مهندسی مکانیک مدرس

مهندسی مکانیک مدرس

جبران خطای تقریب در رگرسیون بردار پشتیبان با استفاده از مدل نیمه‌پارامتری: کاربرد در تخمین وضعیت شارژ باتری لیتیوم-یون

نوع مقاله : مقاله پژوهشی

نویسندگان
مریم کیانی
سعید خراشادی زاده
محمد علی شمسی نژاد
گروه مهندسی برق، دانشگاه بیرجند، بیرجند، ایران
10.48311/mme.2025.117205.82876
چکیده
تخمین دقیق وضعیت شارژ برای مدیریت بهینه انرژی در وسایل نقلیه الکتریکی و حفاظت از باتری در برابر تخلیه عمیق یا شارژ بیش از حد ضروری است. امروزه، روش‌های مختلف هوش مصنوعی به طور گسترده‌ای برای حل این مسئله توسعه یافته و به کار گرفته شده‌اند. در این مقاله، رگرسیون بردار پشتیبان و مدل‌های نیمه‌پارامتری با هم ترکیب شده‌اند تا دقت تخمین بهبود یابد. انگیزه این ایده از شباهت ابرصفحه بهینه رگرسیون بردار پشتیبان و معادله استفاده‌شده در مدل‌های رگرسیون پارامتری نشأت می‌گیرد. با این حال، برای داشتن مدلی منعطف‌تر و دقیق‌تر، از مدل نیمه‌پارامتری استفاده شده است. در واقع، مدل نیمه‌پارامتری نقش جبران خطای تقریب رگرسیون بردار پشتیبان را ایفا می‌کند. برای اعتبارسنجی روش پیشنهادی، پروفایل‌های مختلف جریان مورد استفاده قرار گرفته‌اند. مقایسه رگرسیون بردار پشتیبان، شبکه عصبی با تابع پایه شعاعی، شبکه عصبی پرسپترون چندلایه با روش پیشنهادی نشان می‌دهد که روش پیشنهادی در تخمین وضعیت شارژ دقت بالاتری دارد. علاوه بر این، روش پیشنهادی در پیاده‌سازی‌های واقعی دقت بالا و همگرایی سریعی نشان می‌دهد. نتایج حاصل از برنامه رانندگی دینامومتر شهری برتری روش پیشنهادی را در شرایط عملیاتی واقعی نشان می‌دهد
کلیدواژه‌ها
باتری لیتیوم_یون، تخمین وضعیت شارژ، رگرسیون بردار پشتیبان، مدل نیمه‌پارامتری

موضوعات

عنوان مقاله English

Compensation of The Approximation Error of Support Vector Regression Using Semi-Parametric Model: Application to Lithium-Ion Battery State of Charge Estimation

نویسندگان English

maryam kiani
saeed khorashadizade
mohammad ali shamsi nejad
Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Ira
چکیده English

An accurate estimation of the state of charge (SOC) is necessary for optimal management of the energy in electric vehicles (EV) and protection of the battery from going to the deep discharge or overcharge conditions. Nowadays, many different artificial intelligence methods have been broadly developed and applied to this problem. In this paper, support vector regression (SVR) and semi-parametric models are combined to improve the accuracy of estimation. The motivation of this idea stems from the similarity of the optimal hyper-plain of SVR and the equation used in parametric regression models. However, to have a more flexible and accurate model, semi-parametric model is used. In fact, semi-parametric model plays the role of compensation for the approximation error of the SVR. For validation of the proposed method, various profiles of currents are used. Comparison of SVR, Radial basis function (RBF) neural network, multilayer perceptron (MLP) neural network with the proposed method, shows that the proposed method is more accurate in SOC estimation. In addition, the proposed method shows high accuracy and fast convergence in real-world implementations. The results based on Urban Dynamometer Driving Schedule (UDDS) shows the superiority of the proposed approach under realistic operating conditions

کلیدواژه‌ها English

Lithium-Ion Battery, State of Charge Estimation, Support Vector Regression, Semi-Parametric Model
[1]       T. M. B. Marques, J. L. F. dos Santos, D. S. Castanho, M. B. Ferreira, S. L. Stevan Jr, C. H. Illa Font, T. Antonini Alves, C. M. Piekarski, H. V. Siqueira, and F. C. Corrêa, “An Overview of Methods and Technologies for Estimating Battery State of Charge in Electric Vehicles,” Energies, vol. 16, no. 13, p. 5050, 2023. doi:10.3390/en16135050
[2]       P. Saechan, and I. Dhuchakallaya, “Numerical Study on the Air-Cooled Thermal Management of Lithium-Ion Battery Pack for Electrical Vehicles,” Energy Reports, vol. 8, pp.1264-1270, 2022.
doi:10.1016/j.egyr.2021.11.089
[3]       M. S. Chitnis, S. P. Pandit, and M. N. Shaikh, “Electric Vehicle Li-Ion Battery State of Charge Estimation Using Artificial Neural Network,” In 2018 International Conference on Inventive Research in Computing Applications (ICIRCA), IEEE, pp. 992-995, 2018. doi:10.1109/ICIRCA.2018.8597234
[4]       S. Ceven, and R. Bayır, “Implementation of Hardware-in-the-Loop Based Platform for Real-Time Battery State of Charge Estimation on Li-Ion Batteries of Electric Vehicles Using Multilayer Perceptron,” Int. J. Intell. Syst. Appl. Eng, vol. 8, no. 4, pp. 195-205, 2020. doi:10.18201/ijisae.2020466313
[5]       M. S. Hossain Lipu, M. A. Hannan, A. Hussain, M. H. Saad, A. Ayob, and M. N. Uddin, “Extreme Learning Machine Model for State-of-Charge Estimation of Lithium-Ion Battery Using Gravitational Search Algorithm,” IEEE Transactions on Industry Applications, vol. 55, no. 4, pp. 4225-4234, 2019. doi:10.1109/tia.2019.2902532
[6]     K. Luo, X. Chen, H. Zheng, Z. Shi, “A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries,” Journal of Energy Chemistry.  Vol. 74, pp. 159-173, 2022.
doi:10.1016/j.jechem.2022.06.049
[7]       J. Kuchly, A. Goussian, M. Merveillaut, I. Baghdadi, S. Franger, D. Nelson-Gruel, C. Nouillant, and Y. Chamaillard, “Li-ion battery SOC estimation method using a Neural Network trained with data generated by a P2D model,” IFAC-PapersOnLine, vol. 54, no. 10, pp.  336-343, 2021.
doi:10.1016/j.ifacol.2021.10.185
[8]     N. Tian, Y. Wang, J. Chen, H. Fang, “One-shot parameter identification of the Thevenin’s model for batteries: Methods and validation,” Journal of Energy Storage, Vol. 29, p. 101282, 2020.
doi:10.1016/j.est.2020.101282
[9]     Y. Jiang, J. Zhang, L. Xia, Y. Liu, “State of health estimation for lithium-ion battery using empirical degradation and error compensation models,” IEEE Access, Vol. 8, pp. 123858-123868, 2020. doi:10.1109/ACCESS.2020.3005229
[10]  K. A. Severson, P. M. Attia, N. Jin, N. Perkins, B. Jiang, Z.Yang, R. D. Braatz, “Data-driven prediction of battery cycle life before capacity degradation,” Nature Energy, Vol. 4 no. 5, pp. 383-391, 2019.
doi:10.1038/s41560-019-0356-8
[11]  J. Wang, Z. Deng, T. Yu, A. Yoshida, L. Xu, G. Guan, A. Abudula, “State of health estimation based on modified Gaussian process regression for lithium-ion batteries,” Journal of Energy Storage, Vol. 51, p. 104512, 2022.
doi:10.1016/j.est.2022.104512
[12]  L. Zhang, K. Li, D. Du, C. Zhu, M. Zheng, “A sparse least squares support vector machine used for SOC estimation of Li-ion Batteries,” IFAC-PapersOnLine, Vol. 52, no. 11, pp. 256-261, 2019.
doi:10.1016/j.ifacol.2019.09.150
[13]  S. Jumah, A. Elezab, O. Zayed, R. Ahmed, M. Narimani, A. Emadi, “State of Charge Estimation for EV Batteries Using Support Vector Regression,” In 2022 IEEE Transportation Electrification Conference & Expo (ITEC), pp.964-969, 2022.
doi:10.1109/ITEC53557.2022.9813811
[14]  S. Zhu, N. Zhao, J. Sha, “Predicting battery life with early cyclic data by machine learning,” Energy Storage, Vol. 1, no. 6, e98, 2019.
doi:10.1002/est2.98
[15]  L. Song, K. Zhang, T. Liang, X. Han, Y. Zhang, “Intelligent state of health estimation for lithium-ion battery pack based on big data analysis,” Journal of Energy Storage, Vol. 32, p. 101836, 2020.
doi:10.1016/j.est.2020.101836
[16]  C. W. Hsu, R. Xiong, N. Y. Chen, J. Li, N. T. Tsou, “Deep neural network battery life and voltage prediction by using data of one cycle only,” Applied Energy, Vol. 306, p. 118134, 2022.
doi:10.1016/j.apenergy.2021.118134
[17]  C. Qian, B. Xu, L. Chang, B. Sun, Q. Feng, D. Yang, Z. Wang, “Convolutional neural network based capacity estimation using random segments of the charging curves for lithium-ion batteries,” Energy,Vol. 227, p. 120333, 2021.
doi:10.1016/j.energy.2021.120333
[18]  N. Yang, Z. Song, H. Hofmann, J. Sun, Robust “State of Health estimation of lithium-ion batteries using convolutional neural network and random forest,” Journal of Energy Storage, Vol. 48, p. 103857, 2022.
doi:10.1016/j.est.2021.103857
[19]  C. Bian, S. Yang, J. Liu, E. Zio, “Robust state-of-charge estimation of Li-ion batteries based on multichannel convolutional and bidirectional recurrent neural networks,” Applied Soft Computing, Vol. 116, p. 108401, 2022. doi:10.1016/j.asoc.2021.108401
[20]  F. Heinrich, M. Pruckner, “Virtual experiments for battery state of health estimation based on neural networks and in-vehicle data,” Journal of Energy Storage, Vol. 48, p. 103856, 2022. doi:10.1016/j.est.2021.103856
[21]  J. Chen, X. Feng, L. Jiang, Q. Zhu, “State of charge estimation of lithium-ion battery using denoising autoencoder and gated recurrent unit recurrent neural network,” Energy, Vol. 227, p. 120451, 2021. doi:10.1016/j.energy.2021.120451
[22]  H. Xu, J. Ma, P. Tan, B. Chen, Z. Wu, Y. Zhang, H. Wang, J. Xuan, M. Ni, “Towards online optimisation of solid oxide fuel cell performance: Combining deep learning with multi-physics simulation,” Energy and AI, Vol. 1, p. 100003, 2020.
doi:10.1016/j.egyai.2020.100003
[23]  J. Alvarez Anton, P. Garcia Nieto, F. de Cos J uez, F. Sanchez Lasheras, M. Gonzalez Vega, M. Roqu eni Gutierrez, “Battery state-of-charge estimator using the SVM technique,” Applied Mathematical Modelling, Vol. 37, no. 9, pp. 6244-6253, 2013.
doi:10.1016/j.apm.2013.01.024
[24]  J. C. Alvarez Anton, P. J. Garcia Nieto, C. Blanco Viejo, J. A. Vilan, “Support vector machines used to estimate the battery state of charge,” IEEE Transactions on power electronics, Vol. 28, no. 12, pp. 5919-5926, 2013.
doi:10.1109/TPEL.2013.2243918
[25]  A. Harinarayanan and R. Balamurugan, “Deep learning based state of charge estimation of lithiumion battery for electric vehicle application,” Discover Internet of Things, 2025, doi: 10.1007/s43926-025-00148-y
[26]  F. G. Guo, L. Shui, X. Lan Wu, B. Gang Cao, “SOC Estimation for Li-Ion Battery Using SVM Based on Particle Swarm Optimization,”  Advanced Materials Research, Vol. 1051, pp. 1004-1008, 2014. doi:10.4028/www.scientific.net/AMR.1051.1004
[27]  X. Wu, L. Mi, W. Tan, J. L. Qin, M. N. Zhao, “State of charge (SOC) estimation of ni-mh battery based on least square support vector machines,” Advanced Materials Research, Vol. 211, pp. 1204-1209, 2011.
doi:10.4028/www.scientific.net/AMR.211-212.1204
[28]  G. Gruosso, G. S. Gajani, J. D. Valladolid, D. Patino, F. Ruiz, “State of charge estimation of lifepo4 battery used in electric vehicles using support vector regression, PCA and DP battery model,” In 2019 IEEE vehicle power and propulsion conference (VPPC), pp.1-5, 2019.
doi:10.1109/VPPC46532.2019.8952458
[29]  A. Harinarayanan and R. Balamurugan, “Advanced Techniques for Estimating State of Charge (SoC) in Lithium-Ion Batteries,” J. Energy Storage, vol. 45, 2025. doi:10.21608/astj.2025.391150.1065
[30]  C. G. Manriquez-Padilla, I. Cueva-Perez, A. Dominguez-Gonzalez, D. A. Elvira-Ortiz, A. Perez-Cruz, J. J. Saucedo-Dorantes, “State of Charge Estimation Model Based on Genetic Algorithms and Multivariate Linear Regression with Applications in Electric Vehicles,” Sensors, Vol. 23, no. 6, p. 2924 2023. doi:10.3390/s23062924
[31]  S. Khorashadizadeh, M. Sadeghijaleh, “Adaptive fuzzy tracking control of robot manipulators actuated by permanent magnet synchronous motors,” Computers & Electrical Engineering, Vol. 72, pp. 100-111, 2018.
doi:10.1016/j.compeleceng.2018.09.010
[32]  S. Khorashadizadeh, M. M. Fateh, “Uncertainty estimation in robust tracking control of robot manipulators using the Fourier series expansion,” Robotica, Vol. 35, no. 2, pp. 310-336, 2017.
doi:10.1017/S026357471500051X
[33]  M. Samimi, M. H. Majidi, S. Khorashadizadeh, “Secure communication based on chaos synchronization using brain emotional learning,” AEU-International Journal of Electronics and Communications, Vol. 127, p. 153424, 2020.
doi:10.1016/j.aeue.2020.153424
[34]  H. Drucker, C. J. Burge, L. Kaufman, A. Smola, V. Vapnik, “Support Vector Regression Machines,” Advances in neural information processing systems, Vol. 9, 1996. https://proceedings.neurips.cc/paper/1996/hash/d38901788c533e8286cb6400b40b386d-Abstract.html
[35]  M. Gh. Akbari, Saeed Khorashadizadeh, M. H. Majidi, “Support vector machine classification using semi-parametric model,” Soft Computing, vol. 25, pp. 10040-10062, 2022.
doi:10.1007/s00500-022-07376-2
[36]  M. Chen, G. A. Rincon-Mora, “Accurate electrical battery model capable of predicting runtime and I-V performance,” IEEE transactions on energy conversion, Vol. 21, no. 2, pp. 504-511,2006.
doi:10.1109/TEC.2006.874229
[37]  M. Nouri Khajavi, Gh. R. Bayat, “Comparison of Li-Ion Battery State of Charge Prediction by Artificial Neural Network and Adaptive Neuro Fuzzy Inference System,” Modares Mechanical Engineering, vol. 19, no. 1, pp. 43-52, 2019.
dor:20.1001.1.10275940.1397.19.1.11.1
[38]  S. Hochreiter, J. Schmidhuber, “Long short-term memory,” Neural computation, Vol. 9, no. 8, pp. 1735-1780, 1997.
doi:10.1162/neco.1997.9.8.1735
[39]  B. Saha, K. Goebel, “Battery Data Set,” NASA Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA, 2007.
[40]  A. Maheshwari, S. Nageswari, “Real-time state of charge estimation for electric vehicle power batteries using optimized filter,” Energy, Vol. 254, p. 124328, 2022.
doi:10.1016/j.energy.2022.124328
[41]  Y. Boujoudar, H. Elmoussaoui, T. Lamhamdi, “Lithium-ion batteries modeling and state of charge estimation using artificial neural network,” International Journal of Electrical and Computer Engineering, Vol. 9, no. 5, p. 3415, 2019. doi:10.11591/ijece.v9i5.pp3415-3422
S. Jo, S. Jung, T. Roh, “Battery State-of-Health Estimation Using Machine Learning and Preprocessing with Relative State-of-Charge,” Energies, Vol. 14, no. 21, p. 7206, 021. doi:10.3390/en1421720
مهندسی مکانیک مدرس
دوره 26، شماره 2
بهمن 1404
صفحه 141-156