Estimation of Battery Remaining Life-time with Deep Learning Methods

Abstract

The swift proliferation of renewable energy sources and electric grids causes discrepancies between energy supply and demand. This scenario causes variations in voltage and frequency levels due to discrepancies between energy generation and consumption, jeopardizing the stability of energy networks. The intrinsically fluctuating and unpredictable characteristics of renewable energy sources, such as the sun and wind, intensify these oscillations. In contrast to conventional have to have energy-producing systems, renewable energy systems have energy-producing systems and a restricted ability to adapt immediately to demand. In this environment, energy storage devices arise as a vital solution for the effective management of renewable energy generation and for sustaining grid stability. Research on Remaining Useful Life (RUL) and State of Charge (SoC) of batteries is essential for battery reliability, user satisfaction, and environmental sustainability. These studies provide benefits in energy efficiency, increased mobility, diminished battery replacement requirements, and superior waste management. Estimating battery longevity facilitates the efficient management of battery-operated equipment and the strategic planning of energy requirements. Deep learning techniques have made substantial progress in estimating battery capacity and longevity. Long-lasting batteries with substantial energy storage capacity, favored in industrial applications, are more efficiently assessed utilizing deep learning methodologies. This study analyzes the outcomes derived from the application of the Scaled Conjugate Gradient (SCG) technique for estimating battery capacity. It seeks to enhance the efficient management of battery systems and devise strategies that promote the sustainability of energy storage technology. This study's performance measures, comprising 1.098% MAPE, 0.9823 R², 0.0019 MSE, and 0.0302 MAE, enhance the effective management of energy storage systems, the optimal use of energy resources, and strategic planning to fulfill energy demands. This study's performance measures, 1.098% MAPE, 0.9823 R2, 0.0019 MSE and 0.0302 MAE obtained in this study on battery estimation, it supports the efficient management of energy storage systems, effective use of energy resources and strategic planning for energy demands.

Keywords

• battery
• battery management system
• deep learning
• predictive algorithm
• remaining useful life

Derin Öğrenme Yöntemleri ile Batarya Kalan Kullanım Ömrünün Tahmini

Öz

Yenilenebilir enerji kaynakları ve elektrik şebekelerinin hızla genişlemesi, enerji talep ve arz dengesizliklerine yol açmaktadır. Bu durum, enerji üretimi ve tüketimi arasındaki uyumsuzluklar nedeniyle gerilim ve frekans seviyelerinde dalgalanmalara neden olmakta, enerji sistemlerinin stabilitesini tehdit etmektedir. Özellikle güneş ve rüzgar gibi yenilenebilir enerji kaynaklarının doğası gereği değişken ve öngörülemez olması, bu dalgalanmaları daha da artırmaktadır. Geleneksel enerji üretim sistemlerinin aksine, yenilenebilir enerji sistemleri, talebe anında cevap verme konusunda sınırlı kapasiteye sahiptir. Bu bağlamda, enerji depolama sistemleri, yenilenebilir enerji üretiminin verimli bir şekilde yönetilmesi ve şebeke dengesinin korunması için kritik bir çözüm olarak ön plana çıkmaktadır. Bataryaların kalan kullanım ömrü (Remaining Useful Life, RUL) ve şarj durumu (State of Charge, SoC) üzerine yapılan çalışmalar, batarya güvenilirliği, kullanıcı deneyimi ve çevresel sürdürülebilirlik açısından kritik önemdedir. Bu çalışmalar, enerji verimliliği, mobilite artışı, batarya değişim ihtiyacının azalması ve atık yönetimi avantajları sunmaktadır. Batarya ömrü tahmini, batarya tabanlı sistemlerin etkin yönetimini ve enerji talebine yönelik stratejik planlamayı mümkün kılmaktadır. Derin öğrenme yöntemleri, batarya kapasite ve ömür tahmini alanında önemli ilerlemeler sağlamıştır. Endüstriyel uygulamalarda tercih edilen uzun ömürlü ve yüksek enerji depolama kapasitesine sahip piller, derin öğrenme yöntemleriyle daha iyi analiz edilmektedir. Bu çalışmada da Scaled Conjugate Gradient (SCG) algoritması, batarya kapasite tahmininde kullanılarak elde edilen sonuçlar incelenmektedir. Batarya tabanlı sistemlerin etkin yönetimini kolaylaştırarak enerji depolama teknolojilerinin sürdürülebilirliğini destekleyici yaklaşımlar oluşturmak amaçlanmıştır. Batarya tahmini üzerine yapılan bu çalışmada elde edilen %1.098 MAPE, 0.9823 R2, 0.0019 MSE ve 0.0302 MAE performans metrikleriyle, enerji depolama sistemlerinin verimli yönetimini, enerji kaynaklarının etkin kullanımını ve enerji ihtiyaçlarına yönelik stratejik planlamayı desteklemektedir.

Anahtar Kelimeler

• batarya ömrü
• batarya yönetim sistemi
• derin öğrenme
• enerji tahmin

References

1. [1] Zor, K., Timur, O, Teke, A., "A state-of-the-art review of artificial intelligence techniques for short-term electric load forecasting," 2017 6th International Youth Conference on Energy (IYCE), Budapest, Hungary, 2017, pp. 1-7, doi: 10.1109/IYCE.2017.8003734.
2. [2] Fausett, L., “Fundamentals of neural networks: Architectures, Algorithms and Applications”, PrenticeHall, USA, 1-100.
3. [3] Atalay M.,Çelik E. (2017), “Büyük Veri Analizinde Yapay Zekâ Ve Makine Öğrenmesi Uygulamaları”, Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, Cilt.9 Sayı.22, s.155-172).
4. [4] Zor, K., Çelik, Ö., Timur, O. Teke, “A. Short-Term Building Electrical Energy Consumption Forecasting by Employing Gene Expression Programming and GMDH Networks”, Energies 2020, 13, 1102. doi: 10.3390/en13051102.
5. [5] Saxena, A., Celaya, J., Roychoudhury, I., Saha, B., Saha, S., Goebel, K., (2012). “Designing Data-Driven Battery Prognostic Approaches for Variable Loading Profiles: Some Lessons Learned”, European Conference of the Prognostics and Health Management SoCiety, pp.10.
6. [6] Mena, L.J., Orozco, E.E., Felix, V.G., Ostos, R., Melgarejo, J., Maestre, G.E., (2012). “Machine Learning Approach to Extract Diagnostic and Prognostic Thresholds: Application in Prognosis of Cardiovascular Mortality”, Comput Math Methods Med. 2012;2012:750151, doi: 10.1155/2012/750151, Epub 2012 Aug 9.
7. [7] Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., and Siegel, D. (2014). “Prognostics And Health Management Design For Rotary Machinery Systems-Reviews, Methodology And Applications”, Mechanical Systems and Signal Processing, Volume 42, Issue 1-2, pg. 314–334, doi:10.1016/j.ymssp.2013.06.004
8. [8] Biggio, L., Kastanis, I., (2020). “Prognostics and Health Management of Industrial Assets: Current Progress and Road Ahead”, Frontiers in Artificial Intelligence, Volume 3, doi:10.3389/frai.2020.578613.

9. [9] Innovation Landscape For A Renewable-Powered Future: Solutions To İntegrate Variable Renewables, (2019), International Renewable Energy Agency (IRENA), Abu Dhabi.
10. [10] Meng, J., Stroe, D.I., Ricco, M., Luo,G., Teodorescu, R., (2019). ‘‘A Simplified Model-Based State-OfCharge Estimation Approach For Lithium-İon Battery With Dynamic Linear Model”, IEEE Trans. Ind. Electron., vol. 66, no. 10, pg. 7717–7727, 2019, doi: 10.1109/TIE.2018.2880668.
11. [11] Ulusal Enerji Verimliliği Eylem Planı 2017-2023 (UEVEP), https://enerjiapi.enerji.gov.tr//Media/Dizin/EVCED/tr/Raporlar/Ulusal%20Enerji%20Verimliliği%20Eylem%20Planı/20180102M1_2018.pdf
12. [12] Stroe, D.I., Knap,V., Swierczynski, M., Stroe, A.I., Teodorescu,R., (2017). ‘‘Operation Of A Grid-Connected Lithium-İon Battery Energy Storage System For Primary Frequency Regulation: A Battery Lifetime Perspective’’, IEEETrans. Ind. Appl., vol. 53, no. 1, pp. 430–438, 2017, doi: 10.1109/TIA.2016.2616319.
13. [13] Tuttman, M., Litzelman, S., (2020). “Why Long-Duration Energy Storage Matters,” ARPA-E Blog Post, https://arpa-e.energy.gov/news-and-media/blog-posts/why-longduration-energy-storage-matters.
14. [14] Thompson, C., Velar, V., (2020). “Monetizing Energy Storage in the Data Center,” Schneider Electric, White Paper 274, https://www.se.com/us/en/download/document/SPD_WP274_EN/
15. [15] Muratori, M., Rizzoni, G. (2015). “Residential Demand Response: Dynamic Energy Management And Time-Varying Electricity Pricing”. IEEE Transactions on Power systems, 31(2), 1108-1117.
16. [16] Nan, S., Zhou, M., Li, G. (2018). “Optimal Residential Community Demand Response Scheduling İn Smart Grid”. Applied Energy, 210, 1280-1289.
17. [17] Chen C, Wei J, Li Z. Remaining Useful Life Prediction for Lithium-Ion Batteries Based on a Hybrid Deep Learning Model. Processes. 2023; 11(8):2333. doi.:10.3390/pr11082333.
18. [18] Bao Z, Jiang J, Zhu C, Gao M. A New Hybrid Neural Network Method for State-of-Health Estimation of Lithium-Ion Battery. Energies. 2022; 15(12):4399. https://doi.org/10.3390/en15124399.
19. [19] Imani, M. H., Ghadi, M. J., Ghavidel, S., & Li, L. (2018). Demand response modeling in microgrid operation: a review and application for incentive-based and time-based programs. Renewable and Sustainable Energy Reviews, 94, 486-499.
20. [20] Erdinc, O., Taşcikaraoğlu, A., Paterakis, N. G., & Catalão, J. P. (2018). Novel incentive mechanism for end-users enrolled in DLC-based demand response programs within stochastic planning context. IEEE Transactions on Industrial Electronics, 66(2), 1476-1487.
21. [21] Morstyn, T., Hredzak, B., & Agelidis, V. G. (2016). Control strategies for microgrids with distributed energy storage systems: An overview. IEEE Transactions on Smart Grid, 9(4), 3652-3666.
22. [22] Nghitevelekwa, K., & Bansal, R. C. (2018). A review of generation dispatch with large-scale photovoltaic systems. Renewable and sustainable energy reviews, 81, 615-624.
23. [23] Saha, B., Goebel, K., (2007). “Battery Data Set, NASA Ames Prognostics Data Repository”, [http://ti.arc.nasa.gov/project/prognostic-data-repository],NASA Ames, Moffett Field, CA.
24. [23] Choi, Y., Ryu, S., Park, K.,Kim, H., (2019). "Machine Learning-Based Lithium-Ion Battery Capacity Estimation Exploiting Multi-Channel Charging Profiles," in IEEE Access, vol. 7, pp. 75143-75152, 2019, doi: 10.1109/ACCESS.2019.2920932.
25. [24] Wang, Y., Tian, J., Sun, Z., Wang, L., Xu, R., Li, M., Chen, Z.,(2020). “A Comprehensive Review Of Battery Modeling And State Estimation Approaches For Advanced Battery Management Systems”, Renewable and Sustainable Energy Reviews, Volume 131, ISSN 1364-0321, doi:10.1016/j.rser.2020.110015.
26. [25] Johnson, Michael. (2008). Nonlinear Least‐Squares Fitting Methods. Methods in cell biology. 84. 781-805. doi:10.1016/S0091-679X(07)84024-6.
27. [26] Çavuşlu, M. A. , Becerikli, Y. & Karakuzu, C. (2012). Levenberg-Marquardt Algoritması ile YSA Eğitiminin Donanımsal Gerçeklenmesi . Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi , 5 (1) , - . Retrieved from https://dergipark.org.tr/en/pub/tbbmd/issue/22244/23879.
28. [27] Nguyen-Truong, H. T., Le, H. M. (2015). “An Implementation of the Levenberg–Marquardt Algorithm for Simultaneous-energy-gradient Fitting Using Two-Layer Feed-Forward Neural Networks”. Chemical Physics Letters, 629, 40-45.
29. [28] Møller, M.F., (1993). “A Scaled Conjugate Gradient Algorithm For Fast Supervised Learning”. Neural Networks 6, 525-533, doi: 10.1016/S0893-6080(05)80056-5.
30. [29] Babani, L., Jadhav, S., Chaudhari, B., (2016). “Scaled Conjugate Gradient Based Adaptive ANN Control for SVM-DTC Induction Motor Drive”. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.384-395, doi:10.1007/978-3-319-44944-9_33.
31. [30] Chel, H., Majumder, A., Nandi, D. (2011). “Scaled Conjugate Gradient Algorithm in Neural Network Based Approach for Handwritten Text Recognition”. In: Nagamalai, D., Renault, E., Dhanuskodi, M. (eds) Trends in Computer Science, Engineering and Information Technology. CCSEIT 2011. Communications in Computer and Information Science, vol 204. Springer, Berlin, Heidelberg. doi:10.1007/978-3-642-24043-0_21.
32. [31] Gouravaraju, S., Narayan,J., Sauer, R.A., Gautam, S.S. (2021). “A Bayesian Regularization-Backpropagation Neural Network Model for Peeling Computations”. The Journal of Adhesion, 99(1), 92–115, doi:10.1080/00218464.2021.2001335.
33. [32] Wu,D., Huang, H., Qiu, S., Liu, Y., Wu, Y., Ren, Y., Mou, J. (2022). “Application of Bayesian Regularization Back Propagation Neural Network in Sensorless Measurement of Pump Operational State”, Energy Reports, 8, 3041-3050, doi: 10.1016/j.egyr.2022.02.072.
34. [33] Xu, H., Peng, Y., & Su, L. (2018). Health State Estimation Method of Lithium Ion Battery Based on NASA Experimental Data Set. IOP Conference Series: Materials Science and Engineering, 452, 032067. doi:10.1088/1757-899X/452/3/032067.
35. [34] Nagulapati, V. M., Lee, H., Jung, D. W., Brigljevic, B., Choi, Y., & Lim, H. (2021). Capacity estimation of batteries: Influence of training dataset size and diversity on data driven prognostic models. Reliability Engineering & System Safety, 216, 108048. doi:10.1016/J.RESS.2021.108048.
36. [35] Richardson, R. R., M. A. Osborne, M.A., Howey, D. A. (2017). "Gaussian process regression for forecasting battery state of health.", Journal of Power Sources 357(2017): 209-219.
37. [36] Richardson, R. R., M. A. Osborne, M.A., Howey, D. A. (2017). "Gaussian process regression for forecasting battery state of health.", Journal of Power Sources 357(2017): 209-219. Peng, L., Wang, L., Xia, D., Gao, Q., (2022), “Effective energy consumption forecasting using empirical wavelet transform and long short-term memory”, Energy, 2022, 121756, vol. 238, doi: 10.1016/j.energy.2021.121756
38. [37] Güler, E., & Yerel Kandemir, S. (2022). Lineer ve Kübik Regresyon Analizleri Kullanılarak OECD Ülkelerinin CO2 Emisyonlarının Tahminlemesi. Avrupa Bilim Ve Teknoloji Dergisi(34), 175-180. https://doi.org/10.31590/ejosat.1079187