@inproceedings{ba7f8dc315e8463e8f67a9b686883bc8,
title = "Predictive energy management of fuel cell vehicle based on global driving condition construction",
abstract = "Combined with the current development trend of the Internet of Vehicles, this paper proposes a predictive energy management strategy based on working conditions for plug-in fuel cell vehicles. First, relying on the micro-traffic simulation platform, based on the use of neural networks to predict changes in road traffic in the future, a method for constructing global operating conditions is proposed. Combining vehicle speed conditions with predictive energy management strategies, introducing final value constraints in the control time domain into model predictive control (MPC), which improves the energy-saving effect of real-time control strategies from a global perspective. The simulation results show that the comprehensive energy-saving effect of the proposed fuel cell vehicle predicted energy management strategy based on working conditions can reach 93.99% of the theoretical optimal control effect.",
keywords = "fuel cell vehicle, model predictive control, neural network, predictive energy management, traffic information fusion",
author = "Heyang Ma and Biao Liang and Chao Sun and Jinlong Wu",
note = "Publisher Copyright: {\textcopyright} 2024 SPIE.; 4th International Conference on Mechanical, Electronics, and Electrical and Automation Control, METMS 2024 ; Conference date: 26-01-2024 Through 28-01-2024",
year = "2024",
doi = "10.1117/12.3030631",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Khan, {Zeashan Hameed} and Junxing Zhang and Pengfei Zeng",
booktitle = "Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control, METMS 2024",
address = "United States",
}