What does this research mean for the field?

A two-layer hierarchical energy management strategy combining wavelet decomposition, an improved NSGA-III algorithm, and a TD3 agent reduces hydrogen consumption and inter-stack degradation inconsistency in multi-stack fuel cell hybrid vehicles. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop a two-layer hierarchical energy management strategy for multi-stack fuel cell hybrid vehicles that optimizes fuel economy while mitigating uneven inter-stack aging.

August 28, 2026Energy Storage

Durability‐Oriented Energy Management for Multi‐Stack Fuel Cell Hybrid Vehicles

View Full Paper

Ask AI

Bookmark

Authors

YFYisai Fan ZQZhidong Qi ZCZ. H. Cao

Discussion

Member takes

Overview

Hardware-in-the-loop testing demonstrates reduced hydrogen consumption and degradation inconsistency in multi-stack fuel cell vehicles, indicating enhanced system durability and fuel economy.

Key Points

To develop a two-layer hierarchical energy management strategy for multi-stack fuel cell hybrid vehicles that optimizes fuel economy while mitigating uneven inter-stack aging.
Designed an upper layer using a causal sliding-window Daubechies-4 wavelet transform to route high-frequency loads to the battery, paired with an ARP-SC-NSGA-III algorithm to optimize net fuel cell power output.
Implemented a lower-layer TD3 reinforcement learning agent to allocate target fuel cell power among individual stacks in real time according to their degradation states.
Evaluated system performance using hardware-in-the-loop testing across untrained HWFET and WLTP standard driving cycles against fuzzy control and ECMS benchmarks.
Decreased SOC-corrected equivalent hydrogen consumption by up to 9.71% and inter-stack degradation inconsistency by up to 93.84% compared to fuzzy logic control.
Lowered hydrogen consumption by 4.55% under the WLTP cycle compared to the equivalent consumption minimization strategy (ECMS).
Maintained battery state of charge within ±0.05 of the target value across all evaluated drive cycles.

Cite This Study

Fan et al. (2026) studied this question.

synapsesocial.com/papers/6a914631d15324a1df3a998c https://doi.org/10.1002/est2.70503

View Full Paper

Ask AI

Bookmark

August 28, 2026Energy Storage

Durability‐Oriented Energy Management for Multi‐Stack Fuel Cell Hybrid Vehicles

View Full Paper

Ask AI

Bookmark

Authors

YFYisai Fan ZQZhidong Qi ZCZ. H. Cao

Discussion

Member takes

Overview

Hardware-in-the-loop testing demonstrates reduced hydrogen consumption and degradation inconsistency in multi-stack fuel cell vehicles, indicating enhanced system durability and fuel economy.

Key Points

To develop a two-layer hierarchical energy management strategy for multi-stack fuel cell hybrid vehicles that optimizes fuel economy while mitigating uneven inter-stack aging.
Designed an upper layer using a causal sliding-window Daubechies-4 wavelet transform to route high-frequency loads to the battery, paired with an ARP-SC-NSGA-III algorithm to optimize net fuel cell power output.
Implemented a lower-layer TD3 reinforcement learning agent to allocate target fuel cell power among individual stacks in real time according to their degradation states.
Evaluated system performance using hardware-in-the-loop testing across untrained HWFET and WLTP standard driving cycles against fuzzy control and ECMS benchmarks.
Decreased SOC-corrected equivalent hydrogen consumption by up to 9.71% and inter-stack degradation inconsistency by up to 93.84% compared to fuzzy logic control.
Lowered hydrogen consumption by 4.55% under the WLTP cycle compared to the equivalent consumption minimization strategy (ECMS).
Maintained battery state of charge within ±0.05 of the target value across all evaluated drive cycles.

Cite This Study

Fan et al. (2026) studied this question.

synapsesocial.com/papers/6a914631d15324a1df3a998c https://doi.org/10.1002/est2.70503

View Full Paper

Ask AI

Bookmark