Decoupled safety supervision empowering efficient and safe energy management for fuel cell vehicles
Authors:
Top Cited Papers
Open Access
- 2 March 2026
- journal article
- research article
- Published by Springer Nature in npj Sustainable Mobility and Transport
- Vol. 3 (1) , 16
Abstract
Simultaneously ensuring operational efficiency and safety of energy systems remains a critical challenge for fuel cell vehicle energy management. Mainstream deep reinforcement learning (DRL) approaches often inadequately address explicit safety constraints, especially concerning lithium-ion battery (LIB) thermal management. This study proposes a safety-guided DRL framework introducing an independent safety-guided network to explicitly and reliably enforce safety constraints. By decoupling safety assurance from objective optimization, our architecture overcomes the mutual interference and reward-tuning difficulties inherent in existing reward-penalty methods. Validated on a fuel cell bus platform, our method outperforms state-of-the-art baselines, improving fuel economy by 8.36% and LIB thermal safety by 10.14% under full-load conditions. Notably, it maintains a zero unsafe duration ratio across real-world scenarios and reduces violation severity by up to 21.88% under extreme thermal conditions. These results demonstrate the proposed method’s robust safety assurance and generalization capability, positioning it as a practical solution for intelligent vehicle energy management.Keywords
Funding Information
- Hong Kong Research Grants Council (T23-701/20-R)
- Hong Kong Polytechnic University (P0048560)
- Wisdom Motors (HK) Limited (P0051097)
This publication has 35 references indexed in Scilit:
- Traffic scenario frozen callback and adaptive neuro-fuzzy inference system based energy management strategy for connected fuel cell busesApplied Energy, 2025
- Bayesian optimization for hyper-parameter tuning of an improved twin delayed deep deterministic policy gradients based energy management strategy for plug-in hybrid electric vehiclesApplied Energy, 2024
- Multi-objective adaptive energy management strategy for fuel cell hybrid electric vehicles considering fuel cell health stateApplied Thermal Engineering, 2024
- Predictive energy management of fuel cell plug-in hybrid electric vehicles: A co-state boundaries-oriented PMP optimization approachApplied Energy, 2024
- Health-conscious predictive energy management strategy with hybrid speed predictor for plug-in hybrid electric vehicles: Investigating the impact of battery electro-thermal-aging modelsApplied Energy, 2023
- Hierarchical thermal management for PEM fuel cell with machine learning approachApplied Thermal Engineering, 2023
- Optimizing fuel economy and durability of hybrid fuel cell electric vehicles using deep reinforcement learning-based energy management systemsEnergy Conversion and Management, 2023
- Twin delayed deep deterministic policy gradient-based deep reinforcement learning for energy management of fuel cell vehicle integrating durability information of powertrainEnergy Conversion and Management, 2022
- Eco-Co-Optimization strategy for connected and automated fuel cell hybrid vehicles in dynamic urban traffic settingsEnergy Conversion and Management, 2022
- Overview of batteries and battery management for electric vehiclesEnergy Reports, 2022