Table of Content

15 April 2023 Volume 36 Issue 4

  

Importance Evaluation of Power Grid Nodes Based on Dynamic and Static Indexes

SUN Xiuting,LI Yonggang,ZHANG Xing,XU Zhongyu,YU Yu

Electronic Science and Technology. 2023, 36(4):  1-8.  doi:10.16180/j.cnki.issn1007-7820.2023.04.001

Abstract ( 279 )   HTML ( 63 )   PDF (1044KB) ( 132 )  

Figures and Tables | References | Related Articles | Metrics

With the continuous development of smart grid technology, the scientific and accurate evaluation of smart grid with high reliability is required. The failure of important nodes in the smart grid will lead to large-scale power outages, so the evaluation of the important nodes in the smart grid is an important manifestation of evaluating the reliability of the smart grid.In this study, different dynamic and static comprehensive indicators such as local environment, global attribute, network topology and load level of nodes are studied. These comprehensive indicator models are used to evaluate the importance of nodes in smart grid. Finally, the TOPSIS method is adopted to combine dynamic and static indicators to evaluate the importance of smart grid nodes, and the IEEE-30 nodes are simulated and verified. The results show that the importance of node 6 is relatively high, which should be protected.

Identification and Statistical Analysis of Coal Macerals Based on the Idea of Peak Splitting

CHEN Chun,SHU Huisheng,KAN Xiu,SUN Weizhou

Electronic Science and Technology. 2023, 36(4):  9-20.  doi:10.16180/j.cnki.issn1007-7820.2023.04.002

Abstract ( 256 )   HTML ( 4 )   PDF (3097KB) ( 40 )  

Figures and Tables | References | Related Articles | Metrics

In view of the low accuracy of the existing methods to identify coal macerals, a method for identifying and statistical analysis of coal macerals based on the idea of peak splitting is proposed in this study. The peak offset range of vitrinite of each coal type is determined from the point of view of individual particle, and an adaptive peak finding algorithm is proposed to select the effective peak point of coal and rock particles. In the coal macerals identification stage, the multi-strategy peak position identification algorithm is designed to classify the coal and rock particles into active-inert particles requiring peak clustering and pure vitrinite particles, inertinite particles and exinite particles without peak clustering, and the peak positions of coal and rock particles requiring peak clustering are selected. Then, Gaussian fitting is carried out based on peak splitting rules and statistical methods to determine the threshold values of exinite, vitrinite, and inertinite respectively, and complete the clustering and segmentation of coal and rock particles. The experimental results show that the proposed method can effectively identify single coal particles and realize quantitative statistics of maceral content, with an accuracy of 96.85% and the minimum entropy of 0.615 3. Compared with the traditional method, the proposed method has higher accuracy and has better practical application significance.

SO₂ Diffusion Effect in GIS Equipment Based on CFD Technology

HE Yi,ZHANG Jing,ZHANG Ying,ZHU Chunxiao

Electronic Science and Technology. 2023, 36(4):  21-28.  doi:10.16180/j.cnki.issn1007-7820.2023.04.003

Abstract ( 119 )   HTML ( 3 )   PDF (2541KB) ( 36 )  

Figures and Tables | References | Related Articles | Metrics

GIS equipment faults can be found by detecting SF₆ decomposition materials. However, due to the diffusion effect of decomposition materials inside the equipment, the gas content of detected fault characteristic components will be affected, resulting in insufficient equipment fault judgment. Therefore, the diffusion effect and influencing factors of typical SF₆ decomposition SO₂ in GIS equipment are investigated in this study. Based on CFD technology, this study simulates the diffusion effect of SO₂ inside the equipment. Under the condition of 0.4 Mpa, the influence of 10 initial concentrations on the diffusion of SO₂ is detected, and the function relation between the initial concentration and the concentration when the diffusion is uniform is obtained by fitting, which provides theoretical basis for judging the severity of the fault. Under the conditions of 0.4 MPa,0.5 MPa,0.6 MPa,0.7 MPa and 0.8 Mpa, the time for SO₂ diffusion to reach uniform is 3 940 s,3 850 s,3 740 s,3 630 s and 3 550 s, respectively. These results show that the pressure environment of SF₆ gas has a certain influence on SO₂ diffusion, that is, the higher the pressure, the shorter the time required for the uniform diffusion of SO₂. This study comprehensively discusses the influence of the combined action of pressure and initial concentration on SO₂ diffusion, which provides a theoretical basis for setting the monitoring period of on-line monitoring technology.

Research on Low Mach Number Transitional Cavity Jet Noise Reduction of High-Speed Train Pantograph

TANG Zenan,MIAO Xiaodan,YANG Jian,YUAN Tianchen

Electronic Science and Technology. 2023, 36(4):  29-35.  doi:10.16180/j.cnki.issn1007-7820.2023.04.004

Abstract ( 183 )   HTML ( 4 )   PDF (3302KB) ( 34 )  

Figures and Tables | References | Related Articles | Metrics

The pantograph and its cavity are the main sources of aerodynamic noise in high-speed trains, and it is particularly important to reduce this noise. There is less attention paid to the pantograph cavity compared to the pantograph in previous studies on aerodynamic noise of high-speed trains. In view of the problem of aerodynamic noise reduction of high-speed train pantograph and its cavity, numerical calculation methods are utilized to investigate the flow field characteristics and the law of noise propagation of the simplified high-speed train model under the condition of 350 km·h^-1. The results show that the application of jet on the front edge of the pure cavity can significantly reduce the unsteady flow in the cavity and near the pantograph. When the jet velocity is 27 m·s^-1, the maximum reduction in sound source pressure level of radiated noise on the back wall to the top and side of the cavity is 5 dB, and the noise at the monitoring point on the side of the pantograph is significantly reduced. The proposed study provides a direction for the research of transitional cavity jet noise reduction under low Mach number.

A Review of Research on EEG Signal Preprocessing Methods

LUO Ruipeng,FENG Mingke,HUANG Xin,ZOU Renling,LI Dan

Electronic Science and Technology. 2023, 36(4):  36-43.  doi:10.16180/j.cnki.issn1007-7820.2023.04.005

Abstract ( 1058 )   HTML ( 39 )   PDF (1019KB) ( 251 )  

Figures and Tables | References | Related Articles | Metrics

EEG signal is a complex and important biological signal, which is widely used in the research of brain-like intelligence technology and brain-computer interface. In this study, the types and characteristics of common non-physiological artifacts and physiological artifacts that interfere with normal EEG signals are introduced, and the causes of physiological artifacts are analyzed in detail. Through the review of various EEG artifact removal methods and the analysis of the application status, the research progress of traditional artifact removal methods and new artifact removal methods is compared and summarized, and the advantages and disadvantages of artifact removal methods are further analyzed. Some methods have been successfully applied to the processing of electrocardiogram, ECG and EMG artifacts in EEG signals.The current demand for artifact removal from EEG signals and the problems faced are also given in the present study, and the future research directions are analyzed and prospected.

Helmet Wearing Detection Based on Enhanced Feature Fusion Network

CUI Zhuodong,CHEN Wei,YIN Zhong

Electronic Science and Technology. 2023, 36(4):  44-51.  doi:10.16180/j.cnki.issn1007-7820.2023.04.006

Abstract ( 135 )   HTML ( 5 )   PDF (2574KB) ( 59 )  

Figures and Tables | References | Related Articles | Metrics

Wearing safety helmet is one of the important ways to ensure the safety of workers in production activities. The detection accuracy and speed of the existing helmet detector need to be improved, which makes it difficult for the existing detectors to be applied in real production activities on a large scale. To solve these problems, the helmet detector based on EfficientDet is introduced and improved from the perspective of feature fusion. Specifically, the model reduces the information loss in the process of feature fusion using feature supplement module, and improves the efficiency of feature fusion using improved feature pyramid and adaptive spatial fusion module, and finally achieves the goal of improving performance. Experimental results show that the accuracy of the improved model on the helmet wearing data set is 83.03%, and the model size does not increase significantly. The accuracy of the model on PASCAL VOC 2007 data set is 82.76%.

Research on Transformer Fault Diagnosis Based on Improved Sparrow Search Algorithm Optimization BN

TONG Zhaojing,QIAO Zhengrui,LI Jinxiang,LAN Mengyue,JING Lifei

Electronic Science and Technology. 2023, 36(4):  52-58.  doi:10.16180/j.cnki.issn1007-7820.2023.04.007

Abstract ( 161 )   HTML ( 3 )   PDF (1684KB) ( 39 )  

Figures and Tables | References | Related Articles | Metrics

In view of at the problems of low accuracy and poor stability of transformer fault diagnosis, a transformer fault diagnosis method based on improved sparrow search algorithm and optimized Bayesian network is proposed. By calculating mutual information, the maximum support tree is established and directional processing is carried out to obtain the initial structure of Bayesian network, that is, the initial population, a new cooperation mechanism and sine cosine algorithm are introduced into the algorithm to improve the convergence speed and global search ability of the algorithm. Based on the analysis of dissolved gas in oil, a transformer fault diagnosis model based on improved sparrow search algorithm and optimized Bayesian network is established. In order to prove the superiority of the proposed method, the proposed method is compared with the existing transformer fault diagnosis methods. The results show that the proposed method has the highest fault diagnosis rate and can diagnose the transformer fault more accurately.

A Scientific Literature Recommendation Method Based on Multi-Task Learning

BAI Yingqi,PALIDAN·Tuerxun

Electronic Science and Technology. 2023, 36(4):  59-64.  doi:10.16180/j.cnki.issn1007-7820.2023.04.008

Abstract ( 202 )   HTML ( 5 )   PDF (768KB) ( 44 )  

Figures and Tables | References | Related Articles | Metrics

Traditional recommendation algorithms map text content through topic model or mean value of word vectorization. For the issue that existing methods cannot make full use of text information or ignore word order information, this study proposes a multi-task learning recommendation method for scientific literature. Based on the multi-task learning framework, an encoder is designed and a GL model is established. The GL model is trained to combine content recommendation and text metadata prediction, which improves the sparsity of traditional collaborative filtering and regularizes the collaborative filtering model. Finally, an evaluation test is carried out on public and private data sets respectively, and the superiority of the proposed method is demonstrated by comparing with the existing classical methods.

Super-Resolution Image Reconstruction Algorithm Based on Multi-Feature Gated Feedback Residual Network

SUN Hong,ZHANG Yuxiang

Electronic Science and Technology. 2023, 36(4):  65-70.  doi:10.16180/j.cnki.issn1007-7820.2023.04.009

Abstract ( 157 )   HTML ( 7 )   PDF (1227KB) ( 60 )  

Figures and Tables | References | Related Articles | Metrics

In view of the problem of insufficient feature utilization of low-resolution image in super-resolution reconstruction, a multi-feature gated feedback residual network is proposed based on feedback mechanism and attention mechanism. The network has a simple structure and realizes the reuse of network parameters with a circular way, which can save compute resource effectively. The output features of network iteration are retained to achieve multi-feature fusion. In addition, a further feature refine block is used to extract the reconstructed high-resolution image features to obtain better reconstruction result. Experimental results on five test data sets show that when the scale factor is 4, the peak signal-to-noise ratio of the proposed network is 32.50 dB, 28.83 dB, 27.75 dB, 26.65 dB and 31.12 dB, respectively. Compared with the comparison networks, the test results of the proposed algorithm are significantly improved.

Identification of Foreign Objects on Transmission Lines Using Lightweight Network Algorithm

TANG Zheng,ZHANG Huilin,MA Lixin,LIU Jinzhi,WANG Hao

Electronic Science and Technology. 2023, 36(4):  71-77.  doi:10.16180/j.cnki.issn1007-7820.2023.04.010

Abstract ( 260 )   HTML ( 10 )   PDF (2567KB) ( 56 )  

Figures and Tables | References | Related Articles | Metrics

In view of the power inspection problem caused by various foreign objects on the transmission line, the deep learning image recognition method can be used for detection. This study proposes an improved lightweight network detection algorithm model. By replacing the backbone feature extraction network of YOLOv4 with lightweight neural network GhostNet, the redundancy of feature map generated by image input calculation is reduced. The PANet module of YOLOv4 is modified, and the depth separable convolution module is used to replace the common convolution module, which can reduce the amount of parameter calculation. The results show that, compared with the original YOLOv4 detection algorithm, when the IOU threshold is 0.5, the average accuracy of the improved algorithm decreases by 2.1%, but the detection speed is 2.21 times that of the original algorithm, and the parameter calculation amount is only 17.84% of the original algorithm. The comparison with other algorithms shows that the parameter performance of the proposed algorithm meets the demand. Under the condition of maintaining high accuracy, the detection speed of the proposed algorithm is improved and the computation amount is reduced, which proves the effectiveness and feasibility of the proposed algorithm in target detection.

Dynamic Optimal Scheduling Strategy for Integrated Energy Systems Considering Shiftable Loads

LIU Jinzhi,ZHANG Huilin,MA Lixin,WANG Hao,TANG Zheng

Electronic Science and Technology. 2023, 36(4):  78-83.  doi:10.16180/j.cnki.issn1007-7820.2023.04.011

Abstract ( 215 )   HTML ( 7 )   PDF (2427KB) ( 55 )  

Figures and Tables | References | Related Articles | Metrics

The integrated energy system has attracted wide attention from all walks of life because of its multi-energy complementation, coordination and optimization and other characteristics. However, when the thermal power unit in the system is running, its peak shaving ability has certain limitations. In order to reduce the energy cost of the integrated energy system, increase the energy efficiency of the system and improve its peak shaving capacity, this study proposes a dynamic optimal dispatch strategy for the integrated energy system considering the shiftable load. With the aim of minimizing the overall operation and maintenance cost of the system, a simulation model is built by combining the translational load and related examples, and the adaptive chaotic particle swarm optimization algorithm is used to solve the problem. The results show that when the shiftable load is introduced, the multi-energy microgrid can better achieve the purpose of peak shaving and valley filling, and reduce the overall operating cost of the system, and achieve the effect of energy saving and emission reduction. At the same time, this study compares the traditional particle swarm algorithm with the adaptive chaotic particle swarm algorithm and verifies that the adaptive chaotic particle swarm algorithm is superior to the traditional particle swarm algorithm in terms of accuracy and efficiency.

Hybrid Recommendation Algorithm Fused with User Behavior Sequence Prediction

SUN Hong,LU Meike

Electronic Science and Technology. 2023, 36(4):  84-89.  doi:10.16180/j.cnki.issn1007-7820.2023.04.012

Abstract ( 187 )   HTML ( 5 )   PDF (807KB) ( 39 )  

Figures and Tables | References | Related Articles | Metrics

The capture of user interest hidden in the user behavior sequence is a hot research direction of recommendation algorithms in recent years. The traditional sequence prediction model uses the last product clicked by the user as the target, and establishes the association between user behavior and the target product, but does not fully dig out the sequence relationship between user sequences. This study improves on the traditional DIN model, uses continuous behavior over a period of time as the target vector, uses the transformer structure to complete the sequence-to-sequence prediction task, and further extracts and utilizes the user's deep interest in the user behavior sequence, and it is recommended in conjunction with DIN as an auxiliary feature. The experimental results on the Amazon book and the electronic data sets show that the DIN-based hybrid recommendation model proposed in this study increases the AUC index of the original DIN model by about 0.7% and 1.9%, respectively. It can be seen that the hybrid recommendation based on user behavior sequence prediction can play a certain auxiliary role in the multi-feature recommendation system. In addition, the influence of user sequence length on the model results is also explored.

Summary of Research on Table Tennis Trajectory Prediction and Rotation Measurement

LÜ Chengxu,FAN Suozhong,JI Yunfeng,YOU Yiping

Electronic Science and Technology. 2023, 36(4):  90-102.  doi:10.16180/j.cnki.issn1007-7820.2023.04.013

Abstract ( 682 )   HTML ( 15 )   PDF (1529KB) ( 148 )  

Figures and Tables | References | Related Articles | Metrics

In the process of table tennis man-machine sparring, the ball will rotate when it collides with the racket/table, which will cause the sphere to deviate due to the influence of the Magnus force. Therefore, it is difficult to meet the requirements of accurate trajectory prediction of table tennis robot. Trajectory prediction and rotation measurement technology can help improve the robot's ability of prediction and striking. In order to help researchers in this field understand the research methods and existing technologies of table tennis trajectory prediction and rotation measurement, the new developments in the research of table tennis trajectory prediction and rotation measurement are reviewed. After reclassifying and sorting out the research results based on the research achievements in this field in recent years, the advantages and disadvantages of different methods are analyzed and the key issues are sorted out. Finally, the future research trend of table tennis trajectory prediction and rotation measurement is prospected.