Mei Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mei Yan has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Hongwen He
7 shared publications- Menglin Li
Yanshan University
7 shared publications - Hongwen He
School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China
4 shared publications Menglin Li
4 shared publicationsHongyang Xu
3 shared publications- Jingda Wu
School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China
3 shared publications
Latest Publications
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 16076-16089
Enhancing Fuel Cell Electric Vehicle Efficiency With an Information-Bridged Hierarchical Reinforcement Learning Method
The intelligent transportation system furnishes electrified vehicles with multi-source traffic information, thereby enhancing the potential for greater energy efficiency. Eco-driving and internal energy management represent dual pathways to achieving these efficiencies. Departing from existing studies that typically investigate these pathways independently, this paper introduces a collaborative hierarchical reinforcement learning (RL) method that synchronizes the optimization of both eco-driving and energy management in an integrated solution. To advance RL performance, we propose a novel information bridge scheme at the methodological level. This scheme optimizes the actor-critic RL algorithm’s learning mechanism, facilitating improved information exchange between the dual agents: eco-driving (upper layer) and energy management (lower layer). The critic value of the lower-level agent as a conduit for transmitting condensed state information into the upper, improving the holistic performance. Furthermore, convolutional networks are employed to enhance traffic information extraction. The effectiveness of our method is demonstrated through SUMO simulations, showing a 30.28% improvement in energy efficiency with only a 7.53% compromise in timeliness compared to prevailing Krauss eco-driving. Results also indicate improved training stability and adaptability of our method. This research not only contributes to the optimization of eco-driving for electrified vehicles but also has values in other multi-agent collaborative optimization fields.
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 16076-16089
Enhancing Fuel Cell Electric Vehicle Efficiency With an Information-Bridged Hierarchical Reinforcement Learning Method
The intelligent transportation system furnishes electrified vehicles with multi-source traffic information, thereby enhancing the potential for greater energy efficiency. Eco-driving and internal energy management represent dual pathways to achieving these efficiencies. Departing from existing studies that typically investigate these pathways independently, this paper introduces a collaborative hierarchical reinforcement learning (RL) method that synchronizes the optimization of both eco-driving and energy management in an integrated solution. To advance RL performance, we propose a novel information bridge scheme at the methodological level. This scheme optimizes the actor-critic RL algorithm’s learning mechanism, facilitating improved information exchange between the dual agents: eco-driving (upper layer) and energy management (lower layer). The critic value of the lower-level agent as a conduit for transmitting condensed state information into the upper, improving the holistic performance. Furthermore, convolutional networks are employed to enhance traffic information extraction. The effectiveness of our method is demonstrated through SUMO simulations, showing a 30.28% improvement in energy efficiency with only a 7.53% compromise in timeliness compared to prevailing Krauss eco-driving. Results also indicate improved training stability and adaptability of our method. This research not only contributes to the optimization of eco-driving for electrified vehicles but also has values in other multi-agent collaborative optimization fields.
- 5 December 2024
- Published by Springer Nature
- p. 1-9
A Rapidly Trainable Data-Driven Real-Time Energy Management Strategy for Fuel Cell Hybrid Electric Tractor
- 5 December 2024
- Published by Springer Nature
- p. 1-9
A Rapidly Trainable Data-Driven Real-Time Energy Management Strategy for Fuel Cell Hybrid Electric Tractor
- Open Access
- 27 June 2023
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 20
Data-driven bi-level predictive energy management strategy for fuel cell buses with algorithmics fusion
- 27 June 2023
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 20
Open AccessData-driven bi-level predictive energy management strategy for fuel cell buses with algorithmics fusion
- Open Access
- 16 June 2023
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 2 (4)
Hierarchical predictive energy management strategy for fuel cell buses entering bus stops scenario
- 16 June 2023
- Published by Elsevier in Green Energy and Intelligent Transportation
- Vol. 2 (4)
Open AccessHierarchical predictive energy management strategy for fuel cell buses entering bus stops scenario
- 11 May 2023
- Published by Springer Nature
- p. 152-160
Research on Energy Management Strategy of Fuel Cell Buses In and Out of Bus Stop Based on Speed Optimization
- 11 May 2023
- Published by Springer Nature
- p. 152-160
Research on Energy Management Strategy of Fuel Cell Buses In and Out of Bus Stop Based on Speed Optimization
- Open Access
- 4 December 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (23) , 16190
A Novel Multi-Objective Energy Management Strategy for Fuel Cell Buses Quantifying Fuel Cell Degradation as Operating Cost
Fluctuation in a fuel cell’s output power affects its service life. This paper aims to explore the relationship between power output fluctuation and energy consumption and the cost of the fuel cell system. Hence, based on the actual driving information of vehicles, a novel multi-objective energy management strategy (EMS) for fuel cell buses (FCBs) that quantifies fuel cell life as operating cost is proposed. The actual driving data of FCBs on bus line 727 in Zhengzhou, China, were collected. Based on this, considering the degradation factors of the fuel cell and power battery hybrid energy system, a multi-objective cost framework was established to quantify the life degradation as consumption cost. Furthermore, the influence of different power change limits on the performance of the EMS was analysed based on real-world driving data and the typical Chinese city bus driving cycle, respectively. The simulation results show that the degradation cost of the fuel cell can be effectively reduced when the power change limit is 1 kW, and the simulation results obtained using real-world driving data are very different from those obtained using typical city bus driving cycles. This study provides a reference for the application of a vehicle energy management strategy in real-world scenarios as well as highlights its significance.
- 4 December 2022
- Published by MDPI AG in Sustainability
- Vol. 14 (23) , 16190
Open AccessA Novel Multi-Objective Energy Management Strategy for Fuel Cell Buses Quantifying Fuel Cell Degradation as Operating Cost
Fluctuation in a fuel cell’s output power affects its service life. This paper aims to explore the relationship between power output fluctuation and energy consumption and the cost of the fuel cell system. Hence, based on the actual driving information of vehicles, a novel multi-objective energy management strategy (EMS) for fuel cell buses (FCBs) that quantifies fuel cell life as operating cost is proposed. The actual driving data of FCBs on bus line 727 in Zhengzhou, China, were collected. Based on this, considering the degradation factors of the fuel cell and power battery hybrid energy system, a multi-objective cost framework was established to quantify the life degradation as consumption cost. Furthermore, the influence of different power change limits on the performance of the EMS was analysed based on real-world driving data and the typical Chinese city bus driving cycle, respectively. The simulation results show that the degradation cost of the fuel cell can be effectively reduced when the power change limit is 1 kW, and the simulation results obtained using real-world driving data are very different from those obtained using typical city bus driving cycles. This study provides a reference for the application of a vehicle energy management strategy in real-world scenarios as well as highlights its significance.