Estimación del estado de carga de una batería de litio con redes neuronales y validación con FPGA-en-lazo
Enviado: 05-12-2023
|Aceptado: 13-04-2024
|Publicado: 16-04-2024
Derechos de autor 2024 Erik Martínez-Vera, Alfredo Rosado-Muñoz, Pedro Bañuelos-Sánchez
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Descargas
Palabras clave:
Estado de Carga, Redes Neuronales, FPGA, Batería de Litio, Vehículos Eléctricos
Agencias de apoyo:
Universitat de Valéncia
Universidad de las Américas-Puebla
CONAHCyT
Resumen:
Los vehículos eléctricos presentan una alternativa viable para reducir las emisiones de gases tóxicos en las concentraciones urbanas y para disminuir los efectos de los gases de invernadero. La batería de los vehículos eléctricos debe ser monitoreada con precisión para asegurar su funcionamiento adecuado y seguro. Para esto, es necesario desarrollar algoritmos eficientes que permitan estimar de forma precisa el estado de carga mediante dispositivos embarcados en el vehículo. En este trabajo, se utiliza un conjunto de datos de ciclado de una batería de Litio para entrenar una red neuronal para la estimación del estado de carga. Se realiza una optimización bayesiana para establecer la mejor arquitectura de red neuronal y se valida el comportamiento frente a las mediciones reales que ofrece el conjunto de datos. Para su utilización en un dispositivo embarcado, la red neuronal se valida con un modelo de hardware-en-lazo (HIL) en un FPGA con aritmética de punto fijo. Después del entrenamiento se observa un error promedio cuadrático menor al 2% y una precisión promedio del 97.5%.
Citas:
Ali, A., Faisal, N., Zia, Z., Makda, I., & Usman, A. (2022). Rapid Prototyping of Bidirectional DC-DC Converter Control using FPGA for Electric Vehicle Charging Applications. 2022 IEEE 13th International Symposium on Power Electronics for Distributed Generation Systems (PEDG), 1-6. https://doi.org/10.1109/PEDG54999.2022.9923288
Almaita, E., Alshkoor, S., Abdelsalam, E., & Almomani, F. (2022). State of charge estimation for a group of lithium-ion batteries using long short-term memory neural network. Journal of Energy Storage, 52, 104761. https://doi.org/10.1016/j.est.2022.104761
CBCNews. (2023). Five charts to help understand Canada's record-breaking wildfire season | CBC News. https://www.cbc.ca/news/climate/wildfire-season-2023-wrap-1.6999005
Christophersen, J. P. (2015). Battery Test Manual For Electric Vehicles, Revision 3. https://doi.org/10.2172/1186745
Cui, Z., Dai, J., Sun, J., Li, D., Wang, L., & Wang, K. (2022). Hybrid Methods Using Neural Network and Kalman Filter for the State of Charge Estimation of Lithium-Ion Battery. Mathematical Problems in Engineering, 2022. https://doi.org/10.1155/2022/9616124
Cui, Z., Hu, W., Zhang, G., Zhang, Z., & Chen, Z. (2022). An extended Kalman filter based SOC estimation method for Li-ion battery. Energy Reports, 8, 81-87. https://doi.org/10.1016/j.egyr.2022.02.116
EuroNews. (2023). Libya, Greece, Brazil: Climate-driven storms cause catastrophic flooding around the world | Euronews. https://www.euronews.com/green/2023/09/13/libya-greece-brazil-climate-driven-storms-cause-catastrophic-flooding-around-the-world
Gao, A. Y., Zhang, F. L., Fu, Z. M., Zhang, Z. C., & Li, H. Di. (2017). The SOC estimation and simulation of power battery based on self-recurrent wavelet neural network. Proceedings - 2017 Chinese Automation Congress, CAC 2017, 2017-January, 4247-4252. https://doi.org/10.1109/CAC.2017.8243525
Hun, R., Xu, J., Sun, M., Zhang, S., Chen, Y., & Chiang, P. Y. (2022). Hardware-Software Co-design of Efficient Light-weight Self-Attention Neural Network for Lithium-Ion Batteries State-of-Charge Estimation. 11th International Conference on Communications, Circuits and Systems, ICCCAS 2022. https://doi.org/10.1109/ICCCAS55266.2022.9825471
HWMO. (2023). Wildfire in Hawaii Factsheet - Hawaii Wildfire Management Organization. https://www.hawaiiwildfire.org/fire-resource-library-blog/wildfire-in-hawaii-factsheet
Kang, L. W., Zhao, X., & Ma, J. (2014). A new neural network model for the state-of-charge estimation in the battery degradation process. Applied Energy, 121, 20-27. https://doi.org/10.1016/j.apenergy.2014.01.066
Kollmeyer, P., Vidal, C., Naguib, M., & Skells, M. (2020). LG 18650HG2 Li-ion Battery Data and Example Deep Neural Network xEV SOC Estimator Script. 3. https://doi.org/10.17632/CP3473X7XV.3
Leach, F., Kalghatgi, G., Stone, R., & Miles, P. (2020). The scope for improving the efficiency and environmental impact of internal combustion engines. Transportation Engineering, 1, 100005. https://doi.org/10.1016/j.treng.2020.100005
Liu, Y., He, Y., Bian, H., Guo, W., & Zhang, X. (2022). A review of lithium-ion battery state of charge estimation based on deep learning: Directions for improvement and future trends. Journal of Energy Storage, 52, 104664. https://doi.org/10.1016/j.est.2022.104664
Martinez-Vera, E., Marco, J., Ramirez-Cortes, J. M., & Rangel-Magdaleno, J. (2019). Development of a Lithium-ion Battery Model and State of Charge Estimation Algorithm with Hardware-in-the-loop Validation. 2019 IEEE International Instrumentation & Measurement Technology Conference (I2MTC), 57-61. https://doi.org/10.1109/I2MTC.2019.8827050
MathWorksFPGA. (n.d.). Deploy Neural Network Regression Model to FPGA/ASIC Platform - MATLAB & Simulink - MathWorks España. Retrieved October 26, 2023, from https://es.mathworks.com/help/stats/deploy-neural-network-regression-model-to-fpga-platform.html
MathWorksNN. (2023). Train neural network regression model - MATLAB fitrnet - MathWorks España. https://es.mathworks.com/help/stats/fitrnet.html#mw_7e3de6cb-15e5-434e-82ed-8d870213d539_sep_shared-HyperparameterOptimizationOptions
NASA. (2023). NASA Clocks July 2023 as Hottest Month on Record Ever Since 1880 - NASA. https://www.nasa.gov/news-release/nasa-clocks-july-2023-as-hottest-month-on-record-ever-since-1880/
Nocedal, J., & Wright, S. J. (2006). Numerical Optimization. Springer New York. https://doi.org/10.1007/978-0-387-40065-5
ONU. (2023). Ciudades - Desarrollo Sostenible. https://www.un.org/sustainabledevelopment/es/cities/
Rosero, F., Fonseca, N., López, J. M., & Casanova, J. (2020). Real-world fuel efficiency and emissions from an urban diesel bus engine under transient operating conditions. Applied Energy, 261, 114442. https://doi.org/10.1016/j.apenergy.2019.114442
Shenghao, W. (2021). Improved Algorithm Combining Wavelet Transform and Kalman Filter for Estimating SOC of Lithium-ion Battery in Vehicle. 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2021, 175-179. https://doi.org/10.1109/ICBAIE52039.2021.9390009
Su, J. (2023). Quasi-Newton methods - Cornell University Computational Optimization Open Textbook - Optimization. https://optimization.cbe.cornell.edu/index.php?title=Quasi-Newton_methods
TheGuardian. (2023). A visual guide to Greece's deadly wildfires | Wildfires | The Guardian. https://www.theguardian.com/world/2023/sep/01/greek-wildfires-a-visual-guide
Tiwari, S., Kumar, B., & Tyagi, A. (2022). Artificial Neural Network-based State of Charge (SOC) Estimation of a Lithium-Ion Battery under Different Temperatures Conditions. 2022 IEEE 10th Power India International Conference, PIICON 2022. https://doi.org/10.1109/PIICON56320.2022.10045116
US EPA. (2023). All EPA Emission Standards | US EPA. https://www.epa.gov/emission-standards-reference-guide/all-epa-emission-standards
Vidal, C., Kollmeyer, P., Chemali, E., & Emadi, A. (2019). Li-ion Battery State of Charge Estimation Using Long Short-Term Memory Recurrent Neural Network with Transfer Learning. ITEC 2019 - 2019 IEEE Transportation Electrification Conference and Expo. https://doi.org/10.1109/ITEC.2019.8790543
Yang, B. ;, Wang, Y. ;, Zhan, Y., Yang, B., Wang, Y., & Zhan, Y. (2022). Lithium Battery State-of-Charge Estimation Based on a Bayesian Optimization Bidirectional Long Short-Term Memory Neural Network. Energies 2022, Vol. 15, Page 4670, 15(13), 4670. https://doi.org/10.3390/EN15134670
Ządek, P., Koczor, A., Gołek, M., Matoga, Ł., & Penkala, P. (2015). Improving Efficiency of FPGA-in-the-Loop Verification Environment. IFAC-PapersOnLine, 48(4), 180-185. https://doi.org/10.1016/j.ifacol.2015.07.029
