Setembro 2025 vol. 12 num. 1 - XXXII Simpósio Internacional de Engenharia

Trabalho completo - Open Access.

Idioma principal | Segundo idioma

Uma nova abordagem para prever o estado de carga e a saúde da bateria usando uma rede neural Elman combinada com otimização de enxame de partículas: Validação com dados experimentais de veículos eletrificados

A novel approach for predicting battery state of charge and health using an Elman Neural Network combined with Particle Swarm Optimization: Validation with experimental data from Electrified Vehicles

MIRANDA, Matheus Henrique Rodrigues ; SILVA, Fabrício Leonardo ; CAMPINO, Miguel ; DUARTE, Gonçalo O. ; FARIAS, Tiago ; SILVA, Ludmila Corrêa de Alkmin e ;

Trabalho completo:

No contexto da eletromobilidade, o sistema de armazenamento de energia é essencial para a autonomia do veículo. Esse sistema representa um custo e peso significativos. O gerenciamento eficiente da bateria envolve desafios como a otimização, dimensionamento, estratégias de gerenciamento, vida útil e descarte apropriado. Para garantir seu funcionamento seguro e eficiente, um sistema de gerenciamento de bateria (BMS) é essencial. Para isso, a estimativa precisa do estado de carga (SoC) e do estado de saúde (SoH) é de grande importância. Este artigo apresenta e discute a abordagem baseada em redes neurais artificiais para estimar o SoC e o SoH de baterias de íons de lítio em veículos eletrificados. A metodologia desenvolvida utiliza uma rede neural do tipo Elman treinada pelo algoritmo de otimização multiobjetivo baseado no enxame de partículas para apenas uma célula de bateria. No entanto, também é apresentado um algoritmo que associa essa rede neural, treinada com uma única célula de bateria em diferentes arranjos em série e paralelo, para descrever diferentes topologias de bateria. A precisão desta metodologia foi validada usando um conjunto de dados experimentais obtidos de um ciclo de condução real realizados por veículos eletrificados devidamente instrumentados.

Trabalho completo:

In the context of electromobility, the energy storage system is essential for vehicle autonomy. It represents a significant cost and adds weight, making it one of the most important components of the vehicle. Efficient battery management involves challenges such as optimization, sizing, management strategies, useful life and appropriate disposal. To ensure its safe and efficient performance, a battery management system (BMS) is essential. For this, accurate estimation of the state of charge (SoC) and state of health (SoH) is of major relevance. This paper presents and discusses an approach based on artificial neural networks for estimating the SoC and SoH of lithium-ion batteries in electrified vehicles. The methodology developed uses an Elman-type neural network trained by a multi-objective optimization algorithm based on the particle swarm (MOPSO) for just one battery cell. However, an algorithm is also presented that associates this neural network, trained with a single battery cell in different series and parallel arrangements, to describe different battery topologies. The accuracy of this methodology was validated using a set of experimental data obtained from a real-world driving cycle performed by duly instrumented electrified vehicles.

Download (PDF)

Palavras-chave: -,

Palavras-chave: -,

DOI: 10.5151/simea2025-PAP17

Referências bibliográficas
  • [1] BREUER, J.L., SCHOLTEN, J., KOJ, J.C., SCHORN, F., FIEBRANDT, M., SAMSUN, R.C., ALBUS, R., GÖRNER, K., STOLTEN, D. AND PETERS, R. An overview of promising alternative fuels for road, rail, air, and inland waterway transport in Germany. Energies, 15(4), p.1443, 2022.
  • [2] EL HAFDAOUI, H., JELTI, F., KHALLAAYOUN, A., JAMIL, A. AND OUAZZANI, K. Energy and environmental evaluation of alternative fuel vehicles in Maghreb countries. Innovation and Green Development, 3(1), p.100092, 2024.
  • [3] HASSAN, Q., AZZAWI, I.D., SAMEEN, A.Z. AND SALMAN, H.M. Hydrogen fuel cell vehicles: opportunities and challenges. Sustainability, 15(15), p.11501, 202
  • [4] GLYNIADAKIS, S. AND BALESTIERI, J.A.P. Brazilian light vehicle fleet decarbonization scenarios for 2050. Energy Policy, 181, p.113682, 2023.
  • [5] SECK, G.S., HACHE, E., SABATHIER, J., GUEDES, F., REIGSTAD, G.A., STRAUS, J., WOLFGANG, O., OUASSOU, J.A., ASKELAND, M., HJORTH, I. AND SKJELBRED, H.I. Hydrogen and the decarbonization of the energy system in europe in 2050: A detailed model-based analysis. Renewable and Sustainable Energy Reviews, 167, p.112779, 2022.
  • [6] CAMARGOS, P.H., DOS SANTOS, P.H., DOS SANTOS, I.R., RIBEIRO, G.S. AND CAETANO, R.E. Perspectives on Li‐ion battery categories for electric vehicle applications: a review of state of the art. International Journal of Energy Research, 46(13), pp.19258-19268, 2022.
  • [7] YADLAPALLI, R.T., KOTAPATI, A., KANDIPATI, R. AND KORITALA, C.S. A review on energy efficient technologies for electric vehicle applications. Journal of Energy Storage, 50, p.104212, 2022.
  • [8] QIU, XIANGHUI; WU, WEIXIONG; WANG, SHUANGFENG. Remaining useful life prediction of lithium-ion battery based on improved cuckoo search particle filter and a novel state of charge estimation method. Journal of Power Sources, v. 450, p. 227700, 2020.
  • [9] STEINSTRAETER, M., BUBERGER, J., MINNERUP, K., TRIFONOV, D., HORNER, P., WEISS, B., & LIENKAMP, M. Controlling cabin heating to improve range and battery lifetime of electric vehicles. eTransportation, v. 13, p. 100181, 2022.
  • [10] YANG, R., XIONG, R., HE, H., MU, H., & WANG, C. A novel method on estimating the degradation and state of charge of lithium-ion batteries used for electrical vehicles. Applied Energy, v. 207, p. 336-345, 2017.
  • [11] XIONG, R., CAO, J., YU, Q., HE, H., & SUN, F. Critical review on the battery state of charge estimation methods for electric vehicles. Ieee Access, v. 6, p. 1832-1843, 2017.
  • [12] LIU, D., YIN, X., SONG, Y., LIU, W., & PENG, Y. An on-line state of health estimation of lithium-ion battery using unscented particle filter. Ieee Access, v. 6, p. 40990-41001, 2018.
  • [13] HOW, D. N., HANNAN, M. A., LIPU, M. H., & KER, P. J. State of charge estimation for lithium-ion batteries using model-based and data-driven methods: A review. Ieee Access, v. 7, p. 136116-136136, 2019.
  • [14] DIAO, WEIPING; SAXENA, SAURABH; PECHT, MICHAEL. Accelerated cycle life testing and capacity degradation modeling of LiCoO2-graphite cells. Journal of Power Sources, v. 435, p. 226830, 2019.
  • [15] LEE, Jong-Hyun; KIM, Hyun-Sil; LEE, In-Soo. State of charge estimation and state of health diagnostic method using multilayer neural networks. In: 2021 International Conference on Electronics, Information, and Communication (ICEIC). IEEE, 2021. p. 1-4.
  • [16] DARBAR, Devendrasinh; BHATTACHARYA, Indranil. Application of machine learning in battery: state of charge estimation using feed forward neural network for sodium-ion battery. Electrochem, v. 3, n. 1, p. 42-57, 2022.
  • [17] HUANG, Z., YANG, F., XU, F., SONG, X., & TSUI, K. L. Convolutional gated recurrent unit–recurrent neural network for state-of-charge estimation of lithium-ion batteries. Ieee Access, v. 7, p. 93139-93149, 2019.
  • [18] MIRANDA, M. H., SILVA, F. L., LOURENÇO, M. A., ECKERT, J. J., & SILVA, L. C. Particle swarm optimization of Elman neural network applied to battery state of charge and state of health estimation. Energy, v. 285, p. 129503, 2023.
  • [19] ZHAO, X., XUAN, D., ZHAO, K., & LI, Z. Elman neural network using ant colony optimization algorithm for estimating of state of charge of lithium-ion battery. Journal of Energy Storage, v. 32, p. 101789, 2020.
  • [20] KOOHI-FAYEGH, S., ROSEN, M. A. A review of energy storage types, applications and recent developments. Journal of Energy Storage, v. 27, p. 101047, 20AEA – Brazilian Society of Automotive Engineering - SIMEA 202511
  • [21] ZHANG, S., GUO, X., DOU, X., & ZHANG, X. A data-driven coulomb counting method for state of charge calibration and estimation of lithium-ion battery. Sustainable Energy Technologies and Assessments, 40, 100752, 2020.
  • [22] SHEPHERD, C. M. Design of primary and secondary cells: II. An equation describing battery discharge. Journal of the electrochemical society, v. 112, n. 7, p. 657, 1965.
  • [23] SAW, L. H., SOMASUNDARAM, K., YE, Y., & TAY, A. A. O. Electro-thermal analysis of Lithium Iron Phosphate battery for electric vehicles. Journal of Power Sources, 249, 231-238, 2014.
  • [24] MOTAPON, S. N., LACHANCE, E., DESSAINT, L. A., & AL-HADDAD, K. A generic cycle life model for lithium-ion batteries based on fatigue theory and equivalent cycle counting. IEEE Open Journal of the Industrial Electronics Society, 1, 207-217, 2020.
  • [25] INTERNATIONAL ORGANIZATION FOR STANDARDIZATION (ISO). Electrically propelled road vehicles - test specification for lithium-ion traction battery packs and systems - part 2: High-energy applications. 2012.
  • [26] KOLLMEYER, P. Panasonic 18650pf li-ion battery data. Mendeley Data, v. 1, n. 2018, 2018.
  • [27] VARELLA, R. A., FARIA, M. V., MENDOZA-VILLAFUERTE, P., BAPTISTA, P. C., SOUSA, L., & DUARTE, G. O. Assessing the influence of boundary conditions, driving behavior and data analysis methods on real driving CO2 and NOx emissions. Science of the total environment, 658, 879-894, 2019.
  • [28] SAE – SOCIETY OF AUTOMOTIVE ENGINEERS. J1711 – Recommended Practice for Measuring the Exhaust Emissions and Fuel Economy of Hybrid-Electric Vehicles. Including Plug-in Hybrid Vehicles. SAE International, 2010.
Como citar:

MIRANDA, Matheus Henrique Rodrigues; SILVA, Fabrício Leonardo; CAMPINO, Miguel; DUARTE, Gonçalo O.; FARIAS, Tiago; SILVA, Ludmila Corrêa de Alkmin e; "Uma nova abordagem para prever o estado de carga e a saúde da bateria usando uma rede neural Elman combinada com otimização de enxame de partículas: Validação com dados experimentais de veículos eletrificados", p. 66-76 . In: Anais do XXXII Simpósio Internacional de Engenharia. São Paulo: Blucher, 2025.
ISSN 2357-7592, DOI 10.5151/simea2025-PAP17

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações