Volume 11, Issue 2, 2022
All articles in this special issue have been carefully selected to cover new development and research in advanced learning and data analytics for electrified vehicles, covering EMS, BMS, alternative powertrain modeling, simulation, and experimental demonstration, among other topics.
Special Issue Co-Editors:
Xiaosong Hu, Chongqing University, China
Bin Xu, The University of Oklahoma, USA
The SAE International Journal of Electrified Vehicles provides a forum for peer-reviewed scholarly publication of original research and survey papers that address novel modeling tools, control and optimization methods applied to components, systems, and technologies concerning electrified powertrains (hybrid or full electric)–ground, aerial, and naval.
When applied to electrified vehicles, advanced learning and data analytics can be used in energy management, energy system state estimation, vehicle/road condition modeling, environmental perception, path planning/following, vehicle diagnostics, etc. Compared with conventional modeling and control methods, advanced learning and data analytics methods are less dependent on vehicle system physics and experts, which make their development process more automatic. Therefore, they are time and cost effective.
This special issue contains seven articles, focusing on energy management, energy system state estimation, and vehicle/road condition modeling. The first three articles investigate data-driven methods related to energy management strategies, and the other four articles are related to battery systems, including battery thermal management and the battery state-of-charge and state-of-health estimation. To be more specific, reinforcement learning and supervised learning are applied to electrified vehicles under the topic of energy management. In terms of vehicle and road condition modeling, the battery is modeled with neural networks, and vehicle driving cycle velocity is modeled with the Markov decision process. On the topic of energy system estimation, battery state-of-charge and state-of-health estimates are studied.
- A Decentralized Multi-Agent Energy Management Strategy Based on a Look-Ahead Reinforcement Learning Approach
- Hybrid Electric Vehicle Powertrain Control Based on Reinforcement Learning
- Multi-objective Optimization for Connected and Automated Vehicles Using Machine Learning and Model Predictive Control
- A Neural Network-Based Regression Study for a Hybrid Battery Thermal Management System under Fast Charging
- A Method for the Estimation of Cooling System and Driving Performance for Fuel Cell Vehicles Based on Customer Fleet Data
- Robust Data-Driven Battery State of Charge Estimation for Hybrid Electric Vehicles
- A Novel Fitting Method of Electrochemical Impedance Spectroscopy for Lithium-Ion Batteries Based on Random Mutation Differential Evolution Algorithm