Energy management strategy for long-life fuel cell hybrid power systems based on improved whale optimization algorithm DOI
Zhichao Fu, Qihong Chen, Ze Zhou

и другие.

Energy Sources Part A Recovery Utilization and Environmental Effects, Год журнала: 2024, Номер 46(1), С. 1 - 16

Опубликована: Июнь 26, 2024

Язык: Английский

Energy management strategy for hybrid electric vehicles based on deep reinforcement learning with consideration of electric drive system thermal characteristics DOI
Jiangyi Qin, Haozhong Huang,

Hualin Lu

и другие.

Energy Conversion and Management, Год журнала: 2025, Номер 332, С. 119697 - 119697

Опубликована: Март 6, 2025

Язык: Английский

Процитировано

0

Aging-aware real-time multi-layer co-optimization approach for hybrid vehicles: across configuration, parameters, and control DOI
Yunge Zou, Yalian Yang, Yuxin Zhang

и другие.

Energy Conversion and Management, Год журнала: 2025, Номер 332, С. 119748 - 119748

Опубликована: Март 25, 2025

Язык: Английский

Процитировано

0

Collaborative optimization of velocity planning and energy management for fuel cell hybrid buses at multiple intersections and bus stations DOI
Xiaohua Wu, Pengfei Ma,

Lingxue Zhou

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 135912 - 135912

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0

Multi-perspective evaluation of a novel powertrain integrating series-parallel and power-split modes: An ultra-rapid hierarchical control approach DOI
Yunge Zou, Yuxin Zhang, Yalian Yang

и другие.

Mechanism and Machine Theory, Год журнала: 2025, Номер 210, С. 106034 - 106034

Опубликована: Апрель 14, 2025

Язык: Английский

Процитировано

0

Energy management strategy for fuel cell hybrid ships based on deep reinforcement learning with multi-optimization objectives DOI
Lin Zhu, Yancheng Liu, Yuji Zeng

и другие.

International Journal of Hydrogen Energy, Год журнала: 2024, Номер 93, С. 1258 - 1267

Опубликована: Ноя. 11, 2024

Язык: Английский

Процитировано

2

A Fuzzy Logic Control-Based Approach for Real-Time Energy Management of the Fuel Cell Electrical Bus Considering the Durability of the Fuel Cell System DOI Creative Commons
Juan Du,

Xiaozhang Zhao,

Xiaodong Liu

и другие.

World Electric Vehicle Journal, Год журнала: 2024, Номер 15(3), С. 92 - 92

Опубликована: Март 1, 2024

The present study proposes a fuzzy logical control-based real-time energy management strategy (EMS) for fuel cell electrical bus (FCEB), taking into account the durability of system (FCS), in order to enhance both vehicle’s economic performance and FCS’s service life. At first, model FCEB is established whilst power-following also formulated as benchmark evaluation proposed strategy. Subsequently, controller designed improve work efficiency FCS, which battery state-of-charge (SOC) desired power are considered inputs, FCS output. Then, limitation method integrated restrict change rate strengthen last, accessed based on China city driving cycle (CCBC). results indicate that can satisfy dynamic well. Importantly, it has remarkable effectiveness terms promoting FCEB’s economy. Despite slight reduction contrast control, improvements still acceptable. be confined ±10 kW. Meanwhile, promotion reach up 8.43%, 7.69%, 6.53% consideration under different SOCs. This will significantly benefit saving durability.

Язык: Английский

Процитировано

1

Hierarchical intelligent energy-saving control strategy for fuel cell hybrid electric buses based on traffic flow predictions DOI
Menglin Li,

Long Yin,

Mei Yan

и другие.

Energy, Год журнала: 2024, Номер 304, С. 132144 - 132144

Опубликована: Июнь 19, 2024

Язык: Английский

Процитировано

1

A Comprehensive Review on Energy Management Strategies for Fuel‐Cell‐Based Electric Vehicles DOI Open Access
Sandeep Kumar, Ankur Bhattacharjee

Energy Technology, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 25, 2024

The rapid growth of the transportation sector in past few decades has contributed significantly to global warming issues, leading extensive research on vehicles having nearly zero or total tailpipe carbon emissions. automobiles within this classification belong hybrid electrical (HEVs), plug‐in HEVs, battery–electric (BEVs), fuel‐cell (FC) EVs (FCEVs), and FC HEVs. FCHEVs are powered by a combination systems, rechargeable batteries, ultracapacitors, and/or mechanical flywheels. technology appears hold potential terms extended driving distances quicker refueling times for that emit no exhaust fumes. A significant number studies have examined various types energy‐storage devices as vehicle power supply, their interfacing with drive mechanism using converters energy management strategies (EMS). In article, EMS FC‐based discussed. Classifications FCEVs, BEVs, EMSs developed researchers. review report, it is indicated existing capable performing well, yet further required better reliability intelligence toward achieving greater fuel efficiency lifetime upcoming FCHEVs.

Язык: Английский

Процитировано

1

An Adaptive Power Management Using a Single Point Of Preview Predictive Model of Reference SOC for Plug-In Hybrid Electric Buses in Consideration of the Full Life Circle of the Battery DOI
Hongliang Guo, Mengyue Li, Kun Zhang

и другие.

Опубликована: Янв. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

Процитировано

0

A Comparative Study of Energy Management Strategies for Fuel Cell Hybrid Vehicles Based on Deep Reinforcement Learning DOI
Siyu Wang, Duo Yang,

Fuhui Yan

и другие.

Опубликована: Янв. 1, 2024

The energy management strategy (EMS) is the top priority to ensure safe and efficient operation of fuel cell hybrid vehicles. Nowadays, EMS based on deep reinforcement learning (DRL) has become a research hotspot. However, there lack unified comparison benchmark for DRL-based EMSs. Most EMSs not discussed impact algorithm hyperparameters, provided comprehensive evaluation indicators including cost, aging efficiency. In this paper, five different DRL methods are designed, multi-objective reward function that integrates equivalent hydrogen consumption, degradation, battery state-of-charge fluctuation its working range designed. First, hyperparameters determined convergence performance in training process. weight coefficients average consumption. Then above-mentioned compared horizontally. Finally, six driving conditions used as test sets explore adaptability results show can be effectively applied real-time environments, algorithms applications, which provide valid guidance researchers use EMS.

Язык: Английский

Процитировано

0