Table of Content

15 July 2024 Volume 37 Issue 7

  

Identification Strategy of Power Grid Weak Links Based on Random Matrix Theory

YANG Jie, SUN Weiqing, MA Meiling

Electronic Science and Technology. 2024, 37(7):  1-8.  doi:10.16180/j.cnki.issn1007-7820.2024.07.001

Abstract ( 130 )   HTML ( 12 )   PDF (2265KB) ( 125 )  

Figures and Tables | References | Related Articles | Metrics

With the continuous expansion of the scale of bulk power grid, the operating characteristics of new power system has become more and more complex. Accurately identifying the weak links in the power grid is of great practical significance for improving the monitoring ability of the system and ensuring its reliable operation. Therefore, an identification strategy of weak links for power grid is proposed based on random matrix theory. The strategy uses the measured data in power grid operation to construct a random matrix and uses the weak links judgment index based on the random matrix theory to design the judgment method of weak nodes and weak branches. This method is analyzed from the perspective of data correlation, without considering the complex network structure and operation mechanism of the actual power grid, so there is no complex modeling process. To verify the feasibility of the method, an example simulation is established through the IEEE 39 node system and compared with the traditional methods. The results show that the proposed identification strategy has a good effect on identifying weak nodes and branches, and the accuracy is improved compared with the traditional methods.

Intelligent Equalization Method of Battery Pack Based on Two-Level Equalization Circuit

REN Zihao, TIAN Engang

Electronic Science and Technology. 2024, 37(7):  9-15.  doi:10.16180/j.cnki.issn1007-7820.2024.07.002

Abstract ( 59 )   HTML ( 4 )   PDF (850KB) ( 47 )  

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem of low efficiency of traditional balanced electric topology, a two-level balanced topology is proposed. This balancing topology divides the battery pack into two forms: Intra-group and inter-group. Buck-Boost equalization circuit is used in the group, and reconfigurable equalization circuit is used between the groups. The intra-group and inter-group can be equalized at the same time, which improves the equalization efficiency. Taking SOC(State of Charge) as the equalization variable, the intra-group equalization algorithm adopts the fuzzy logic control strategy based on SOC to reduce the equalization time and improve the equalization efficiency. MATLAB/Simulink software is used to model and simulate the circuit topology and the results are compared with the traditional Buck-Boost circuit. The simulation results show that compared with the traditional Buck-Boost circuit, the proposed algorithm and equalization topology reduce the equalization time by about 28% under the charge-discharge state, indicating that the equalization circuit and algorithm have good performance.

Automatic Summarization of Small Samples Based on Enhanced Regularization

LI Qing, WAN Weibing

Electronic Science and Technology. 2024, 37(7):  16-24.  doi:10.16180/j.cnki.issn1007-7820.2024.07.003

Abstract ( 32 )   HTML ( 4 )   PDF (1411KB) ( 40 )  

Figures and Tables | References | Related Articles | Metrics

Automatic text summarization aims to extract the main statements from text information for the purpose of compressing information. Existing generative automatic summarization methods do not take full advantage of the pre-trained model to learn the semantics of the original text, resulting in the loss of important information in the generated content, when the data set with a small number of samples is often prone to overfitting. In order to solve such problems and obtain better fine-tuning performance, the pre-trained model mT5(multilingual T5) is used as a baseline to improve the learning ability of the model by combining R-drop(Regularized dropout) with reinforced regularity for model fine-tuning, and Sparse softmax is used to reduce the ambiguity of prediction generation to ensure the accuracy of the output. The model calculates BLEU(Bilingual Evaluation Understudy) for hyperparameter test on Chinese data sets LCSTS and CSL, and uses Rouge as evaluation index to evaluate data sets of different orders of magnitude. The experimental results show that the optimized pre-trained model can better learn the semantic representation of the original text, and the model can maintain a good fit in the small samples and generate more practical results.

Scene Recognition Algorithm Based on Discriminative Patch Extraction and Two-Stage Classification

HAN Yinghao, LI Feifei

Electronic Science and Technology. 2024, 37(7):  25-32.  doi:10.16180/j.cnki.issn1007-7820.2024.07.004

Abstract ( 50 )   HTML ( 4 )   PDF (2407KB) ( 44 )  

Figures and Tables | References | Related Articles | Metrics

In the scene recognition task, there are cases where heterogeneous scenes contain items with high similarity or the spatial layout of similar scenes is too different, that is, the inter-class similarity and intra-class difference of scenes.Existing methods improve the discriminant ability of classifiers by enhancing data sets or using multi-level information complementation. Although some improvements have been made, there are still limitations.In this study, the DPE(Discriminative Patch Extraction) and TSC(Two-Stage Classification) network method are proposed to overcome the inter-class similarity and intra-class difference of scenes. DPE avoids the impact of intra-class differences on scene recognition by preserving the key information regions in images, while the TSC network avoids the impact of inter-class similarities on scene recognition by the coarse-fine two-stage training.After combining the proposed method with baseline networks such as ViT(Vision Transformer), the classification accuracy of classical scene recognition data sets Scene15, MITindoor67 and SUN397 reaches 96.9%, 88.4% and 76.0%, respectively. The proposed method achieves the highest classification accuracy of 60.5% on the largest scene recognition dataset Places365.

Research on AGV Path Fusion of Object Detection and DWA Algorithm

LI Jun, LIU Hu, YANG Haima, WANG Yuan, XU Wencheng, HUANG Hongxin

Electronic Science and Technology. 2024, 37(7):  33-42.  doi:10.16180/j.cnki.issn1007-7820.2024.07.005

Abstract ( 69 )   HTML ( 8 )   PDF (4156KB) ( 45 )  

Figures and Tables | References | Related Articles | Metrics

In view of the path planning and navigation problem when the AGV forklift is in the situation of unknown environment information or dynamic change of environment, a method is proposed to obtain the target position by YOLOv5(You Only Look Once version 5) target detection algorithm. The global basic path is planned according to the target location, and the method of AGV path planning and navigation is integrated with DWA(Dynamic Window Approach) local dynamic path planning algorithm, so that the AGV forklift can quickly identify the target location and complete the path planning to reach the target location in the unknown environment or the environment with unknown local environment information. The experimental results show that compared with the previous method, the proposed method has good performance in terms of path length, time consumption and heading error of AGV forklift truck. The average path length is reduced by 12%, the average time consumption is reduced by about 5%, and the average error between the AGV heading and the target heading is within 5°. The proposed method can improve the working efficiency and flexibility of AGV forklift in unknown environment.

A Self-Supervised CT Image Classification Method Incorporating Intra-Slice Semantic and Inter-Slice Structural Features

CAO Chunping, XU Zhihua

Electronic Science and Technology. 2024, 37(7):  43-52.  doi:10.16180/j.cnki.issn1007-7820.2024.07.006

Abstract ( 39 )   HTML ( 2 )   PDF (1952KB) ( 43 )  

Figures and Tables | References | Related Articles | Metrics

In view of the scarcity of artificial labels and poor classification performance in CT(Computed Tomography) image analysis, a self-supervised CT image classification method combining in-slice semantic and interslice structural features is proposed in this study.In this method, the hierarchical structure of CT images and the semantic features of local components are utilized to process the unlabeled lesion images through the confusion section generation algorithm, and the spatial index and confusion section are generated as supervisory information.In the self-supervised auxiliary task, the ResNet50 network was used to extract both the intraslice semantic and interslice structural features related to the lesion site from the confused sections, and the learned features were transferred to the subsequent medical classification task, so that the final model gained from the unlabeled data.The experimental results show that compared with other 2D and 3D models for CT images, the proposed method can achieve better classification performance and label utilization efficiency when the used labeled data is limited.

Pavement Pothole Detection Method Based on Improved YOLOv5

HE Xing, HUANG Yongming, ZHU Yong

Electronic Science and Technology. 2024, 37(7):  53-59.  doi:10.16180/j.cnki.issn1007-7820.2024.07.007

Abstract ( 94 )   HTML ( 10 )   PDF (2169KB) ( 83 )  

Figures and Tables | References | Related Articles | Metrics

Pothole is a common road disease, it reduce driving safety, accurate and rapid detection of potholes is more important.In viewof the problem that the detection accuracy of existing pothole detection methods is not high in the scenario of small targets and dense targets, an improved YOLOv5(You Only Look Once version 5) model is proposed in this study.TheCBAM(Convolutional Block Attention Module) is introduced into YOLOv5's backbone network to improve the model's ability to pay attention to key features. The loss function of YOLOv5 is changed to EIoU(Efficient Intersection over Union) to improve the detection accuracy of the model.The experimental results show that the proposed model can detect Potholes quickly and accurately in the scenarios of small targets and dense targets, and the mAP(mean Average Precision) in the open source Annotated Potholes Image Dataset reaches 82%. Compared with YOLOv5 and other mainstream methods, it is also improved.

Coarse Registration Method of Double-Layer Sampling Point Cloud for Shield Topography Reconstruction

WAN Shengrui, ZHOU Zhifeng, WU Minghui, WANG Liduan, ZHOU Wei

Electronic Science and Technology. 2024, 37(7):  60-65.  doi:10.16180/j.cnki.issn1007-7820.2024.07.008

Abstract ( 20 )   HTML ( 1 )   PDF (1767KB) ( 32 )  

Figures and Tables | References | Related Articles | Metrics

In view of the problems of low precision and time-consuming point cloud coarse registration in the process of 3D reconstruction of shield surface topography, this study proposes a double-layer sampling point cloud coarse registration algorithm based on the traditional RANSAC(Random Sample Consensus) point cloud coarse registration algorithm framework. In each iteration of the first layer of the proposed algorithm, the single-point sampling is used for rigid constraints to reduce the size of the corresponding set, which is regarded as the "interior point candidate set" of the second layer. The second layer of the algorithm performs continuous random sampling of two points and computes their respective minimum models. The optimal rigid body transformation matrix is obtained by iteratively maximizing the consistent set and using the least square method. In the experimental stage, 6 groups of shield point clouds with different degrees of down sampling are used, and the RANSAC algorithm and the proposed algorithm are used to conduct a point cloud coarse registration comparison experiment. Experimental results show that the proposed algorithm is superior to the RANSAC algorithm in both rough registration speed and rough registration accuracy. The registration speed is about twice that of the RANSAC algorithm, and the root-mean-square error of the proposed algorithm is 10^-3 mm, which is nearly 400 times higher than the RANSAC algorithm.

Date Communication over Mobile Voice Channel Based on Pitch Delay Steganography

LI Jing, PENG Tao

Electronic Science and Technology. 2024, 37(7):  66-71.  doi:10.16180/j.cnki.issn1007-7820.2024.07.009

Abstract ( 29 )   HTML ( 1 )   PDF (792KB) ( 43 )  

Figures and Tables | References | Related Articles | Metrics

In view of the security problem of end-to-end data transmission in mobile communication, this study proposes a message transmission method based on pitch delay steganography used for mobile voice channel, which hides the intended data in the voice signal. The algorithm uses secret information to control the parity characteristics of pitch delay value in the voiced part of speech, so as to embed data bits. The pitch delay value of the voiceless part is quantified and output by secret information to realize the embedding of steganographic information. The pitch delay change caused by embedding does not cause serious degradation of the original speech quality, so it is difficult for the outside world to detect hidden data information when transmitting speech signals. This algorithm can ensure the security and privacy of end-to-end information transmission. The simulation results show that the transmission rate of secret information can reach 200 bit·s^-1 and the accuracy rate is about 94%.

Quality Guidance Based Branch-Cut Phase Unwrapping Algorithm

TAI Manli, LI Wenguo, LIU Tao, ZHONG Yongpeng

Electronic Science and Technology. 2024, 37(7):  72-80.  doi:10.16180/j.cnki.issn1007-7820.2024.07.010

Abstract ( 64 )   HTML ( 3 )   PDF (4316KB) ( 42 )  

Figures and Tables | References | Related Articles | Metrics

Phase unwrapping is a key data processing step in phase measurement profilometry. In this study, a quality-guided branch-cut phase unwrapping algorithm is proposed based on the traditional Goldstein branch-cut method, aiming to obtain more accurate phase unwrapping results. The proposed algorithm uses the second-order differential of the wrapped phase as a supplement parameter for residual detection principle, and regards the mutation points in the second-order differential of the wrapped phase as non-polar residual points, and uses modulation as the criterion for residual point effectiveness judgment, regarding the residual points with low modulation as having higher effectiveness for local optimization to reduce the density of residual points. The optimized equivalent residual points are connected into branch-cut to block error propagation. The proposed algorithm calculates the quality of pixels using modulation to guide the order of phase unwrapping, with the unwrapping path circumventing the branch-cut and prioritizing high-quality pixels. Experimental results show that the proposed algorithm has higher accuracy and competitiveness in phase unwrapping results.

A Two-Stage Adaptive Non-Local Mean Filtering Method Based on Sine-Cosine Decomposition

SUN Yujuan, WANG Yawei, TANG Furui, GENG Yan, LI Yuchen, XU Yuanyuan

Electronic Science and Technology. 2024, 37(7):  81-88.  doi:10.16180/j.cnki.issn1007-7820.2024.07.011

Abstract ( 36 )   HTML ( 2 )   PDF (2967KB) ( 33 )  

Figures and Tables | References | Related Articles | Metrics

In order to solve the problem of speckle noise in the wrapped phase diagram, a two-stage adaptive non-local mean filtering method based on sine and cosine decomposition is proposed. The proposed method realizes the adaption of the algorithm by improving the size and similarity measurement of the attenuation parameters twice. This method is used to denoise the sine and cosine components of the wrapped phase diagram. After denoising, the inverse tangent operation is used to obtain the clean wrapped phase, and unwrapping operation is carried out on the phase. The experimental and simulation results show that the proposed method not only effectively removes the noise in the wrapped phase diagram, but also preserves the edge information in the phase diagram. Compared with SCA(Sine Cosine Algorithm) method and BM3D(Block-Matching and 3D filtering) method, ENL(Equivalent Number of Looks) and SSI(Speckle Suppression Index) of the image denoised by the proposed method are the largest and the smallest, and the mean square error is increased by about two times. These results reveal that the proposed method can effectively remove the noise in the wrapped phase and improve the accuracy of phase unwrapping.

Dynamic Weight Load Balancing Algorithm Based on Microservice for Smart Street Lamp Cloud Platform

YANG Zemin, XIA Changquan, LI Jiaying, ZHU Jinrong, HAN Yifan

Electronic Science and Technology. 2024, 37(7):  89-94.  doi:10.16180/j.cnki.issn1007-7820.2024.07.012

Abstract ( 47 )   HTML ( 5 )   PDF (794KB) ( 43 )  

Figures and Tables | References | Related Articles | Metrics

A large-scale street lights send data to the cloud platform, causing load imbalance among nodes of the server in high concurrency, resulting in communication failure. In view of this problem, based on microservices, this study proposes a dynamic weight load balancing algorithm based on the smart street lamp cloud platform. The algorithm calculates the respective weight coefficients and the initial weights of each node according to the hardware performance of each server during initialization, and dynamically adjusts the server weights according to the idle rate of CPU(Central Processing Unit) and network bandwidth during the request process to realize load optimization. By setting the minimum threshold and comparing it with the calculated remaining load rate, the weight of the server that reaches the upper limit of the load is set to 0 to prevent the server from being overloaded. The test results show that the proposed algorithm has a better load balancing effect than the minimum number of connections algorithm and the smooth weighted round robin algorithm in the experimental environment. Compared with the dynamic weight algorithm, the average response time and the actual number of concurrent connections of the proposed method are also improved.