Application of Artificial Intelligence in Hybrid Electric Vehicle Energy Management

Application of Artificial Intelligence in Hybrid Electric Vehicle Energy Management presents the state of the art in hybrid electric vehicle system modeling and management. With a focus on learning-based energy management strategies, this book provides detailed methods, mathematical models, and strategies designed to optimize the energy management of the energy supply module of a hybrid vehicle.This book first addresses the underlying problems in Hybrid Electric Vehicle (HEV) modeling, and then introduces several artificial intelligence-based energy management strategies of HEV systems, including those based on fuzzy control with driving pattern recognition, multiobjective optimization, fuzzy Q-learning and Deep Deterministic Policy Gradient (DDPG) algorithms. To help readers apply these management strategies, this book also introduces State of Charge and State of Health prediction methods and real-time driving pattern recognition. For each application, the detailed experimental process, program code, experimental results, and algorithm performance evaluation are provided.Application of Artificial Intelligence in Hybrid Electric Vehicle Energy Management is a valuable reference for anyone involved in the modeling and management of hybrid electric vehicles, and will be of interest to graduate students, researchers, and professionals working on HEVs in the fields of energy, electrical, and automotive engineering. Provides a guide to the modeling and simulation methods of hybrid electric vehicle energy systems, including fuel cell systemsDescribes the fundamental concepts and theory behind CNN, MPC, fuzzy control, multi objective optimization, fuzzy Q-learning and DDPGExplains how to use energy management methods such as parameter estimation, Q-learning, and pattern recognition, including battery State of Health and State of Charge prediction, and vehicle operating conditions INDICE: PrefaceAcknowledgments1. Introduction2. System modeling of lithiumeion battery, PEMFC, and supercapacitor in HEV3. Neural network modeling for SOH of lithium-ion battery and performance degradation prediction of fuel cell4.Optimal fuzzy energy management for fuel cell/supercapacitor systems using neural network-based driving pattern recognition5. Optimal fuzzy energy management system optimization based on NSGA-III-SD for lithium battery/supercapacitor HEV6. Q learning-based hybrid energy management strategy7. Improved DDPG hybrid energy management strategy based on LSH8. Further idea on meta EMS for HEVIndex

• ISBN: 978-0-443-13189-9
• Editorial: Elsevier
• Encuadernacion: Rústica
• Páginas: 346
• Fecha Publicación: 03/05/2024
• Nº Volúmenes: 1
• Idioma: Inglés