Call for papers: SAE International Journal of Electrified Vehicles
Special Issue on Advanced Learning and Data Analytics Methods for Electrified Vehicles
In recent years, advanced learning and data analytics, such as reinforcement learning, deep reinforcement learning, and machine learning, have gained significant attention in the electrified vehicles (i.e., fuel cell vehicles [FCVs], hybrid electric vehicles [HEVs], and electric vehicles [EVs]) industry. Their flexibility and intelligent characteristics are superior to the contemporary control and modeling methodologies and could improve efficiency, operation, and longevity of the electrified vehicles. The artificial intelligent-enabled reinforcement learning and deep reinforcement learning lift the high ceiling of the electrified vehicle control technologies and enable more possibilities in modeling (either in clustering, classification, or regression). Successful applications of advanced learning and data analytics have been implemented in the energy management strategies (EMS) in FCVs and HEVs, battery management strategies (BMS) in EVs, alternative powertrain sub-components modeling, etc. This special issue will focus on 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. It is a peer-reviewed platform for both industry and academia to present new research and developments.
Potential topics include, but are not limited to:
- Reinforcement learning/ Deep learning in FCVs and HEVs EMS or EVs BMS.
- Energy efficiency optimization for autonomous/ connected electrified vehicles in smart city.
- Data analytics, data driven, learning-based approaches for static and dynamic behavior modeling of powertrain subcomponents for control, optimization, and design purposes.
- Battery pack and fuel cell system design with the help of data analytics.
- Aging, remaining useful lifetime prediction of fuel cells/ batteries by means of artificial intelligence and learning-based algorithms.
- Development of novel diagnosis and prognosis tools based on non-model, unsupervised/supervised classification, deep learning, reinforcement learning to improve durability, reliability, and health condition of fuel cells/ batteries.
- Development of advanced machine learning algorithms, e.g., decentralized learning-based and parallel reinforcement learning in fuel cells and batteries applications.
- Component sizing for alternative powertrain.
- Electrified vehicle operation and performance enhancement.