Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Predicting Capacity Change in Li-ion Batteries using Regression Models

Regresyon Modelleri ile Li-ion Bataryalarında Kapasite Değişimi Tahmini

How to cite: Sürücü M. Predicting capacity change in li-ion batteries using regression models. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2022; 5(2): 120-125. DOI: 10.54856/jiswa.202212229

Full Text: PDF, in English.

Total number of downloads: 119

Title: Predicting Capacity Change in Li-ion Batteries using Regression Models

Abstract: The lithium-ion battery technology has led to significant changes in the usage of rechargeable batteries due to its low discharge current, high energy capacity, and long charge/discharge cycles. The easy production of portable and high-energy density batteries has not only contributed to the proliferation of smart devices like the Internet of Things (IoT) devices but has also led to an increase in the use of electric vehicles (EVs). As battery chemistry varies based on manufacturers and storage conditions, the importance of determining the charge lifespan and capacity of batteries connected to smart devices is growing progressively. Therefore, various studies are being conducted to assess capacity and lifespan calculations for Li-Ion batteries. In this study, the behavioral patterns of Li-Ion cells in end-user products are analyzed, aiming to predict capacities for similar battery groups. For this purpose, besides a fundamental linear regression analysis, regression analysis using Gaussian Process Regression (GPR) and Convolutional Neural Networks (CNN) is carried out. The regression performance is evaluated using diverse metric criteria such as R-squared (R2), Adjusted R-squared (Adj. R2), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Normalized Mean Squared Error (NMSE).

Keywords: Lithium-ion battery, capacity, regression, GPR, CNN


Başlık: Regresyon Modelleri ile Li-ion Bataryalarında Kapasite Değişimi Tahmini

Özet: Lityum-iyon pil teknolojisi, düşük deşarj akımı, yoğun enerji kapasitesi ve uzun şarj/deşarj dongüsü sebebiyle şarj edilebilir pillerin kullanım alanlarında büyük değişimler yaşanmasına sebep olmuştur. Taşınabilir ve enerji güvenliği yüksek bataryaların kolayca üretilmesi ile IoT gibi akıllı aygıtların yaygınlaşmasının yanısıra elektrikli araçların(EV) kullanılmasında da artış meydana gelmiştir. Pil kimyasının üretici temelli ve saklama koşulları ile değişmesi sebebiyle akıllı cihazlara bağlı pillerin şarj omrünün ve kapasitesinin tespitinin onemi gitgide artmaktadır. Bu sebeple Li-Ion pillerde de kapasite ve omür hesabında çeşitli çalışmalar yapılmaktadır. Bu çalışmada ozellikle Li-Ion hücrelerin son kullanıcı ürünlerindeki davranış modelleri incelenerek benzer batarya grupları için kapasite tahmini yapılması amaçlanmıştır. Bu sebeple temel bir doğrusal regresyon analizinin yanı sıra Gaussian Process Regression (GPR) ve Convolutional Neural Networks (CNN) ile regresyon analizi gerçekleştirilmiştir. Çeşitli metrik olçütlerle, (R-squared (R2), Adjusted R-squared (Adj. R2), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and Normalized Mean Squared Error (NMSE)), regresyon performansı incelenmiştir.

Anahtar kelimeler: Lityum-iyon batarya, kapasite, regresyon, GPR, CNN


Bibliography:
  • Li N, Liu X, Yu B, Li L, Xu J, Tan Q. Study on the environmental adaptability of lithium-ion battery powered UAV under extreme temperature conditions. Energy 2021; 219: 119481.
  • Depcik C, Cassady T, Collicott B, Burugupally SP, Li X, Alam SS, Arandia JR, Hobeck J. Comparison of lithium ion batteries, hydrogen fueled combustion engines, and a hydrogen fuel cell in powering a small unmanned aerial vehicle. Energy Conversion and Management 2020; 207: 112514.
  • Ma Y, Chiang SW, Chu X, Li J, Gan L, Xu C, Yao Y, He Y, Li B, Kang F, Du H. Thermal design and optimization of lithium ion batteries for unmanned aerial vehicles. Energy Storage 2019; 1(1): e48.
  • Shahjalal M, Shams T, Islam MdE, Alam W, Modak M, Hossain SB, Ramadesigan V, Ahmed MdR, Ahmed H, Iqbal A. A review of thermal management for Li-ion batteries: Prospects, challenges, and issues [Homepage on the Internet]. Journal of Energy Storage 2021; 39: 102518
  • Kumar A, Hoque MA, Nurmi P, Pecht MG, Tarkoma S, Song J. Battery health estimation for IoT devices using V-Edge dynamics. Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications 2020; 1: 56-61.
  • Hemavathi S. Li-ion battery health estimation based on battery internal impedance measurement. Book chapter in Innovations in Sustainable Energy and Technology 2021; 183-193.
  • Shah FA, Shahzad Sheikh S, Mir UI, Owais Athar S. Battery health monitoring for commercialized electric vehicle batteries: Lithium-ion. 2019 International Conference on Power Generation Systems and Renewable Energy Technologies (PGSRET) 2019; 1: 1-6.
  • Li X, Yuan C, Li X, Wang Z. State of health estimation for Li-Ion battery using incremental capacity analysis and Gaussian process regression. Energy 2020; 190: 116467.
  • Li X, Yuan C, Wang Z. State of health estimation for Li-ion battery via partial incremental capacity analysis based on support vector regression. Energy 2020; 203: 117852.
  • Farmann A, Waag W, Marongiu A, Sauer DU. Critical review of on-board capacity estimation techniques for lithium-ion batteries in electric and hybrid electric vehicles. Journal of Power Sources 2015; 281: 114-130.
  • Min Zhu, Wensong Hu, Kar NC. The SOH estimation of LiFePO4 battery based on internal resistance with Grey Markov Chain. IEEE Transportation Electrification Conference and Expo (ITEC) 2016; 1: 1-6.
  • Balagopal B, Chow M-Y. The state of the art approaches to estimate the state of health (SOH) and state of function (SOF) of lithium Ion batteries. 13th International Conference on Industrial Informatics (INDIN) 2015; 1: 1302-1307.
  • Chen ZP, Wang QT. The application of UKF algorithm for 18650-type lithium battery SOH estimation. Applied Mechanics and Materials 2014; 519-520: 1077-1082.
  • Pastor-Fernandez C, Widanage WD, Chouchelamane GH, Marco J. A SoH diagnosis and prognosis method to identify and quantify degradation modes in li-ion batteries using the IC/DV technique. 6th Hybrid and Electric Vehicles Conference 2016; 1: 1-6.
  • Yao H, Jia X, Zhao Q, Cheng Z-J, Guo B. Novel lithium-ion battery state-of-health estimation method using a genetic programming model. IEEE Access 2020; 8: 95333-95344.
  • Pastor-Fernandez C, Uddin K, Chouchelamane GH, Widanage WD, Marco J. A comparison between electrochemical impedance spectroscopy and incremental capacity-differential voltage as li-ion diagnostic techniques to identify and quantify the effects of degradation modes within battery management systems. Journal of Power Sources 2017; 360: 301-318.
  • Harting N, Wolff N, Roder F, Krewer U. State-of-health diagnosis of lithium-ion batteries using nonlinear frequency response analysis. Journal of The Electrochemical Society 2019; 166(2): A277-A285.
  • Wang Z, Yuan C, Li X. Lithium battery state-of-health estimation via differential thermal voltammetry with Gaussian process regression. IEEE Transactions on Transportation Electrification 2021; 7(1): 16-25.
  • Shibagaki T, Merla Y, Offer GJ. Tracking degradation in lithium iron phosphate batteries using differential thermal voltammetry. Journal of Power Sources 2018; 374: 188-195.
  • Yang J, Cai Y, Mi C. A battery capacity estimation method using surface temperature change under constant-current charge scenario. IEEE Energy Conversion Congress and Exposition (ECCE) 2021; 1: 1687-1691.
  • Saha B, Goebel K. Battery Data Set: NASA Prognostics Data Repository. NASA Ames Research Center, Moffett Field, CA, 2007.
  • Long B, Xian W, Jiang L, Liu Z. An improved autoregressive model by particle swarm optimization for prognostics of lithium-ion batteries. Microelectronics Reliability 2013; 53(6): 821-831.
  • Kang W, Xiao J, Xiao M, Hu Y, Zhu H, Li J. Research on remaining useful life prognostics based on fuzzy evaluation-Gaussian process regression method. IEEE Access 2020; 8: 71965-71973.
  • Saha B, Goebel K. Modeling Li-ion battery capacity depletion in a particle filtering framework. In Proceedings of the Annual Conference of the Prognostics And Health Management Society 2021; 1: 2909-2924.
  • Penna JAM, Nascimento CL, Rodrigues LR. Health monitoring and remaining useful life estimation of lithium-ion aeronautical batteries. IEEE Aerospace Conference 2012; 1: 1-12.
  • Liu D, Luo Y, Liu J, Peng Y, Guo L, Pecht M. Lithium-ion battery remaining useful life estimation based on fusion nonlinear degradation AR model and RPF algorithm. Neural Computing and Applications 2013; 25(3-4): 557-572.
  • Huang M, Zhang Q. Prediction of remaining useful life of lithium-ion battery based on UKF. 2020 Chinese Automation Congress (CAC) 2020; 1: 4502-4506.
  • Shi Y, Yang Y, Wen J, Cui F, Wang J. Remaining useful life Prediction for lithium-ion battery based on CEEMDAN and SVR. IEEE 18th International Conference on Industrial Informatics (INDIN) 2020; 1: 888-893.
  • Wang Z, Zeng S, Guo J, Qin T. Remaining capacity estimation of lithium-ion batteries based on the constant voltage charging profile. PLoS ONE 2018; 13(7): e0200169.
  • Meng J, Ricco M, Luo G, Swierczynski M, Stroe DI, Stroe AI, Teodorescu R. An overview and comparison of online implementable soc estimation methods for lithium-ion battery. IEEE Transactions on Industry Applications 2018; 54(2): 1583-1591.
  • Egeli SS, Isler Y. Determining the relation between the count number and x-ray energy level in pyroelectric materials using linear regression analysis. Journal of Intelligent Systems with Applications 2021; 4(1): 58-60.
  • Dogdu B, Ertugrul O. Statistical relationship between strontium content and cooling rate on a356 alloy by using regression analysis. Journal of Intelligent Systems with Applications 2021; 4(1): 31-37.
  • Rasmussen CE, Williams CKI. Gaussian Processes for Machine Learning. Cambridge, Mass. Mit Press. 2006.
  • Montgomery DC. Introduction To Linear Regression Analysis. S.L.: John Wiley, 2021.
  • Ozdemir V, Caliskan A, Yigit A. Machine learning based electric energy consumption prediction of a large-scaled production plant with small-scaled data. Journal of Intelligent Systems with Applications 2020; 3(2): 84-89.
  • Kızıltas Koc S, Yeniad M. Diabetes prediction using machine learning techniques. Journal of Intelligent Systems with Applications 2021; 4(2): 150-152.
  • Habibi Aghdam H, Jahani Heravi E. Guide to Convolutional Neural Networks. Springer International Publishing, 2017.
  • Spiess A-N, Neumeyer N. An evaluation of R2 as an inadequate measure for nonlinear models in pharmacological and biochemical research: A Monte Carlo approach. BMC Pharmacology and Toxicology 2010; 10(1): 6.
  • Leach FJ, Henson RK. The use and impact of adjusted r 2 effects in published regression research. Multiple Linear Regression Viewpoints 2007; 33(1): 1-11.
  • Botchkarev A. A new typology design of performance metrics to measure errors in machine learning regression algorithms. Interdisciplinary Journal of Information, Knowledge, and Management (IJIKM) 2019; 14: 045-076.
  • Spuler M, Sarasola-Sanz A, Birbaumer N, Rosenstiel W, Ramos-Murguialday A. Comparing metrics to evaluate performance of regression methods for decoding of neural signals. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2015: 1083-1086.