Search

During the cold-start process of a PEMFC, the supply of air and hydrogen in the gas supply system has a great influence on the cold-start performance. The cold-start of a PEMFC is a complex nonlinear coupling process, and the traditional control strategy is not sensitive to the real-time characteristics of the system. Inspired by the strong perception and decision-making abilities of deep reinforcement learning, this paper proposes a cold-start control strategy for a gas supply system based on the MADDPG algorithm, and designs an air supply controller and a hydrogen supply controller based on this algorithm. The proposed strategy can optimize the control parameters of the gas supply system in real time according to the temperature rise rate of the stack during the cold-start process, the fluctuation of the OER, and the voltage output characteristics. After the strategy is trained offline according to the designed reward function, the detailed in-loop simulation experiment results are given and compared with the traditional control strategy for the gas supply system. From the results, it can be seen that the proposed MADDPG control strategy has a more effective coordination control effect. [ABSTRACT FROM AUTHOR]

Mining-induced hydromechanical behavior of sandstone is critical to mining safety and disaster prevention. To investigate the evolution behavior of the mechanical and permeability properties of sandstone, mining-induced stress was imitated by increasing axial stress and decreasing confining stress, and a set of hydromechanical experiments were further performed, incorporating the effect of in situ stress, pore pressure, and mining stress. The results show the similar variation tendencies of the deformation and permeability of sandstone under different loading paths of in situ stress and pore pressure. Most sandstone samples maintain a compression state for the peak stress condition. The failure mode evolved from shear failure to shear–tension failure with the increase in in situ stress. The stress-relief effect significantly effects the permeability, since the permeability of sandstone increases exponentially with decreasing effective confining stress. The growth rate of permeability in Stage II is significantly greater than that in Stage I. One order of magnitude of permeability was presented at the peak stress situation. A fitting exponential model based on the alteration of effective confining stress was proposed to describe the permeability evolution dominated by the stress-relief effect, and the discovered permeability model can accurately describe the experimental results. The research results provide significant guidance for understanding the hydromechanical behavior and water hazard prevention for underground coal mines. [ABSTRACT FROM AUTHOR]

Since the Industrial Revolution, fossil fuels have become the main energy source for economic development. However, fossil fuels have also been linked to serious environmental impacts. China has recently undergone rapid economic growth, but its development model demands large amounts of energy and causes severe pollution. Therefore, there has been a recent shift toward the development of coordinated strategies to achieve economic growth while minimizing energy consumption and preserving the environment. This study sought to explore the spatiotemporal evolution of the coordination degree between economic growth, energy consumption, and environmental conservation (i.e., the "3E" system) in China, thus establishing a basis to improve coordinated development and minimize regional differences. This study evaluated 30 Chinese provinces using mathematical models. Between 2000 and 2019, the coordinated development level of the components of the 3E system in China increased steadily but remained generally low. Clear spatial agglomeration was also identified at the provincial scale, with the highest values occurring on the east coast and lower values occurring in the west and middle provinces. [ABSTRACT FROM AUTHOR]

Faced with key obstacles, such as the short driving range, long charging time, and limited volume allowance of battery-powered electric light scooters in Asian cities, the aim of this study is to present a passive fuel cell/battery hybrid system without DC-DC to ensure a compact volume and low cost. A novel topology structure of the passive fuel cell/battery power system for the electric light scooter is proposed, and the passive power system runs only on hydrogen. The power performance and efficiency of the passive power system are evaluated by a self-developed test bench before installation into the scooters. The results of this study reveal that the characteristics of stable power output, quick response, and the average efficiency are as high as 88% during the Shanghainese urban driving cycle and 89.5% during the Chinese standard driving cycle. The results present the possibility that this passive fuel cell/battery hybrid powertrain system without DC-DC is practical for commercial scooters. [ABSTRACT FROM AUTHOR]

Due to the low efficiency and high pollution of conventional internal combustion engine vehicles, the fuel cell hybrid electric vehicles are expected to play a key role in the future of clean energy transportation attributed to the long driving range, short hydrogen refueling time and environmental advantages. The development of energy management strategies has an important impact on the economy and durability, but most strategies ignore the aging of fuel cells and the corresponding impact on hydrogen consumption. In this paper, a rule-based fuzzy control strategy is proposed based on the constructed data-driven online estimation model of fuel cell health. Then, a genetic algorithm is used to optimize this fuzzy controller, where the objective function is designed to consider both the economy and durability by combining the hydrogen consumption cost and the degradation cost characterized by the fuel cell health status. Considering that the rule-based strategy is more sensitive to operating conditions, this paper uses an artificial neural network for predictive control. The results are compared with those obtained from the genetic algorithm optimized fuzzy controller and are found to be very similar, where the prediction accuracy is assessed using MAPE, RMSE and 10-fold cross-validation. Experiments show that the developed strategy has a good generalization capability for variable driving cycles. [ABSTRACT FROM AUTHOR]