Song Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Song Huang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Dugang Kang
Chongqing Special Equipment Inspection and Research Institute, Chongqing 401121, China
2 shared publications - Chunchun Jia
Research Centre for Electric Vehicles, Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, China
1 shared publication - Dagang Lu
School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
1 shared publication Dingding Fan
Chongqing Special Equipment Inspection and Research Institute, Chongqing 401121, China
1 shared publication- Donghai Hu
School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
1 shared publication - Fengyan Yi
School of Automotive Engineering, Shandong Jiaotong University, Jinan 250357, China
1 shared publication
Latest Publications
- Open Access
- 1 March 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3204 (1)
Numerical simulation study on temperature rise during rapid filling of 70 MPa high-pressure hydrogen storage cylinders
As a critical component of fuel cell vehicles, the temperature rise effect in 70 MPa high-pressure hydrogen cylinders during rapid filling is a core issue affecting their safety. This study investigates the rapid filling processes of cylinders with different specifications (140 L, 210 L, and 410 L) through numerical simulations. The results indicate that there is a non-linear inverse correlation between filling duration and the final temperature increase. Specifically, the rate of temperature decrease diminishes as the filling process continues. Initially, the highest temperatures occur at the cylinder bottom due to direct hydrogen impingement and isentropic compression. Furthermore, larger cylinder volumes are associated with higher average temperatures and greater maximum temperature rise rates during filling. For instance, a 410 L cylinder reached a peak temperature of 380 K. Across all tested conditions, the internal temperature surpassed the established safety threshold, with the overheating issue becoming more severe as the cylinder volume increased. To ensure the safe operation of 70 MPa hydrogen storage systems, it is imperative to implement temperature rise mitigation strategies, such as reducing the filling rate and employing hydrogen pre-cooling in subsequent engineering practices.
- 1 March 2026
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 3204 (1)
Open AccessNumerical simulation study on temperature rise during rapid filling of 70 MPa high-pressure hydrogen storage cylinders
As a critical component of fuel cell vehicles, the temperature rise effect in 70 MPa high-pressure hydrogen cylinders during rapid filling is a core issue affecting their safety. This study investigates the rapid filling processes of cylinders with different specifications (140 L, 210 L, and 410 L) through numerical simulations. The results indicate that there is a non-linear inverse correlation between filling duration and the final temperature increase. Specifically, the rate of temperature decrease diminishes as the filling process continues. Initially, the highest temperatures occur at the cylinder bottom due to direct hydrogen impingement and isentropic compression. Furthermore, larger cylinder volumes are associated with higher average temperatures and greater maximum temperature rise rates during filling. For instance, a 410 L cylinder reached a peak temperature of 380 K. Across all tested conditions, the internal temperature surpassed the established safety threshold, with the overheating issue becoming more severe as the cylinder volume increased. To ensure the safe operation of 70 MPa hydrogen storage systems, it is imperative to implement temperature rise mitigation strategies, such as reducing the filling rate and employing hydrogen pre-cooling in subsequent engineering practices.
- Open Access
Research Progress in Multi-Domain and Cross-Domain AI Management and Control for Intelligent Electric Vehicles
Recent breakthroughs in artificial intelligence are accelerating the intelligent transformation of vehicles. Vehicle electronic and electrical architectures are converging toward centralized domain controllers. Deep learning, reinforcement learning, and deep reinforcement learning now form the core technologies of domain control. This review surveys advances in deep reinforcement learning in four vehicle domains: intelligent driving, powertrain, chassis, and cockpit. It identifies the main tasks and active research fronts in each domain. In intelligent driving, deep reinforcement learning handles object detection, object tracking, vehicle localization, trajectory prediction, and decision making. In the powertrain domain, it improves power regulation, energy management, and thermal management. In the chassis domain, it enables precise steering, braking, and suspension control. In the cockpit domain, it supports occupant monitoring, comfort regulation, and human–machine interaction. The review then synthesizes research on cross-domain fusion. It identifies transfer learning as a crucial method to address scarce training data and poor generalization. These limits still hinder large-scale deployment of deep reinforcement learning in intelligent electric vehicle domain control. The review closes with future directions: rigorous safety assurance, real-time implementation, and scalable on-board learning. It offers a roadmap for the continued evolution of deep-reinforcement-learning-based vehicle domain control technology.
Open AccessResearch Progress in Multi-Domain and Cross-Domain AI Management and Control for Intelligent Electric Vehicles
Recent breakthroughs in artificial intelligence are accelerating the intelligent transformation of vehicles. Vehicle electronic and electrical architectures are converging toward centralized domain controllers. Deep learning, reinforcement learning, and deep reinforcement learning now form the core technologies of domain control. This review surveys advances in deep reinforcement learning in four vehicle domains: intelligent driving, powertrain, chassis, and cockpit. It identifies the main tasks and active research fronts in each domain. In intelligent driving, deep reinforcement learning handles object detection, object tracking, vehicle localization, trajectory prediction, and decision making. In the powertrain domain, it improves power regulation, energy management, and thermal management. In the chassis domain, it enables precise steering, braking, and suspension control. In the cockpit domain, it supports occupant monitoring, comfort regulation, and human–machine interaction. The review then synthesizes research on cross-domain fusion. It identifies transfer learning as a crucial method to address scarce training data and poor generalization. These limits still hinder large-scale deployment of deep reinforcement learning in intelligent electric vehicle domain control. The review closes with future directions: rigorous safety assurance, real-time implementation, and scalable on-board learning. It offers a roadmap for the continued evolution of deep-reinforcement-learning-based vehicle domain control technology.
- Open Access
Deep Learning-Based Automated Detection of Welding Defects in Pressure Pipeline Radiograph
This study applies deep learning-based object detection technology to defect detection in weld radiographs, proposing a technical solution for accurately identifying the types and locations of defects in weld X-ray radiographs. The research encompasses the construction of a defect dataset, the design of a multi-model object detection network, and the development of an automated film evaluation algorithm. This technology significantly enhances the efficiency and accuracy of detecting and identifying harmful defects on weld radiographs, providing critical technical support for ensuring the safe operation and efficient maintenance of pipelines of pressure equipment.
Open AccessDeep Learning-Based Automated Detection of Welding Defects in Pressure Pipeline Radiograph
This study applies deep learning-based object detection technology to defect detection in weld radiographs, proposing a technical solution for accurately identifying the types and locations of defects in weld X-ray radiographs. The research encompasses the construction of a defect dataset, the design of a multi-model object detection network, and the development of an automated film evaluation algorithm. This technology significantly enhances the efficiency and accuracy of detecting and identifying harmful defects on weld radiographs, providing critical technical support for ensuring the safe operation and efficient maintenance of pipelines of pressure equipment.
- Open Access
Effect of Surface Reaction on the Distribution Characteristics of Temperature and OH Radicals in Microchannel Combustion
Microchannel burners suffer from low combustion efficiency and poor stability in applications. In order to explore the effect of wall reaction on methane/air premixed combustion performances in the microchannel, the effects of wall activity, inlet velocity, pressure, and equivalence ratio on the temperature and radical distribution characteristics were studied by CFD computational simulations. It is found that as the reaction pressure increases, there are more free-radical collisions, causing the reaction temperature to rise. The OH radicals participate in the reaction at the active near wall so that the mass fraction of the OH radical on the active wall is lower than that on the inert wall. As the equivalence ratio increases from 0.6 to 1.2, the high-temperature regions increase but the maximum temperature decreases. The mass fraction of OH radical increases with the increase of the equivalence ratio, and the increase of OH radical near the inert wall is larger than that of the active wall. As the flow rate increases, the disturbance increases, and the combustion reaction becomes more intense, resulting in an increase in the temperature and the mass fraction of OH radicals. The mass fraction of H, O, OH, and CH3 radicals in the inert wall was slightly higher than that in the active wall, in which the peak mass fraction of CH3 radical appeared at the axial position closest to the entrance, while the other three radicals reached the peak at about the same axial position. This study provides a reference for combustion stability in microcombustors.
Open AccessEffect of Surface Reaction on the Distribution Characteristics of Temperature and OH Radicals in Microchannel Combustion
Microchannel burners suffer from low combustion efficiency and poor stability in applications. In order to explore the effect of wall reaction on methane/air premixed combustion performances in the microchannel, the effects of wall activity, inlet velocity, pressure, and equivalence ratio on the temperature and radical distribution characteristics were studied by CFD computational simulations. It is found that as the reaction pressure increases, there are more free-radical collisions, causing the reaction temperature to rise. The OH radicals participate in the reaction at the active near wall so that the mass fraction of the OH radical on the active wall is lower than that on the inert wall. As the equivalence ratio increases from 0.6 to 1.2, the high-temperature regions increase but the maximum temperature decreases. The mass fraction of OH radical increases with the increase of the equivalence ratio, and the increase of OH radical near the inert wall is larger than that of the active wall. As the flow rate increases, the disturbance increases, and the combustion reaction becomes more intense, resulting in an increase in the temperature and the mass fraction of OH radicals. The mass fraction of H, O, OH, and CH3 radicals in the inert wall was slightly higher than that in the active wall, in which the peak mass fraction of CH3 radical appeared at the axial position closest to the entrance, while the other three radicals reached the peak at about the same axial position. This study provides a reference for combustion stability in microcombustors.