QDQN-ThermoNet: A quantum-driven dual deep Q-Network framework for intelligent thermal regulation in solid-state and hydrogen fuel cell systems of future electric vehicles

This paper presents QDQN-ThermoNet, a novel Quantum-Driven Dual Deep Q-Network framework for intelligent thermal regulation in next-generation electric vehicles with hybrid energy systems. Our approach introduces a dual-agent architecture where a classical DQN governs solid-state battery thermal management while a quantum-enhanced DQN regulates proton exchange membrane fuel cell dynamics, both sharing a unified quantum-enhanced experience replay buffer to facilitate cross-system information transfer. Hardware-in-the-Loop validation across diverse operational scenarios demonstrates significant performance improvements compared to classical methods, including enhanced thermal stability (95.1 % vs. 82.3 %), faster thermal response (2.1 s vs. 4.7 s), reduced overheating events (0.3 vs. 3.2), and superior energy efficiency (22.4 % energy savings). The quantum-enhanced components deliver 38.7 % greater sample efficiency and maintain robust performance under sparse data conditions (33.9 % improvement), while material-adaptive control strategies leveraging MXene-enhanced phase change materials achieve a 50.3 % reduction in peak temperature rise during transients. Component lifetime analysis reveals a 33.2 % extension in battery service life through optimized thermal management. These results establish QDQN-ThermoNet as a significant advancement in AI-driven thermal management for future electric vehicle platforms, effectively addressing the complex challenges of coordinating thermal regulation across divergent energy sources with different optimal operating temperatures. Highlights • Developed QDQN-ThermoNet , a quantum-driven reinforcement learning framework for EV thermal management. • Leveraged quantum computing to improve stability, response times, and efficiency, particularly under sparse data. • Enhanced thermal regulation of solid-state batteries and hydrogen fuel cells, greatly minimizing overheating. • Confirmed practical applicability and durability through rigorous hardware-based testing. • Integrated advanced MXene-enhanced PCMs to limit peak temperature increases significantly.

Authors

Institutions

Publication Details

Journal
International Journal of Hydrogen Energy
Published
2025-10-25
DOI
https://doi.org/10.1016/j.ijhydene.2025.151979
Primary Topic
Advanced Battery Technologies Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

QDQN-ThermoNet: A quantum-driven dual deep Q-Network framework for intelligent thermal regulation in solid-state and hydrogen fuel cell systems of future electric vehicles

Omer Abbaker Ahmed Mohammed, Sheeraz Iqbal, Muhammad Aurangzeb, Md Shafiullah et al.
International Journal of Hydrogen Energy
Advanced Battery Technologies Research
article

QDQN-ThermoNet: A quantum-driven dual deep Q-Network framework for intelligent thermal regulation in solid-state and hydrogen fuel cell systems of future electric vehicles

Omer Abbaker Ahmed Mohammed, Sheeraz Iqbal, Muhammad Aurangzeb, Md Shafiullah, Kai Meng, Ahmed Mohmed Dafalla, Qingsheng Liu, Shusheng Xiong, Muhammad Zeshan Afzal
article en

Abstract

This paper presents QDQN-ThermoNet, a novel Quantum-Driven Dual Deep Q-Network framework for intelligent thermal regulation in next-generation electric vehicles with hybrid energy systems. Our approach introduces a dual-agent architecture where a classical DQN governs solid-state battery thermal management while a quantum-enhanced DQN regulates proton exchange membrane fuel cell dynamics, both sharing a unified quantum-enhanced experience replay buffer to facilitate cross-system information transfer. Hardware-in-the-Loop validation across diverse operational scenarios demonstrates significant performance improvements compared to classical methods, including enhanced thermal stability (95.1 % vs. 82.3 %), faster thermal response (2.1 s vs. 4.7 s), reduced overheating events (0.3 vs. 3.2), and superior energy efficiency (22.4 % energy savings). The quantum-enhanced components deliver 38.7 % greater sample efficiency and maintain robust performance under sparse data conditions (33.9 % improvement), while material-adaptive control strategies leveraging MXene-enhanced phase change materials achieve a 50.3 % reduction in peak temperature rise during transients. Component lifetime analysis reveals a 33.2 % extension in battery service life through optimized thermal management. These results establish QDQN-ThermoNet as a significant advancement in AI-driven thermal management for future electric vehicle platforms, effectively addressing the complex challenges of coordinating thermal regulation across divergent energy sources with different optimal operating temperatures. Highlights • Developed QDQN-ThermoNet , a quantum-driven reinforcement learning framework for EV thermal management. • Leveraged quantum computing to improve stability, response times, and efficiency, particularly under sparse data. • Enhanced thermal regulation of solid-state batteries and hydrogen fuel cells, greatly minimizing overheating. • Confirmed practical applicability and durability through rigorous hardware-based testing. • Integrated advanced MXene-enhanced PCMs to limit peak temperature increases significantly.

International Journal of Hydrogen EnergyVol. 189
King Fahd University of Petroleum and Minerals (SA), Ministry of Education (RO), Zhejiang Energy Research Institute (CN), Shanghai Electric (China) (CN), University of Nyala (SD), South China Institute of Collaborative Innovation (CN), Zhejiang University (CN)
Openalex Percentile: Top 66%
Advanced Battery Technologies Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.