Inteligência artificial na análise de vida útil de baterias / Artificial intelligence in battery life analysis
DOI:
https://doi.org/10.34117/bjdv7n3-227Keywords:
Inteligência Artificial, Teste Elétrico, Degradação de Bateria, Previsão de Vida Útil.Abstract
As baterias são componentes essenciais para muitos dispositivos e sistemas eletroeletrônicos, avaliar corretamente o seu ciclo de vida é importante para evitar trocas desnecessárias e prever possíveis falhas na mesma. Embora a predição de tempo de vida útil de baterias seja uma informação útil, ela ainda é pouco explorada em equipamentos e aplicações comerciais. Objetivo: Este trabalho tem o objetivo de apresentar as principais técnicas de teste de baterias e avaliar a aplicabilidade de determinados algoritmos de inteligência artificial para uma eficiente avaliação dos dados obtidos nos testes, e consequentemente a correta previsão de vida útil desses componentes. Metodologia: Este trabalho foi feito em 2 etapas. A primeira constitui a análise das principais variáveis elétricas utilizadas para avaliação e teste de baterias. Na segunda etapa foram analisados alguns algoritmos de inteligência artificial e sua possível aplicação na previsão de vida útil de baterias, de forma que a metodologia possa ser aplicada independente do tipo de bateria utilizada. Resultados: Com base no levantamento de dados foi possível identificar os algoritmos de inteligência artificial mais adequados para o processamento das informações obtidas nas variáveis de teste e consequentemente uma correta previsão de vida útil de baterias. Conclusão: Embora exista uma grande variedade de algoritmos de inteligência computacional, apenas uma parcela é adequada para o processamento de dados temporais e a correta análise de vida útil de baterias.
References
Akerkar, Rajendra. Artificial intelligence for business. 1st. edition ed. New York, NY: Springer Science+Business Media, 2018.
I. Buchmann. Artificial intelligence reads battery state-of-health in three minutes - IEEE Conference Publication. Disponível em: <https://ieeexplore.ieee.org/document/905135>. Acesso em: 29 abr. 2020.
Beard, K. W. Linden’s Handbook of Batteries, Fifth Edition. 5 edition ed. New York, NY: McGraw-Hill Education, 2019.
Blanke, H. Impedance measurements on lead acid batteries for state-of-charge, state-of-health and cranking capability prognosis in electric and hybrid electric vehicles. Journal of Power Sources, v.144, ed. 2, 2005.
Belova, I. A. et al. Optimization of Artificial Neural Network Learning for Maximum Power Point Tracking After the Degradation of the Solar Battery. 2019 20th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM). Anais... In: 2019 20TH INTERNATIONAL CONFERENCE OF YOUNG SPECIALISTS ON MICRO/NANOTECHNOLOGIES AND ELECTRON DEVICES (EDM). jun. 2019
Chowdhary, K. R. FUNDAMENTALS OF ARTIFICIAL INTELLIGENCE. Place of publication not identified: SPRINGER, INDIA, PRIVATE, 2020.
Cai, Y. et al. Prediction of lithium-ion battery remaining useful life based on hybrid data-driven method with optimized parameter. 2017 2nd International Conference on Power and Renewable Energy (ICPRE). Anais... In: 2017 2ND INTERNATIONAL CONFERENCE ON POWER AND RENEWABLE ENERGY (ICPRE). set. 2017
De Marchi, L.; Mitchell, L. Hands-on neural networks: learn how to build and train your first neural network model using Python. Birmingham, Inglaterra. Packt Publishing, 2019.
Dudney, N. J.; West, W. C.; Nanda, J. (EDS.). Handbook of Solid State Batteries: 2nd Edition. 2nd Revised ed. edition ed. New Jersey London Singapore Beijing Shanghai Hong Kong Taipei Chennai Tokyo: WSPC, 2015.
Enyong HU et al. Study on the aerial storage battery capacity testing method with the fuzzy neural network data fusion technique. 2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC). Anais... In: 2011 2ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE,
MANAGEMENT SCIENCE AND ELECTRONIC COMMERCE (AIMSEC). ago. 2011
Géron, A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems. Sebastopol: Canada: O’Reilly Media, 2019.
How, D. N. T. et al. State-of-Charge Estimation of Li-ion Battery in Electric Vehicles: A Deep Neural Network Approach. 2019 IEEE Industry Applications Society Annual Meeting. Anais... In: 2019 IEEE INDUSTRY APPLICATIONS SOCIETY ANNUAL MEETING. set. 2019.
Huggins, R. Advanced Batteries: Materials Science Aspects. 2009 edition ed. New York?; London: Springer, 2008.
Joshi, N.; SAFARI, AN O. M. C. Hands-On Artificial Intelligence with Java for Beginners. Birmingham, Inglaterra. Packt Publishing, 2018.
Khumprom, P.; Yodo, N. Data-driven Prognostic Model of Li-ion Battery with Deep Learning Algorithm. 2019 Annual Reliability and Maintainability Symposium (RAMS). Anais... In: 2019 ANNUAL RELIABILITY AND MAINTAINABILITY SYMPOSIUM (RAMS). jan. 2019.
Korthauer, R. (ED.). Lithium-Ion Batteries: Basics and Applications. 1st ed. 2018 edition ed. New York, NY: Springer, 2018.
LI, S. et al. Machine learning algorithm based battery modeling and management method: A Cyber-Physical System perspective. 2019 3rd Conference on Vehicle Control and Intelligence (CVCI). Anais... In: 2019 3RD CONFERENCE ON VEHICLE CONTROL AND INTELLIGENCE (CVCI). set. 2019.
Machine Learning Applied to Electrified Vehicle Battery State of Charge and State of Health Estimation: State-of-the-Art - IEEE Journals & Magazine. Disponível em: <https://ieeexplore.ieee.org/document/9036949>. Acesso em: 29 abr. 2020.
Nazri, G.-A.; Pistoia, G. (EDS.). Lithium Batteries: Science and Technology. 2003 edition ed. New York, NY: Springer, 2009.
Plett, G. L. Battery Management Systems: 1. Edição: Unabridged edition ed. Boston?: London: Artech House Publishers, 2015.
Rahn, C. D.; Wang, C.-Y.; Rahn. Battery Systems Engineering. Edição: 1 ed. Chichester, West Sussex, United Kingdom: Wiley, 2013.
Root, M. The TAB Battery Book: An In-Depth Guide to Construction, Design, and Use. 1 edition ed. New York: McGraw- Hill Education TAB, 2010.
Silva, E. L.; MENEZES, E. M. Metodologia da pesquisa e elaboração de dissertação. 4. ed. Florianópolis, 2005.
Veeraraghavan, A. et al. Battery aging estimation with deep learning. 2017 IEEE Transportation Electrification Conference (ITEC-India). Anais... In: 2017 IEEE TRANSPORTATION ELECTRIFICATION CONFERENCE (ITEC-INDIA). dez.
You, W. et al. Predicting the Aging Rate of Capacity in Ni/H Battery Using Artificial Neural Network. 2009 Second International Symposium on Computational Intelligence and Design. Anais... In: 2009 SECOND INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN. dez. 2009
Paredes Larroca, F. et al. Development of a Fuzzy Logic-Based Solar Charge Controller for Charging Lead–Acid Batteries. In: NUMMENMAA, J. et al. (Eds.). . Advances and Applications in Computer Science, Electronics and Industrial Engineering. Advances in Intelligent Systems and Computing. Cham: Springer International Publishing, 2020. v. 1078p.
–183.
Plana-TC Manual do analisador Digital de Bateria c/ Impressora TBI-5000/I Disponível em:
<http://www.planatc.com.br/config/templates/pt_BR/manuais/MN11849.pdf>. Acesso em: 21 maio. 2020.
How does Depth of Discharge factor into Grid Connected battery systems? | CED Greentech. Disponível em:
<https://www.cedgreentech.com/article/how-does-depth-discharge-factor-grid-connected-battery-systems>. Acesso em: 25
