The subject addressed is the fault diagnosis of the circuit breaker based on the coil current in the operating circuit. The characteristics of the coil current in the operating circuit are analyzed at length by extracting eight features. The discretization of continuous variables based on the matrix decomposition is applied to change the eight continuous features into discrete variables. Followed by that, the Bayesian algorithm is used to achieve the fault diagnosis based on the discrete variables. Finally, the accuracy of the improved algorithm is verified by the simulation results.
A dual-motor coupling propulsion system with multi-speed transmission offers the possibility of comprehensive improvement of the vehicle, with an increased difficulty and time cost of design though. This paper takes an electric city bus as research object to design a matching dual-motor propulsion system with two-speed transmission. For convenience and rapidity, a bi-level programming method for parameter matching and energy management of the propulsion system is established. The inner level seeks for the optimal control rules concluding gearshift schedule and torque-allocation proportion for instantaneous minimum power loss, while the outer level leverages the particle swarm optimization algorithm (PSO) to seek the optimal propulsion system parameters within reasonable limits. The objective function of the whole loop takes into account the whole power loss of the entire C-WTVC condition. It indicates that the proposed design and energy management strategy provide a significant improvement of the powertrain efficiency and great reduction of the design cost.
Energy management strategy is important for improving fuel economic of hybrid electric vehicles. We present a deep neuroevolution based energy management strategy for hybrid electric vehicles, which learns optimal energy split strategies through evolution of its deep neural networks structure. We define the optimization objective of the deep neural networks by the fuel consumption and properties of target HEV. The deep neural networks controller is learnt through a parallel and evolution way. The simulation results on a standard driving cycles show that the proposed deep neuroevolution method outperforms the DRL based model, and achieves comparative performance to global–‐optimal method–‐dynamic programming.
Lithium-ion batteries of electric vehicles have shorter life and lower safety in high-temperature environment, and battery packs need to be cooled to ensure that they operate in a suitable temperature range. In this study, two different cooling schemes were compared. With the maximum temperature and maximum temperature difference of a battery pack as indices, the thermal characteristics of the battery pack at a high discharge rate were studied by conducting a CFD simulation under fin forced convection cooling and composite cooling (fin and phase change material). The results showed that the maximum temperature and maximum temperature difference of the battery pack at high discharge rates can be significantly reduced under fin forced convection cooling (at low air flow rates) and composite cooling. Under the composite cooling, the system is simpler, and the uniformity between the batteries is better.
In direct photoelectrochemical reduction of CO2, ptype semiconductors are usually used as photocathode to supply light-induced electrons to reduce CO2. However, since the band position at the surface of semiconductor is fixed, the overpotential of CO2 reduction reaction at the interface is unchangeable. Therefore, it is impossible to boost the interfacial reaction through increasing interfacial overpotential. A photoelectrochemical cell (PEC) that consists of an ntype photoanode and a metal cathode offers the opportunity to manipulate the cathode overpotential. Furthermore, by applying different pH values for the anolyte and catholyte, the PEC can be self-contained and no bias voltage is needed.
Battery Is the Bottleneck Technology of Electric Vehicles (Evs), Which Has Complex and Hardly Observable Inside Chemical Reactions. to Reduce the Training Data Volume Requirement in Artificial Intelligent Algorithm Based Battery Model, This Paper Presents a Deep Transfer Learning Algorithm Based Battery Modeling Method. the Deep Belief Network – Extreme Learning Machine (Dbnelm) Algorithm Is Used for Battery Modeling Issue in This Paper to Excavate the Hidden Features in Battery Data Set and Improve the Accuracy and Stability. the Results Show That the Proposed Transfer Learning Algorithm Based Battery Modeling Method Is Able to Achieve a Highly Accurate Simulation for Battery Dynamic Characteristics Under an Insufficient Data Set, and the Mean Absolute Percentage Error of the Established Model Is Within 3%.
This paper presents an experiment study on the composition effect on droplet combustion of ABE mixture fuel. The ratios of ethanol and butanol in ABE are varied. Experimental results show that the micro-explosion characteristics of the two ABE/kerosene droplets are different, which is obviously reflected by (D/D0) 2 curves. Increasing proportion of ethanol will lead to more intense micro-explosion. The process of nucleation in droplets in the early stage of micro-explosion is recorded to investigate the underlying physics. These experimental results show that besides the boiling point difference of ethanol and butanol, ethanol will tend to cause more intense micro-explosion due to insoluble in kerosene than butanol under the same conditions.
To obtain a deep understanding of the pyrolysis mechanism of oil shale kerogen, critical organic intermediate——thermal bitumen was firstly prepared by heating Fushun oil shale up to the critical temperature point (450℃), and then extracted by IL(BmimCl) which was mixed with NMP. Scanning electron microscope, X-ray diffraction, Fourier transform infrared spectrophotometry and flash pyrolysis-gas chromatography-mass spectrometry were employed to investigate the physical and chemical transformation in oil shale pyrolysis and extraction processes. Results showed that thermal bitumen was mainly composed of aliphatic structures. In the thermolysis and extraction courses, aliphatic structures have poor stability by comparison of peak intensities. Thermal bitumen mainly comprised short and middle-chain alkanes/alkenes in the range from C4 to C26.