Sistema de gestión energética usando un controlador difuso de velocidad optimizada con enjambre artificial de peces basado en un clasificador de aprendizaje neuronal recurrente profundo
Resumen
Los vehículos eléctricos híbridos (VEHs) tienen que garantizar la demanda de potencia utilizando un consumo mínimo de combustible y una estrategia de control. Existen métodos de control , fáciles de aplicar, de respuesta rápida y buen rendimiento. La demanda de energía se debe a numerosos factores, como el nivel de expansión social y económico, la industrialización, la urbanización y el crecimiento tecnológico. Sin embargo, los problemas como el mayor gasto de energía, baja calidad, menor precision, falta de robustez y rango de operación limitado, no se han reducido en los métodos de controlador existentes. Este trabajo presenta un controlador PID difuso (AFSSOF-PIDC) para la optimización de la velocidad de enjambres de peces artificiales. AFSSOF-PIDC-DRNLC incluye varias capas de gestión del tren de potencia. En primer lugar, se consideran varios datos del vehículo como entrada en la capa de entrada y se envían a la capa oculta 1. La aptitud se determina mediante una optimización mejorada de la velocidad del enjambre de peces artificiales para encontrar valores óptimos que minimicen la demanda de potencia y se envía a la capa oculta 2. En la capa oculta 2 se utiliza un controlador PID difuso Mamdani. Si el valor de aptitud de la información del vehículo es inferior al valor umbral, se minimiza el consumo de combustible en el HEV. En caso contrario, el consumo de combustible no se minimiza en el HEV. Por último, la gestión de la energía se consigue minimizando la demanda de potencia. Los resultados indican que el rendimiento de la técnica AFSSOFPIDC-DRNLC propuesta minimiza el consumo de combustible para aumentar el rendimiento del controlador en comparación con los métodos existentes.
Referencias bibliográficas
Ali, M. B., & Boukettaya, G. (2020). Optimal energy management strategies of a parallel hybrid electric vehicle Based on different offline optimization algorithms. International Journal of Renewable Energy Research (IJRER), 10(4), 1621-1637. https://doi.org/10.20508/ijrer.v10i4.11405.g8047
Al‐Sagheer, Y., & Steinberger‐Wilckens, R. (2020). Energy management controller for fuel cell hybrid electric vehicle based on SAT‐NAV data. Fuel Cells, 20(4), 420-430.https://doi.org/10.1002/fuce.201900196
Chen, H., Guo, G., Tang, B., Hu, G., Tang, X., & Liu, T. (2023). Data-driven transferred energy management strategy for hybrid electric vehicles via deep reinforcement learning. Energy Reports, 10, 2680-2692. https://doi.org/10.1016/j.egyr.2023.09.087
Chen, T. C., Ibrahim Alazzawi, F. J., Grimaldo Guerrero, J. W., Chetthamrongchai, P., Dorofeev, A., Ismael, A. M., ... & Esmail Abu Al-Rejal, H. M. (2022). Development of machine learning methods in hybrid energy storage systems in electric vehicles. Mathematical Problems in Engineering, 2022, 1-8. https://doi.org/10.1155/2022/3693263
Chen, Z., Gu, H., Shen, S., & Shen, J. (2022). Energy management strategy for power-split plug-in hybrid electric vehicle based on MPC and double Q-learning. Energy, 245, 123182. https://doi.org/10.1016/j.energy.2022.123182
Chen, Z., Liu, Y., Zhang, Y., Lei, Z., Chen, Z., & Li, G. (2022). A neural network-based ECMS for optimized energy management of plug-in hybrid electric vehicles. Energy, 243, 122727.https://doi.org/10.1016/j.energy.2021.122727
Climent, H., Pla, B., Bares, P., & Pandey, V. (2021). Exploiting driving history for optimising the Energy Management in plug-in Hybrid Electric Vehicles. Energy Conversion and Management, 234, 113919. https://doi.org/10.1016/j.enconman.2021.113919
da Silva, S. F., Eckert, J. J., Silva, F. L., Silva, L. C., & Dedini, F. G. (2021). Multi-objective optimization design and control of plug-in hybrid electric vehicle powertrain for minimization of energy consumption, exhaust emissions and battery degradation. Energy Conversion and Management, 234, 113909.https://doi.org/10.1016/j.enconman.2021.113909
Donatantonio, F., Ferrara, A., Polverino, P., Arsie, I., & Pianese, C. (2022). Novel Approaches for Energy Management Strategies of Hybrid Electric Vehicles and Comparison with Conventional Solutions. Energies, 15(6), 1972.https://doi.org/10.3390/en15061972
Du, R., Hu, X., Xie, S., Hu, L., Zhang, Z., & Lin, X. (2020). Battery aging-and temperature-aware predictive energy management for hybrid electric vehicles. Journal of Power Sources, 473, 228568.https://doi.org/10.1016/j.jpowsour.2020.228568
Fernandes, P., Tomás, R., Ferreira, E., Bahmankhah, B., & Coelho, M. C. (2021). Driving aggressiveness in hybrid electric vehicles: Assessing the impact of driving volatility on emission rates. Applied Energy, 284, 116250. https://doi.org/10.1016/j.apenergy.2020.116250
Gautam, A. K., Tariq, M., Pandey, J. P., Verma, K. S., & Urooj, S. (2022). Hybrid Sources Powered Electric Vehicle Configuration and Integrated Optimal Power Management Strategy. IEEE Access, 10, 121684-121711. https://doi.org/10.1109/ACCESS.2022.3217771.
Hemmati, S., Doshi, N., Hanover, D., Morgan, C., & Shahbakhti, M. (2021). Integrated cabin heating and powertrain thermal energy management for a connected hybrid electric vehicle. Applied Energy, 283, 116353. https://doi.org/10.1016/j.apenergy.2020.116353
Hu, B., Xiao, Y., Zhang, S. and Liu, B. (2023). A Data-Driven Solution for Energy Management Strategy of Hybrid Electric Vehicles Based on Uncertainty-Aware Model-Based Offline Reinforcement Learning, IEEE Transactions on Industrial Informatics, 19 (6), 7709 – 7719. https://doi.org/10.1109/TII.2022.3213026
Hu, D., & Zhang, Y. (2022). Deep reinforcement learning based on driver experience embedding for energy management strategies in hybrid electric vehicles. Energy Technology, 10(6), 2200123. https://doi.org/10.1002/ente.202200123
Hua, M., Zhang, C., Zhang, F., Li, Z., Yu, X., Xu, H., & Zhou, Q. (2023). Energy Management of Multi-mode Plug-in Hybrid Electric Vehicle using Multi-agent Deep Reinforcement Learning. Applied Energy, 348, 1-13. https://doi.org/10.1016/j.apenergy.2023.121526
Javadi, S., & Marzban, M. Investigating on Different Methods of Energy Management System in Hybrid Electric Vehicles and Presenting Proposed Solutions for its Optimization. International Journal of Transportation Systems (IJTS), 68-77. https://www.iaras.org/iaras/filedownloads/ijts/2016/019-0011.pdf
Kamoona, M. A., Kivanc, O. C., & Ahmed, O. A. (2023). Intelligent Energy Management System Evaluation of Hybrid Electric Vehicle Based on Recurrent Wavelet Neural Network and PSO Algorithm. International Journal of Intelligent Engineering & Systems, 16(1). https://doi.org/10.22266/ijies2023.0228.34
Kim, J., Kim, H., Bae, J., Kim, D., Eo, J. S., & Kim, K. K. K. (2020). Economic nonlinear predictive control for real-time optimal energy management of parallel hybrid electric vehicles. IEEE Access, 8, 177896-177920. https://doi.org/10.1109/ACCESS.2020.3027024
Lee, W., Jeoung, H., Park, D., Kim, T., Lee, H., & Kim, N. (2021). A real-time intelligent energy management strategy for hybrid electric vehicles using reinforcement learning. IEEE Access, 9, 72759-72768. https://doi.org/10.1109/ACCESS.2021.3079903
Liu, Y., Huang, Z., Li, J., Ye, M., Zhang, Y., & Chen, Z. (2021). Cooperative optimization of velocity planning and energy management for connected plug-in hybrid electric vehicles. Applied Mathematical Modelling, 95, 715-733. https://doi.org/10.1016/j.apm.2021.02.033
Liu, Y., Wu, Y., Wang, X., Li, L., Zhang, Y., & Chen, Z. (2023). Energy management for hybrid electric vehicles based on imitation reinforcement learning. Energy, 263, 125890. https://doi.org/10.1016/j.energy.2022.125890
Martinez, C. M., Hu, X., Cao, D., Velenis, E., Gao, B., & Wellers, M. (2016). Energy management in plug-in hybrid electric vehicles: Recent progress and a connected vehicles perspective. IEEE Transactions on Vehicular Technology, 66(6), 4534-4549. https://doi.org/10.1109/TVT.2016.2582721
Millo, F., Rolando, L., Tresca, L., & Pulvirenti, L. (2023). Development of a neural network-based energy management system for a plug-in hybrid electric vehicle. Transportation Engineering, 11, 100156. https://doi.org/10.1016/j.treng.2022.100156
Mousa, A. (2023). Extended-deep Q-network: A functional reinforcement learning-based energy management strategy for plug-in hybrid electric vehicles. Engineering Science and Technology, an International Journal, 43, 101434. https://doi.org/10.1016/j.jestch.2023.101434
Neffati, A., & Marzouki, A. (2020). Local energy management in hybrid electrical vehicle via Fuzzy rules system. AIMS Energy, 8(3). https://doi.org/10.3934/energy.2020.3.421
Panday, A., & Bansal, H. O. (2016). Energy management strategy for hybrid electric vehicles using genetic algorithm. Journal of Renewable and Sustainable Energy, 8(1). https://doi.org/10.1063/1.4938552
Parsa, N., Bahmani-Firouzi, B. & Niknam, T. (2021). A social-economic-technical framework for reinforcing the automated distribution systems considering optimal switching and plug-in hybrid electric vehicles. Energy, 220, 1-11. https://doi.org/10.1016/j.energy.2020.119703
Peng, H., Yang, Y., & Liu, C. (2018, February). An energy management for series hybrid electric vehicle using improved dynamic programming. In IOP Conference Series: Earth and Environmental Science (Vol. 121, No. 5, p. 052077). IOP Publishing. https://doi.org/10.1088/1755-1315/121/5/052077
Pulvirenti, L., Rolando, L., & Millo, F. (2023). Energy management system optimization based on an LSTM deep learning model using vehicle speed prediction. Transportation Engineering, 11, 100160.. https://doi.org/10.1016/j.treng.2023.100160
Song, K., Ding, Y., Hu, X., Xu, H., Wang, Y., & Cao, J. (2021). Degradation adaptive energy management strategy using fuel cell state-of-health for fuel economy improvement of hybrid electric vehicle. Applied Energy, 285, 116413. https://doi.org/10.1016/j.apenergy.2020.116413
Udeogu, C. U., & Lim, W. (2022). Improved Deep Learning-Based Energy Management Strategy for Battery-Supercapacitor Hybrid Electric Vehicle With Adaptive Velocity Prediction. IEEE Access, 10, 133789-133802. https://doi.org/10.1109/ACCESS.2022.3232062
Wu, Y., Zhang, Y., Li, G. Shen, J., Chen, Z. & Liu, Y. (2020). A predictive energy management strategy for multi-mode plug-in hybrid electric vehicles based on multi neural networks. Energy, 208, 118366. https://doi.org/10.1016/j.energy.2020.118366
Zeng, X., Qian, Q., Chen, H., Song, D., & Li, G. (2021). A unified quantitative analysis of fuel economy for hybrid electric vehicles based on energy flow. Journal of Cleaner Production, 292, 126040. https://doi.org/10.1016/j.jclepro.2021.126040
Zhang, L.P., Liu, W., & Qi, B. N. (2020). Energy optimization of multi-mode coupling drive plug-in hybrid electric vehicles based on speed prediction. Energy, 206, 118126. https://doi.org/10.1016/j.energy.2020.118126
Zhang, T., Zhao, C., Sun, X., Lin, M. & Chen, Q. (2022). Uncertainty-Aware Energy Management Strategy for Hybrid Electric Vehicle Using Hybrid Deep Learning Method. IEEE Access, 10, 63152 – 63162. https://doi.org/10.1109/ACCESS.2022.3182805
Zhou, D., Zhao, D., Shuai, B., Li, Y., Williams, H., & Xu, H. (2021). Knowledge Implementation and Transfer With an Adaptive Learning Network for Real-Time Power Management of the Plug-in Hybrid Vehicle. IEEE Transactions on Neural Networks and Learning Systems, 32(12), 5298 –5308. https://doi.org/10.1109/TNNLS.2021.3093429
Zhou, J., Xue, S., Xue, Y., Liao, Y., Liu, J. & Zhao, W. (2021). A novel energy management strategy of hybrid electric vehicle via an improved TD3 deep reinforcement learning. Energy, Elsevier, 224, 120118. https://doi.org/10.1016/j.energy.2021.120118
Zhou, Y., Ravey, A., Péra, M. (2020). Multi-objective Energy Management for Fuel Cell Electric 1 Vehicles using Online-Learning Enhanced Markov Speed Predictor, Energy Conversion and Management, 213, 1-36 https://doi.org/10.1016/j.enconman.2020.112821
Zou, R., Fan, L., Dong, Y., Zheng, S., & Hu, C. (2021). DQL energy management: An online-updated algorithm and its application in fix-line hybrid electric vehicle. Energy, 225, 120174. https://doi.org/10.1016/j.energy.2021.120174
Descargas
Derechos de autor 2023 CT&F - Ciencia, Tecnología y Futuro
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
