A5022417497- Advanced Combustion Engine Technologies
- Electric and Hybrid Vehicle Technologies
- Vehicle emissions and performance
- Electric Vehicles and Infrastructure
- Advanced battery technologies research
- Perovskite Materials and Applications
- Autonomous Vehicle Technology and Safety
- Advanced Battery Technologies Research
- Real-time simulation and control systems
- Traffic control and management
- Refrigeration and Air Conditioning Technologies
- Combustion and flame dynamics
- Electrocatalysts for Energy Conversion
- Catalytic Processes in Materials Science
- Reinforcement Learning in Robotics
- Advanced Memory and Neural Computing
- Biodiesel Production and Applications
- Advanced Photocatalysis Techniques
- Indoor and Outdoor Localization Technologies
- Power Systems and Technologies
- Energy Efficient Wireless Sensor Networks
- Ferroelectric and Negative Capacitance Devices
- Aerodynamics and Fluid Dynamics Research
- Underwater Vehicles and Communication Systems
- Microgrid Control and Optimization
Chongqing University of Technology
2017-2025
Anhui University
2023-2025
Shenyang Institute of Automation
2024
Chinese Academy of Sciences
2012-2024
Kunming University of Science and Technology
2023
Wuhan University of Technology
2023
Sinopec (China)
2022
Utah State University
2016-2021
Chongqing University
2021
Xi'an Jiaotong University
2018-2021
Redox flow batteries (RFBs) are a viable technology to store renewable energy in the form of electricity that can be supplied grids. However, widespread implementation traditional RFBs, such as vanadium and Zn-Br2 is limited due number challenges related materials, including low abundance high costs redox-active metals, expensive separators, active material crossover, corrosive hazardous electrolytes. To address these challenges, we demonstrate neutral aqueous organic redox battery (AORFB)...
Abstract Semitransparent organic solar cells have great potential for building integrated photovoltaics and power‐generating windows owing to their advantages of light weight, mechanical flexibility, color tunability. However, the performance previous semitransparent been limited by relatively weak optical absorptions. In this paper, an efficient nonfullerene tandem cell that exhibits a broad absorption from 300 1000 nm is reported. The rear subcell based on narrow‐bandgap acceptor named...
A stable rod-like sulfonated viologen (R-Vi) derivative is developed through a spatial-structure-adjustment strategy for neutral aqueous organic redox flow batteries (AORFBs). The obtained R-Vi features four individual methyl groups on the 2,2',6,6'-positions of 4,4'-bipyridine core ring. tethered methyls confine movement alkyl chain as well sulfonic anion, thus driving spatial structure from sigmoid to rod shape. with weak charge attraction and large molecular dimension displays an ultralow...
With the development of recent artificial intelligence technology, especially after great success AlphaGo, there has been a growing interest in applying reinforcement learning (RL) to solve energy management strategy (EMS) problems for hybrid electric vehicles. However, issues current RL algorithms including deployment inefficiency, safety constraint, and simulation-to-real gap make it inapplicable many industrial EMS tasks. these mind considering fact that exists suboptimal controllers...
With the development of artificial intelligence, there has been a growing interest in machine learning-based control strategy, among which reinforcement learning (RL) opened up new direction field hybrid electric vehicle (HEV) energy management. However, issues current RL setting ranging from inappropriate battery state-of-charge (SOC) constraint to ineffective and risky exploration make it inapplicable many industrial management strategy (EMS) tasks. To address this, an adaptive...
Considering the simulation-to-real gap and fact that data-driven learning methods are often suboptimal, an effective offline-to-online paradigm can further improve initialized offline policy in a real environment is necessary. However, for most industrial applications, this two-stage challenging to implement, as frequently deviates from optimal improvement during fine-tuning. To address this, reinforcement (RL) based training framework bridges initialization online fine-tuning will be...
Microbial ecosystems have been widely used in industrial production, but the inter-relationships of organisms within them haven't completely clarified due to complex composition and structure natural microbial ecosystems. So it is challenging for ecologists get deep insights on how function interplay with surrounding environments. But recent progresses synthetic biology show that construction artificial where relationships species are comparatively clear could help us further uncover meadow...
For the ongoing revolution in developing intelligent and connected vehicles (ICVs), there is a lack of research for powertrain control systems using latest artificial intelligence vehicle-to-everything technology that have already been widely adopted autonomous driving systems. In this context, recent development deep reinforcement learning (DRL) one computing frameworks are coupled to facilitate an onboard-based control. Taking boost diesel engine equipped with variable geometry...
Redox-active 2,2,6,6-tetramethylpiperidine-1-oxyl (TEMPO) derivatives have recently been investigated to expand the choice of catholyte for aqueous flow batteries (AFBs). However, effects substituent R in 4-position on redox potential and corresponding capacity fading mechanism are still unclear. Here, we conduct comparative studies four R-TEMPO with = -OH, -NH2, -COOH, -NHCOCH3 zinc hybrid AFBs. Experimental theoretical analyses reveal that low-radical head charge population sum radical...
Energy management strategy (EMS) is one of the key technologies that improves fuel efficiency hybrid electric vehicles (HEVs) by governing energy flow between tank and storage. With rapid development artificial intelligence especially after great success AlphaGo, reinforcement learning (RL) has opened up a new window for EMS. Although many RL-based solutions have been successfully applied to EMS tasks, most current approaches only consider RL as an offline optimization tool, i.e., used solve...
The intricate interactions with other road users and the diversity of traffic environments create a challenging decision-making task for autonomous driving systems. While offline learning solutions are renowned their high execution efficiency ability to approximate optimal policy across entire state space, they often unsafe fragile when encountering untrained states. Conversely, online planning methods possess capacity thoroughly assess how current decisions influence future outcomes online,...
Deep reinforcement learning (DRL) is an area of machine that combines a deep approach and (RL). However, there seem to be few studies analyze the latest DRL algorithms on real-world powertrain control problems. Meanwhile, boost variable geometry turbocharger (VGT)-equipped diesel engine difficult mainly due its strong coupling with exhaust gas recirculation (EGR) system large lag, resulting from time delay hysteresis between input output dynamics engine’s exchange system. In this context,...
Engine downsizing is a proven approach for achieving superior fuel efficiency. It conventionally achieved by reducing the swept volume of engine and employing some means increasing specific output to achieve desired installed power, usually in form an exhaust-driven turbocharger. However, because perceptible time needed turbocharger system generate required boost pressure, characteristic turbocharged engines their degraded driveability comparison with those naturally aspirated counterparts....