Search

The era of Industry 4.0 is gradually transforming our society into a data-driven one, which can help us uncover valuable information from accumulated data, thereby improving the level of social governance. The detection of anomalies, is crucial for maintaining societal trust and fairness, yet it poses significant challenges due to the ubiquity of anomalies and the difficulty in identifying them accurately. This paper aims to enhance the performance of the current Graph Convolutional Network (GCN)-based Graph Anomaly Detection (GAD) algorithm on datasets with extremely low proportions of anomalous labels. This goal is achieved through modifying the GCN network structure and conducting feature extraction, thus fully utilizing three types of information in the graph: node label information, node feature information, and edge information. Firstly, we theoretically demonstrate the relationship between label propagation and feature convolution, indicating that the Label Propagation Algorithm (LPA) can serve as a regularization penalty term for GCN, aiding in training and enabling learnable edge weights, providing a basis for incorporating node label information into GCN networks. Secondly, we introduce a method to aggregate node and edge features, thereby incorporating edge information into GCN networks. Finally, we design different GCN trainable weights for node features and co-embedding features. This design allows different features to be projected into different spaces, greatly enhancing model expressiveness. Experimental results on the DGraph dataset demonstrate superior AUC performance compared to baseline models, highlighting the feasibility and efficacy of the proposed approach in addressing GAD tasks in the scene with extremely low proportions of anomalous data. [ABSTRACT FROM AUTHOR]

A phase-locked loop (PLL) of a phase-shifting power supply for the power system is designed in this paper. Taking the industrial frequency current as the reference signal, the input and output characteristics of the phase-frequency detector with charge pump are analyzed. In addition, the transfer function of the PLL system is analyzed by combining the passive second-order low-pass filter and the voltage-controlled oscillator. As a result, the influence of parameters such as charge pump current, phase margin, and loop bandwidth on the performance of the PLL is investigated, and the optimal parameters of each section are obtained. The results show that the optimized PLL has a locking time of 0.75 s, a pull-out range of 63.16 Hz, and a locking range of 43.82 Hz, with high stability and noise immunity. [ABSTRACT FROM AUTHOR]

The operating parameters of the active direct methanol fuel cell (DMFC) are essential factors affecting its power delivery performance. Different operating parameters lead to variations in the amount of methanol crossover in a DMFC, which might cause overpotential and cathode catalyst poisoning. Due to the complexity of the DMFC system, changes in operating conditions, and correlations among these parameters, it is challenging to maintain output power density while reducing the negative effects of methanol crossover. This paper proposes an adaptive joint optimization method for fuel cell operating parameters. The principle operating parameters are selected by the orthogonal tests, which include an adaptive numerical simulation and multiobjective optimization regarding cell output power density and methanol crossover. The selected parameter combinations are verified by an evaluation model that quantifies the influences of operating parameters on the active DMFC power density and its methanol crossover, where the nonlinear mapping function for the two optimization objectives is obtained. The nondominated sorting genetic algorithm‐II (NSGA‐II) is applied to rapidly obtain the optimal combination. The results show that with the optimal parameters, the maximum power density is increased by 16.7% and the methanol crossover is reduced by 35.1%. [ABSTRACT FROM AUTHOR]

Micro‐porous layer (MPL) is an essential component of the membrane electrode assembly in a direct methanol fuel cell (DMFC). It enables proton transport and maintains the stability of gas diffusion layers. The wettability and internal resistance of MPL directly affect the cell output power density. Herein, a hydrophilic MPL is developed on the anode side of DMFC by depositing Ag‐modified carbon nano‐fiber powder (CNFP). The modification improves the diffusion of methanol–water solution into the anode catalytic layer, leading to an increased catalytic reaction rate and output power density. Moreover, thanks to the lower electrical resistance of CNFP/Ag, the cell's charge transfer and mass transfer resistances can be reduced, which leverage the power densities at different concentrations. The experimental results show that the peak power density of the modified MPL is increased by 42.2% from 25.6$$ 25.6$$ to 32.0 mW cm−2$$ 32.0{\text{\hspace{0.17em}mW\hspace{0.17em}cm}}^{-2}$$. The charge transfer resistance is reduced by 34.8% from 2.784$2.784$ to 1.816 Ω$$ 1.816\text{\hspace{0.17em}}\Omega $$ and a reduction of 43.1% from 1.371$1.371$ to 0.780 Ω$$ 0.780\text{\hspace{0.17em}}\Omega $$ for the mass transfer resistance. [ABSTRACT FROM AUTHOR]

A double spherical shell (DSS) electric field sensor based on charge sensing has characteristics of small size and simple fabrication, which are appropriate for measuring complex electric field environments, but the sensitivity is low. To improve the sensitivity of the DSS electric field sensor, we theoretically analyze the effect of the diameter of the outer spherical shell opening on the sensitivity of the sensor. The sensors with outer spherical shell apertures of 2, 4, and 6 mm are designed and manufactured, and the sensor's sensitivity, linearity, hysteresis, and repeatability are tested. The relative error of the sensor is evaluated by measuring the rotational characteristics of the sensor. The experimental results show that the sensor sensitivity increases with the increase in hole diameter, while the sensor has good linearity, hysteresis, and repeatability after opening the hole. The rotational characteristics experiments' results show that the sensors' relative errors with different apertures are 18, 23, and 31%, respectively. The DSS open-hole structure is more suitable for electric field measurements than the conventional flat plate structure. [ABSTRACT FROM AUTHOR]