Derechos de autor 2023 Investigación e Innovación en Ingenierías
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Comparación de modelo de predicción de degradación de batería de Li-ion con redes neuronales NAR, NARX y ANFIS
Corresponding Author(s) : Andres Santos
Investigación e Innovación en Ingenierías,
Vol. 11 Núm. 2 (2023): Julio - Diciembre
Resumen
Objetivo: Comparar modelos de degradación de batería de Li-ion basados en redes neuronales NAR, NARX y ANFIS. Metodología: Se usaron redes neuronales NAR, NARX y ANFIS para modelar la degradación de la batería de Li-ion. Las redes neuronales se entrenaron en Matlab con tres diferentes grupos de datos, cada grupo de datos representa un batería diferente y contiene ciclos de carga y descarga en forma de curvas de tensión y corriente, al final de un ciclo de carga-descarga el grupo de datos contiene la capacidad de la batería. Las redes NAR, NARX y ANFIS se comparan entre sí para determinar cual tiene un menor error cuadrático medio (MSE por sus siglas en ingles). Resultados: El mejor modelo que se logró está representado en una red NARX (MSE=3.01x10-5) con una sola capa de quince neuronas y dos datos antecesores tanto en la entrada como en la salida. Conclusiones: Al final se concluye que las redes neuronales NAR y NARX reproducen con mayor fidelidad el comportamiento de la degradación de la batería para los primeros cien ciclos de uso, en comparación a los modelos basados en sistemas ANFIS. En contraste los modelos ANFIS tienen mayor fidelidad, después de los cien primeros ciclos, que los modelos NAR y NARX.
Palabras clave
Descargar cita
Endnote/Zotero/Mendeley (RIS)BibTeX
- T. Horiba, "Lithium-Ion Battery Systems", Proceedings of the IEEE, vol. 102, n.o 6, pp. 939-950, jun. 2014, DOI 10.1109/JPROC.2014.2319832.
- Y. Jia, G. Luo, y Y. Zhang, "Development of optimal speed trajectory control strategy for electric vehicles to suppress battery aging", Green Energy and Intelligent Transportation, vol. 1, n.o 2, p. 100030, sep. 2022, DOI 10.1016/j.geits.2022.100030.
- A. García, J. Monsalve-Serrano, S. Martinez-Boggio, y D. Golke, "Energy assessment of the ageing phenomenon in Li-Ion batteries and its impact on the vehicle range efficiency", Energy Conversion and Management, vol. 276, p. 116530, ene. 2023, DOI 10.1016/j.enconman.2022.116530.
- L. Liu, H. Sun, C. Li, T. Li, J. Xin, y N. Zheng, "Managing Battery Aging for High Energy Availability in Green Datacenters", IEEE Transactions on Parallel and Distributed Systems, vol. 28, n.o 12, pp. 3521-3536, dic. 2017, DOI 10.1109/TPDS.2017.2712778.
- X. Liu et al., "A new dynamic SOH estimation of lead-acid battery for substation application", International Journal of Energy Research, vol. 41, n.o 4, pp. 579-592, 2017, DOI 10.1002/er.3662.
- H. Aaltonen, S. Sierla, V. Kyrki, M. Pourakbari-Kasmaei, y V. Vyatkin, "Bidding a Battery on Electricity Markets and Minimizing Battery Aging Costs: A Reinforcement Learning Approach", Energies, vol. 15, n.o 14, Art. n.o 14, ene. 2022, DOI 10.3390/en15144960.
- S. Dambone Sessa, A. Tortella, M. Andriollo, y R. Benato, "Li-Ion Battery-Flywheel Hybrid Storage System: Countering Battery Aging During a Grid Frequency Regulation Service", Applied Sciences, vol. 8, n.o 11, Art. n.o 11, nov. 2018, DOI 10.3390/app8112330.
- S. Jang y H. Yang, "A Real-Time Scheduling Approach to Mitigation of Li-Ion Battery Aging in Low Earth Orbit Satellite Systems", Electronics, vol. 10, n.o 1, Art. n.o 1, ene. 2021, DOI 10.3390/electronics10010086.
- I. P. Rodrigues, P. A. S. Oliveira, A. M. Ambrosio, y R. A. J. Chagas, "Modeling satellite battery aging for an operational satellite simulator", Advances in Space Research, vol. 67, n.o 6, pp. 1981-1999, mar. 2021, DOI 10.1016/j.asr.2020.12.031.
- B. Gou, Y. Xu, y X. Feng, "State-of-health estimation and remaining-useful-life prediction for lithium-ion battery using a hybrid data-driven method", IEEE Transactions on Vehicular Technology, vol. 69, n.o 10, pp. 10854-10867, 2020, DOI 10.1109/TVT.2020.3014932.
- B. Long, X. Li, X. Gao, y Z. Liu, "Prognostics Comparison of Lithium-Ion Battery Based on the Shallow and Deep Neural Networks Model", ENERGIES, vol. 12, n.o 17, sep. 2019, DOI 10.3390/en12173271.
- P. Wang, X. Dan, y Y. Yang, "A multi-scale fusion prediction method for lithium-ion battery capacity based on ensemble empirical mode decomposition and nonlinear autoregressive neural networks", International Journal of Distributed Sensor Networks, vol. 15, n.o 3, p. 1550147719839637, 2019, DOI 10.1177/1550147719839637.
- S. Bamati y H. Chaoui, "Lithium-ion batteries long horizon health prognostic using machine learning", IEEE Transactions on Energy Conversion, vol. 37, n.o 2, pp. 1176-1186, 2022, DOI 10.1109/TEC.2021.3111525.
- S. Khaleghi et al., "Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network", Applied Energy, vol. 282, p. 116159, 2021, DOI https://doi.org/10.1016/j.apenergy.2020.116159.
- Z. Cui, C. Wang, X. Gao, y S. Tian, "State of health estimation for lithium-ion battery based on the coupling-loop nonlinear autoregressive with exogenous inputs neural network", Electrochimica Acta, vol. 393, p. 139047, oct. 2021, DOI 10.1016/j.electacta.2021.139047.
- H. Meng, M. Geng, J. Xing, y E. Zio, "A hybrid method for prognostics of lithium-ion batteries capacity considering regeneration phenomena", Energy, vol. 261, p. 125278, dic. 2022, DOI 10.1016/j.energy.2022.125278.
- O. Rahbari, C. Mayet, N. Omar, y J. Van Mierlo, "Battery aging prediction using input-time-delayed based on an adaptive neuro-fuzzy inference system and a group method of data handling techniques", Applied Sciences, vol. 8, n.o 8, 2018, DOI 10.3390/app8081301.
- B Saha y K Goebel, "Battery Data Set", presentado en NASA Ames Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA, 2007. [En línea]. Disponible en: https://www.nasa.gov/content/prognostics-center-of-excellence-data-set-repository
- The MathWorks Inc., "Option set for genfis command - genfisOptions". https://la.mathworks.com/help/fuzzy/genfisoptions.html (accedido 7 de junio de 2020).
- The MathWorks Inc., "Adaptive Noise Cancellation Using ANFIS". https://la.mathworks.com/help/fuzzy/adaptive-noise-cancellation-using-anfis.html (accedido 29 de mayo de 2020).
- C. A. Ruíz Ramírez, D. M. Montoya Quintero, y J. A. Jimenez Builes, "Un Ambiente visual integrado de desarrollo para el aprendizaje de programación en robótica", Investigación e Innovación en Ingenierías, vol. 9, n.º 1, pp. 7–21, 2021. DOI: https://doi.org/10.17081/invinno.9.1.3957
Referencias
T. Horiba, "Lithium-Ion Battery Systems", Proceedings of the IEEE, vol. 102, n.o 6, pp. 939-950, jun. 2014, DOI 10.1109/JPROC.2014.2319832.
Y. Jia, G. Luo, y Y. Zhang, "Development of optimal speed trajectory control strategy for electric vehicles to suppress battery aging", Green Energy and Intelligent Transportation, vol. 1, n.o 2, p. 100030, sep. 2022, DOI 10.1016/j.geits.2022.100030.
A. García, J. Monsalve-Serrano, S. Martinez-Boggio, y D. Golke, "Energy assessment of the ageing phenomenon in Li-Ion batteries and its impact on the vehicle range efficiency", Energy Conversion and Management, vol. 276, p. 116530, ene. 2023, DOI 10.1016/j.enconman.2022.116530.
L. Liu, H. Sun, C. Li, T. Li, J. Xin, y N. Zheng, "Managing Battery Aging for High Energy Availability in Green Datacenters", IEEE Transactions on Parallel and Distributed Systems, vol. 28, n.o 12, pp. 3521-3536, dic. 2017, DOI 10.1109/TPDS.2017.2712778.
X. Liu et al., "A new dynamic SOH estimation of lead-acid battery for substation application", International Journal of Energy Research, vol. 41, n.o 4, pp. 579-592, 2017, DOI 10.1002/er.3662.
H. Aaltonen, S. Sierla, V. Kyrki, M. Pourakbari-Kasmaei, y V. Vyatkin, "Bidding a Battery on Electricity Markets and Minimizing Battery Aging Costs: A Reinforcement Learning Approach", Energies, vol. 15, n.o 14, Art. n.o 14, ene. 2022, DOI 10.3390/en15144960.
S. Dambone Sessa, A. Tortella, M. Andriollo, y R. Benato, "Li-Ion Battery-Flywheel Hybrid Storage System: Countering Battery Aging During a Grid Frequency Regulation Service", Applied Sciences, vol. 8, n.o 11, Art. n.o 11, nov. 2018, DOI 10.3390/app8112330.
S. Jang y H. Yang, "A Real-Time Scheduling Approach to Mitigation of Li-Ion Battery Aging in Low Earth Orbit Satellite Systems", Electronics, vol. 10, n.o 1, Art. n.o 1, ene. 2021, DOI 10.3390/electronics10010086.
I. P. Rodrigues, P. A. S. Oliveira, A. M. Ambrosio, y R. A. J. Chagas, "Modeling satellite battery aging for an operational satellite simulator", Advances in Space Research, vol. 67, n.o 6, pp. 1981-1999, mar. 2021, DOI 10.1016/j.asr.2020.12.031.
B. Gou, Y. Xu, y X. Feng, "State-of-health estimation and remaining-useful-life prediction for lithium-ion battery using a hybrid data-driven method", IEEE Transactions on Vehicular Technology, vol. 69, n.o 10, pp. 10854-10867, 2020, DOI 10.1109/TVT.2020.3014932.
B. Long, X. Li, X. Gao, y Z. Liu, "Prognostics Comparison of Lithium-Ion Battery Based on the Shallow and Deep Neural Networks Model", ENERGIES, vol. 12, n.o 17, sep. 2019, DOI 10.3390/en12173271.
P. Wang, X. Dan, y Y. Yang, "A multi-scale fusion prediction method for lithium-ion battery capacity based on ensemble empirical mode decomposition and nonlinear autoregressive neural networks", International Journal of Distributed Sensor Networks, vol. 15, n.o 3, p. 1550147719839637, 2019, DOI 10.1177/1550147719839637.
S. Bamati y H. Chaoui, "Lithium-ion batteries long horizon health prognostic using machine learning", IEEE Transactions on Energy Conversion, vol. 37, n.o 2, pp. 1176-1186, 2022, DOI 10.1109/TEC.2021.3111525.
S. Khaleghi et al., "Online health diagnosis of lithium-ion batteries based on nonlinear autoregressive neural network", Applied Energy, vol. 282, p. 116159, 2021, DOI https://doi.org/10.1016/j.apenergy.2020.116159.
Z. Cui, C. Wang, X. Gao, y S. Tian, "State of health estimation for lithium-ion battery based on the coupling-loop nonlinear autoregressive with exogenous inputs neural network", Electrochimica Acta, vol. 393, p. 139047, oct. 2021, DOI 10.1016/j.electacta.2021.139047.
H. Meng, M. Geng, J. Xing, y E. Zio, "A hybrid method for prognostics of lithium-ion batteries capacity considering regeneration phenomena", Energy, vol. 261, p. 125278, dic. 2022, DOI 10.1016/j.energy.2022.125278.
O. Rahbari, C. Mayet, N. Omar, y J. Van Mierlo, "Battery aging prediction using input-time-delayed based on an adaptive neuro-fuzzy inference system and a group method of data handling techniques", Applied Sciences, vol. 8, n.o 8, 2018, DOI 10.3390/app8081301.
B Saha y K Goebel, "Battery Data Set", presentado en NASA Ames Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA, 2007. [En línea]. Disponible en: https://www.nasa.gov/content/prognostics-center-of-excellence-data-set-repository
The MathWorks Inc., "Option set for genfis command - genfisOptions". https://la.mathworks.com/help/fuzzy/genfisoptions.html (accedido 7 de junio de 2020).
The MathWorks Inc., "Adaptive Noise Cancellation Using ANFIS". https://la.mathworks.com/help/fuzzy/adaptive-noise-cancellation-using-anfis.html (accedido 29 de mayo de 2020).
C. A. Ruíz Ramírez, D. M. Montoya Quintero, y J. A. Jimenez Builes, "Un Ambiente visual integrado de desarrollo para el aprendizaje de programación en robótica", Investigación e Innovación en Ingenierías, vol. 9, n.º 1, pp. 7–21, 2021. DOI: https://doi.org/10.17081/invinno.9.1.3957