doi.org/10.31590/ejosat.1045564.