Top Read Articles

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Reference Manager ProCite BibTeX RefWorks Toggle Thumbnails

Select

Design of Multifunctional Array Signal Processing System Based on FPGA LUO Xin,FENG Wu,SUN Weijie,LIU Maliang Electronic Science and Technology    2023, 36 (3): 1-6.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.001 Abstract （704）   HTML （457）    PDF（pc） （2270KB）（130）       Knowledge map    Save In order to adapt to the characteristics of high real-time performance and large computation of the array signal processing system, this study proposes a multifunctional array signal processing system based on FPGA. By using advanced large-scale high-performance FPGA and multichannel high-precision ADC chips, the synchronous acquisition and digital down conversion processing of 40 intermediate frequency signals can be accomplished, and 36 sets of beam data can be obtained by digital beamforming. By configuring various types of external interfaces, the network data interaction, serial port control, beam control and MGT high-speed data transmission can be achieved. In this study, the hardware and software architecture of the system is presented, and the chip models, peripheral interface and the realization method of each software function module are introduced in detail. The measurement results indicate that the system meets the design requirements, has a strong array signal processing capabilities and good versatility and scalability. Table and Figures | Reference | Related Articles | Metrics

Select

Optimal Design of Permanent Magnet Synchronous Machine Based on Analytic Model ZHU Tuo,LI Zheng,ZHANG Kai,LI Zi Electronic Science and Technology    2023, 36 (3): 69-75.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.011 Abstract （405）   HTML （43）    PDF（pc） （1917KB）（31）       Knowledge map    Save Electromagnetic torque and eddy current loss are two important indexes of permanent magnet synchronous motor. Under the limited conditions of volume, effectively improving electromagnetic torque and reducing rotor eddy current loss are the key for motor design. In view of this problem, the analytical method is used to calculate the electromagnetic torque and eddy current loss respectively, and the PSO algorithm is used to optimize the size parameters of the motor. The analytical model includes armature reactive magnetic field and no-load magnetic field model. When calculating eddy current loss, eddy current reaction and circumferential segmentation of permanent magnet are considered. The objective function of the optimization algorithm uses weight values to convert multi-objective into single objective. The comparison between the analytical solution and the time-stepping finite element numerical solution shows that the error of the analytical solution is about 2%. The response surface of parameter influence analysis reveals that the correlation between electromagnetic torque and eddy current loss is consistent when the stator winding pitch is 25°. The optimization iteration results show that the optimized design reduces the average eddy current loss by 76%, the average electromagnetic torque by 22%, and the electromagnetic torque ripple by 68%. Table and Figures | Reference | Related Articles | Metrics

Select

Text Keyword Extraction Method Based on BERT and LightGBM HE Chuanpeng,YIN Ling,HUANG Bo,WANG Mingsheng,GUO Ruyan,ZHANG Shuai,JU Jiaji Electronic Science and Technology    2023, 36 (3): 7-13.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.002 Abstract （355）   HTML （9）    PDF（pc） （1624KB）（32）       Knowledge map    Save Traditional text keyword extraction methods ignore the contextual semantic information and cannot solve the problem of ambiguity of a word, so the extraction effect is not ideal. Based on the LDA and BERT models, this study proposes the LDA-BERT-LightGBM (LB-LightGBM) model. The LDA topic model is selected to obtain the topic of each review and its word distribution, candidate keywords are filtered out according to the threshold, and the filtered words and the original review text are spliced and input into the BERT model. The word vector training is performed to obtain the word vector containing the text topic, so the text keyword extraction problem is converted into a two-classification problem through the LightGBM algorithm. The textrank algorithm, LDA algorithm, LightGBM algorithm and the proposed LB-LightGBM model are compared through experiments on the accuracy rate P, recall rate R and F1 of text keyword extraction in the present study. The results show that when TopN takes 3~6, the average value of F1 is 3.5% higher than that of the optimal method, indicating that the extraction effect of this method is generally better than that of the comparison method selected in the experiment, and the text keywords can be found more accurately. Table and Figures | Reference | Related Articles | Metrics

Select

Path Planning and Smoothing for Unmanned Surface Vehicle Based on Improved Ant Colony Optimization SUN Pengna,ZHANG Zhongmin Electronic Science and Technology    2023, 36 (3): 14-20.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.003 Abstract （304）   HTML （9）    PDF（pc） （910KB）（32）       Knowledge map    Save In view of the problems of USV path planning in complex environment, such as large steering angle, many turning points, and high energy consumption, a path planning and smoothing method based on improved ant colony optimization is proposed. The method adopts the grid method for environmental modeling, and improves the path optimization and static obstacle avoidance ability by introducing the path smoothness and distance heuristic factor into the heuristic function and introducing the obstacle heuristic factor into the path transition probability. Combined with heuristic factors, the pheromone update standard is improved, and the adaptability of the algorithm to increase the volatile factor of pheromone can be adjusted. And then the key nodes of the optimal path are extracted and smoothed to further guarantee path smoothness and security. According to the simulation results of obstacle avoidance under different grid map, compared with the traditional ACO, the path optimization speed of improved ACO is increased by 45%~62%, and the steering times of path is reduced by 25%~44 %. Moreover, the path security and feasibility after smoothing are improved. The above results show that the autonomous path planning of USV in different environments is realized. Table and Figures | Reference | Related Articles | Metrics

Select

An Accurate Design Approach for the Folded Cascode Operational Amplifier WANG Jiaqi,LÜ Gaochong,GUO Yushun Electronic Science and Technology    2023, 36 (3): 50-54.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.008 Abstract （297）   HTML （4）    PDF（pc） （663KB）（20）       Knowledge map    Save The results obtained from the traditional design procedure of the folded cascode amplifier are inaccurate. The optimization method can produce fairly accurate design results, but consumes large amount of computations. This study presents an accurate design method for this kind of amplifier. Through SPICE simulation, the errors caused by the analysis and approximation of various performance indicators in the traditional design process are compensated. At the same time, The device size calculation based on the BSIM model is adopted, and this design process is repeatedly executed, which gradually eliminates the errors existing in the traditional design process and obtains accurate design results. Compared with the traditional manual method, the proposed method is more accurate and avoids repeated debugging during design. When compared with the optimization method, although the proposed design still needs to go through an iterative process, the calculation amount is smaller due to the faster convergence. The circuit design under the actual process library of 0.18 μm and 90 nm is taken as an example, and the simulation experiments proves the correctness and effectiveness of the proposed method. Table and Figures | Reference | Related Articles | Metrics

Select

Small Signal Modeling of Flexible Interconnected Microgrid LU Hongwen,YUAN Xufeng,CHEN Ruijie,LI Yulong Electronic Science and Technology    2023, 36 (3): 21-28.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.004 Abstract （283）   HTML （11）    PDF（pc） （3840KB）（30）       Knowledge map    Save In view of the problem that the traditional PCC hard switch cannot actively adjust the power flow, the back-to-back converters are used to replace the traditional PCC hard switch to flexibly interconnect the distribution network and microgrid, so as to facilitate the coordinated control between them. In order to analyze the stability of the system and consider the different number of distributed generators in microgrid of different scales, a microgrid small signal state space model framework with N distributed generators connected through back-to-back converter is established. The eigenvalue analysis is carried out using MATLAB, and the key parameters affecting the stability and dynamic performance of microgrid are determined. Finally, a microgrid flexible grid connection operation model based on droop control is built on PSCAD / EMTDC platform. The established small signal model is combined with the built simulation model, and the simulation is carried out under multiple working conditions to verify the correctness of the modeling, analysis and conclusion. Table and Figures | Reference | Related Articles | Metrics

Select

Fault-Tolerant Clock Synchronization Algorithm Based on Grey Prediction LU Yu,ZHANG Li,ZHANG Fengdeng Electronic Science and Technology    2023, 36 (3): 29-35.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.005 Abstract （282）   HTML （7）    PDF（pc） （842KB）（36）       Knowledge map    Save In view of the problem of clock Byzantine failure and node communication link loss failure in the non-master clock synchronization in the distributed real-time system, a fault-tolerant clock synchronization algorithm based on gray prediction is proposed in this study. The proposed algorithm is based on the LL model of the broadcast communication network, and uses the gray prediction method of GM (1,1) to analyze the correction deviation value of the previous round, so as to predict the correction deviation value of the node in the failure order, and then obtain the correction value through calculation. The experimental results show that the gray prediction algorithm proposed in this study can tolerate Byzantine faults, and at the same time, it can overcome the problems caused by the failure of node communication link loss, and improve the universality of the FTA algorithm. The data comparison analysis results show that the clock synchronization precision of this algorithm is improved by 24.3% when compared with Original algorithm. At the same time, the algorithm complexity has certain advantages when compared with other algorithms. Table and Figures | Reference | Related Articles | Metrics

Select

Short-Term Photovoltaic Power Prediction Based on VMD and Improved TCN HUANG Yuan,WEI Yunbing,TONG Dongbing,WANG Weigao Electronic Science and Technology    2023, 36 (3): 42-49.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.007 Abstract （280）   HTML （4）    PDF（pc） （1971KB）（16）       Knowledge map    Save Photovoltaic power generation fluctuates, photovoltaic output is easily affected by various meteorological characteristics, and traditional TCN networks tend to over-enhance spatial characteristics and weaken individual characteristics. In view of these problem, a short-term photovoltaic power generation prediction model based on VMD and improved TCN is proposed in this study. The original photovoltaic power generation time series is decomposed into several modal components of different frequencies through VMD, and each modal component and the corresponding meteorological data are input to the improved TCN network for modeling and learning. The center frequency method is used to determine the optimal decomposition modal number of VMD. On the basis of the traditional TCN prediction model, DropBlock regularization is used to replace Dropout regularization to achieve the effect of suppressing information synergy in the convolutional layer, and the attention mechanism is introduced to autonomously mine and highlight the impact of key meteorological input characteristics and quantify the impact of various meteorological factors on photovoltaic power generation to improve forecasting precision. Based on the real data of a photovoltaic power station in Jiangsu, the simulation experiments show that the RMSE of the proposed prediction method is 0.62 MW and the MAPE is 2.03%. Table and Figures | Reference | Related Articles | Metrics

Select

Garbage Detection and Classification Based on YOLO Neural Network ZHANG Wei,LIU Na,JIANG Yang,LI Qingdu Electronic Science and Technology    2022, 35 (10): 45-50.   DOI: 10.16180/j.cnki.issn1007-7820.2022.10.008 Abstract （279）   HTML （15）    PDF（pc） （1231KB）（54）       Knowledge map    Save In view of the problems of low efficiency of manual garbage sorting, heavy tasks and harsh environment, this study proposes a YOLO-based target detection method to realize garbage detection and classification. The model is adjusted through making a specific dataset, using K-means clustering algorithm and Mish activation function. According to the characteristics of the convolutional neural network, the CBAM attention module is embedded in front of each detection head of the YOLO model, combined with PANet to enhance the feature integration ability to improve the accuracy of small target detection. The experimental results show that the garbage detection and classification method proposed in this study can accurately and quickly identify garbage. Compared with YOLOv4, the map value of the proposed model on the garbage data set has increased by 2.81%. The recognition accuracy of Cans can reach 94.56%, and the accuracy of PlasticBottle has increased by 6.36%. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Control Strategy of Single-Phase Grid-Connected Inverter Based on dSPACE XIA Zihao,LI Yudong Electronic Science and Technology    2023, 36 (3): 62-68.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.010 Abstract （277）   HTML （12）    PDF（pc） （1907KB）（17）       Knowledge map    Save In view of the problem of high harmonic content of grid-connected current caused by voltage distortion, a control strategy combining quasi-proportional resonance control and voltage feed-forward is proposed in this study. Considering the infinite gain of the quasi-proportional resonance controller at the resonant frequency, the steady-state error of grid-connected current is reduced, and the voltage feed-forward is introduced to eliminate the influence of voltage on the system, so as to improve the quality of grid-connected current. The structure of single-phase grid-connected inverter is analyzed, the harmonic component of grid-connected current caused by voltage distortion is suppressed by closed-loop control, and the parameters of quasi-proportional resonance controller are set by control variable method, so as to analyze the influence of parameters of quasi-proportional resonance controller on system performance. Finally, the MATLAB/Simulink simulation model and the dSPACE-DS1104 hardware-in-the-loop simulation platform are established to verify the effectiveness of the proposed strategy under different strategies. Table and Figures | Reference | Related Articles | Metrics

Select

Task Partitioning Optimization Algorithm Based on MrsP Protocol ZHANG Haitao,ZHANG Tong,ZHANG Yuhui,GUAN Yinfeng,ZHANG Fengdeng Electronic Science and Technology    2023, 36 (3): 36-41.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.006 Abstract （272）   HTML （4）    PDF（pc） （785KB）（12）       Knowledge map    Save Scheduling and resource sharing are the core problems in multiprocessor real-time systems, the corresponding scheduling algorithm and shared resource access protocol will directly affect the performance of the system, which requires the scheduling algorithm and resource access protocol to maximize the computing power of the hardware platform on the basis of ensuring real-time performance. However, most existing scheduling algorithms assume that tasks are independent of each other and do not consider resource sharing among tasks. Besides, shared resource access protocols also focus on rules and worst-case response time analysis. In this regard, the whole schedule ability condition of multiprocessor real-time system is obtained by combining P-RM algorithm and MrsP protocol. According to the characteristics of the MrsP protocol, this study proposes a task division algorithm to reduce the blocking time. By improving the calculation method of the task utilization, the proposed method solves the problem of repeated calculation in the critical area. Compared with the previous task partitioning algorithm, the proposed algorithm also solves the key area of double-counting and splits the redistribution after task classification problem. Experiments resalts show that the number of processors required by the algorithm is reduced by 15% to 20%. Table and Figures | Reference | Related Articles | Metrics

Select

Research Progress of Node Assignment Optimization Strategy in Road Traffic Network LU Dongxiang Electronic Science and Technology    2023, 36 (3): 81-86.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.013 Abstract （271）   HTML （14）    PDF（pc） （734KB）（24）       Knowledge map    Save In order to further improve the traffic efficiency of urban road traffic network, a variety of intelligent optimization algorithms such as particle swarm optimization algorithm and neural network algorithm have attracted extensive attention. Recently, the popularization and application of deep learning technology has greatly improved the efficiency of node identification of urban traffic network, and the node scheduling of traffic network has expanded the application of deep learning technology. In this study, the key problems of traffic node scheduling are analyzed in detail, and the research status of relevant network node allocation is summarized. On this basis, the proposed study thoroughly discusses and analyzes the application prospect of node scheduling and deep learning in urban transportation network, and prospects the future research direction of node allocation optimization strategy in transportation network. Reference | Related Articles | Metrics

Select

An Acoustic Treatment Method for On-Line Fault Monitoring of Electromechanical Systems in Complex Noise Environment BAI Xingyu,GOU Yutao,JIANG Yu,LIU Mingyu Electronic Science and Technology    2023, 36 (3): 55-61.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.009 Abstract （269）   HTML （6）    PDF（pc） （2517KB）（14）       Knowledge map    Save In view of the problem of electromechanical system fault detection under complex background noise environment, this study proposes a noise suppression and fault monitoring method based on broadband acoustic processing. This method starts from acoustic signal pick-up and processing, and establishes the voiceprint database of the normal operating state of the system by collecting, tracking the data and suppressing the complex background noise of the acoustic signal under the normal operating state of the electromechanical equipment. In addition, the proposed method further realizes the detection and classification of fault signals through the voiceprint signal matching and pattern recognition technology based on broadband acoustic processing, and then realizes the online monitoring of the operating state of the electromechanical system and the autonomous early warning of invisible faults. This processing method organically combines the autocorrelation noise suppression technology based on data tracking and the fault signal detection and classification technology based on broadband acoustic processing, which can monitor the early hidden faults of the electromechanical system and effectively solve the fault detection problem of the electromechanical system in the complex noise environment. The simulation experiment finally proves the effectiveness and good practicability of the proposed method. Table and Figures | Reference | Related Articles | Metrics

Select

Research Progress of Smart Grid Data Security Based on Internet of Things Technology YING Jieyao Electronic Science and Technology    2023, 36 (3): 76-80.   DOI: 10.16180/j.cnki.issn1007-7820.2023.03.012 Abstract （265）   HTML （33）    PDF（pc） （639KB）（24）       Knowledge map    Save In order to protect the core data in smart grid equipment and users' personal privacy, a number of Internet of things security technologies such as distributed computing and homomorphic encryption have gradually attracted attention. In recent years, the development of internet of things technology has promoted the rapid popularization of intelligent power grid, and the application of smart grid has promoted the renewal of internet of things technology. Through introducing various attack methods faced by smart grid, this study reviews and combs the research background and current situation of smart grid data security. On this basis, the definitions of false data injection attack and personal privacy protection are discussed and analyzed, and the future research direction and ideas of smart grid data security technology are prospected. Reference | Related Articles | Metrics

Select

Design of WeChat Mini Program for Lost and Found Based on Image Recognition ZHANG Yangfan,HAO Yuxin,LI Yinfeng,TIAN Xinyu,ZHENG Chunhong,LI Zehao Electronic Science and Technology    2022, 35 (10): 33-38.   DOI: 10.16180/j.cnki.issn1007-7820.2022.10.006 Abstract （232）   HTML （13）    PDF（pc） （2111KB）（30）       Knowledge map    Save In view of the scattered distribution of lost and found information on campus, the difficulty of the owner’s inquiry, and the low success rate of item retrieval, this study uses image character recognition technology to develop a set of WeChat-based lost and found applets. This program can recognize the card number, name, and other text information in the lost property picture of the certificate, and fill in the form automatically. When the uploaded lost property information matches the school database personnel information, the system will notify the owner to claim the item via SMS and WeChat. The system has been put into operation on campus, which has improved the release efficiency of lost and found information and increased the success rate of lost property recovery. Table and Figures | Reference | Related Articles | Metrics

Select

A Survey of Intelligent Transportation Path Planning Algorithms LU Dongxiang Electronic Science and Technology    2022, 35 (7): 22-27.   DOI: 10.16180/j.cnki.issn1007-7820.2022.07.004 Abstract （224）   HTML （10）    PDF（pc） （640KB）（44）       Knowledge map    Save In order to solve problems such as traffic congestion, traffic safety and environmental pollution of urban roads, a variety of technologies including path planning algorithm and vehicle self-organizing network have gradually become important research directions in the field of intelligent transportation and attracted a lot of attention. In recent years, the application and popularization of intelligent transportation provide rich and diverse research topics for the research of path planning algorithm, and the research of path planning algorithm also effectively promotes the development of cutting-edge technology of intelligent transportation. By reviewing the research of multiple path planning algorithms, this study summarizes the existing problems in the research of path planning algorithms. On this basis, this study deeply studies and analyzes the advantages and disadvantages of static and dynamic path planning algorithms, and puts forward the future research trend and methods of path planning algorithms in intelligent transportation. Reference | Related Articles | Metrics

Select

Numerical Simulation and Thermal Cycle Analysis of MAG Welding Temperature Field Based on ABAQUS MING Can,MA Chunwei Electronic Science and Technology    2022, 35 (9): 74-78.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.011 Abstract （193）   HTML （4）    PDF（pc） （2551KB）（20）       Knowledge map    Save In order to control the production cost of MAG welding and provide accurate technical support for MAG welding process, finite element software is used to simulate the welding process. Based on ABAQUS finite element analysis software, the temperature field of 8 mm-thick Q235 MAG is numerically simulated, the loading process of welding heat source is simulated, and the temperature field of each stage and the welding thermal cycle law of vertical and parallel points near the weld are analyzed. The results show that the temperature field is steady, the welding thermal cycle is stable, the peak temperature time away from the weld is slightly delayed, and the temperature gradient decreases. The numerical simulation results are in good agreement with the actual changes of the welding temperature field. Table and Figures | Reference | Related Articles | Metrics

Select

Glasses Virtual Try-on System Based on 3D Frame Modeling ZHANG Xindong,FU Dongxiang Electronic Science and Technology    2022, 35 (9): 52-57.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.008 Abstract （182）   HTML （5）    PDF（pc） （1493KB）（26）       Knowledge map    Save In the virtual try-on system, virtual glasses need to be superimposed on the face image accurately, which determines the experience of the virtual try-on system. The key technology is to construct a real glasses model and quickly and accurately estimate the 3D face pose of the image. In response to this technical requirement, a virtual try-on technology combining 3D mirror frame modeling and head space pose estimation based on facial feature detection is proposed and a virtual try-on system is implemented. First, the method uses ERT cascade regression to locate the facial feature points of the face images. Then, the VTK visualization tool is adopted to construct a 3D mirror frame, and the processed mirror frame image is accurately fused to the face image according to the information of the face feature points and the rotation information of the head. Finally, the accuracy of the pose estimation method is tested using the AFLW data set. The results show that the algorithm has high precision and fast speed. It can still quickly and accurately realize three-dimensional and multi-angle virtual try-on under complicated conditions of large angles, many background interferences and poor light conditions, which basically meets the requirements of virtual try-on technology. Table and Figures | Reference | Related Articles | Metrics

Select

Design of A Multi-Channel Radar Echo Playback System Based on FPGA ZHAO Yingxiao,SU Yang Electronic Science and Technology    2023, 36 (2): 1-7.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.001 Abstract （179）   HTML （1079）    PDF（pc） （1913KB）（101）       Knowledge map    Save In order to solve the problem of effective verification of radar real-time signal processing function and performance, a wideband and narrowband integrated radar echo playback system with multiple channels is designed and implemented. The system transfers the radar echo data to the real-time signal processing system according to the time sequence and data rate of the radar operation, so as to reproduce the target tracking scene and realize the effective verification of the real-time signal processing function and performance of the radar. The data playback system comprises a disk array server and two PCIe fiber boards. Based on the Xilinx series products, the PCIe DMA control process and response mechanism are further adjusted according to the system characteristics, and the high-speed batch transmission of radar echo data from the server to the fiber board is realized. According to the working mechanism of the radar and the echo data structure, the FPGA playback control state machine and related function modules are designed, and the radar echo data is transmitted from the optical fiber board to the real-time processing system in strict accordance with the working sequence and data rate of the radar. To ensure the synchronization between multiple boards when wideband and narrowband echo playback is carried out at the same time, the study proposes two methods based on software and hardware respectively. The test results show that the system realizes the synchronous playback of wide-band and narrow-band radar echo data between boards, each data type supports 6 parallel data channels, and the peak data playback rate can reach 1 920 MB·s-1.The designed system can be directly integrated in the origin radar hardware platform, without adding extra circuit boards or cables, which has good generality and convenience. The system has been successfully applied in a multi-function phased array radar. Table and Figures | Reference | Related Articles | Metrics

Select

YOLO-Improve Detection Method of Real-Time Mask Wearing CHENG Changwen,CHEN Wei,CHEN Jinhong,YIN Zhong Electronic Science and Technology    2023, 36 (2): 73-80.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.011 Abstract （178）   HTML （589）    PDF（pc） （2859KB）（87）       Knowledge map    Save The existing YOLO target detection model is based on the One-stage idea for multi-target detection. It is insufficient for dual-classification detection, and the performance consumption is large during detection. In order to improve the detection efficiency of dual-classification mask wearing during the period of the outbreak of COVID-19, this study proposes a real-time detection method based on YOLO for detecting the condition of bi-objective mask wearing. The feedforward input layer of the model is improved, the data enhancement part is optimized, and adaptive image scaling is added to improve the detection accuracy and detection efficiency of dual-classification and small targets. The adaptive anchoring frame is added to replace the activation function so as to reduce the computational complexity of the method and improves the detection efficiency of the method. The optimization of Neck and the addition of Focus structure improve the capability of feature fusion and reduce the amount of parameters to raise the efficiency. The experimental results showed that compared with the YOLOv4, the proposed method has a 0.33% increase in F1 and a 0.71% increase in mAp in the data set in the text, and the detection efficiency is also significantly improved under the same experimental environment. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Synchronous Rectification Technology of Multi-Output Flyback Switching Power Supply CHEN Zhuo,WANG Jingmei,LIU Yu Electronic Science and Technology    2022, 35 (10): 15-20.   DOI: 10.16180/j.cnki.issn1007-7820.2022.10.003 Abstract （166）   HTML （6）    PDF（pc） （1989KB）（19）       Knowledge map    Save In the flyback switching power supply, the traditional diode rectification method has large rectification loss, low efficiency, and poor cross-regulation characteristics of multiple outputs. To solve this problem, synchronous rectification technology is used to investigate the multi-output flyback switching power supply. The synchronous rectification technology of flyback converter and its driving method are analyzed, and chip UCC24610 based on the drain-source voltage is selected to design a three-output flyback switching power supply prototype. In order to adjust each output of the prototype, the method of weighted voltage feedback control is introduced in this study. The comparison between the proposed prototype and the diode rectifier prototype show that the full load efficiency of the former is 7.6% higher than that of the latter. Experimental results indicate that the synchronous rectification technology effectively improves the output voltage accuracy of the prototype and improves the multi-output cross-regulation characteristics. Table and Figures | Reference | Related Articles | Metrics

Select

Improved Montgomery Modular Multiplication Algorithm and FPGA Implementation CHENG Biqian,LIU Guangzhu,XIAO Hao Electronic Science and Technology    2022, 35 (7): 58-63.   DOI: 10.16180/j.cnki.issn1007-7820.2022.07.010 Abstract （142）   HTML （2）    PDF（pc） （1639KB）（36）       Knowledge map    Save In order to ensure the online information security of users, the public key cryptosystem is used to encrypt the data information. As the core operation of public key cryptosystem, the computation efficiency of large integer modular multiplication is very important to the performance of public key cryptosystem. In this study, a polynomial expanded cross Montgomery modular multiplication algorithm is proposed, which is based on the classical Montgomery modular multiplication algorithm. By decomposing large bit-width logic operations, and performing modular multiplication and modular reduction operations with polynomial expansion, this algorithm can effectively improve the calculation efficiency of large integer modular multiplication operations, and reduce the resource consumption of hardware implementation. FPGA experiment verification shows that compared with other methods, the proposed algorithm can reduce AT1 and AT2 (the products of area and time) by 96.5% and 69% respectively, indicating that the proposed method achieves the balance between computing time and hardware overhead, has high flexibility and universality, and is suitable for cost-sensitive applications with a large number of encryption requirements. Table and Figures | Reference | Related Articles | Metrics

Select

A GAN-Based Lightweight Style Transfer Model for Ink Painting ZHAO Jin,LI Feifei Electronic Science and Technology    2023, 36 (2): 81-86.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.012 Abstract （142）   HTML （438）    PDF（pc） （2030KB）（38）       Knowledge map    Save Current style transfer methods are mainly suitable for photos or Western paintings. Due to the inherent differences between Chinese and Western paintings, existing algorithms cannot generate satisfactory results when applied to the style transfer task of Chinese ink paintings. Consequently, a novel style transfer method based on GAN for ink painting is proposed in the study. This method combines AdaIN, style-attention module and perceptual loss to learn the style features of ink painting more accurately, thereby solving the problem that the generated results of ink painting have poor quality. According to the qualitative analysis and quantitative evaluation, experimental results show that this method has better performance and the generated results have higher visual quality. Compared with the baseline, the method reduces the number of parameters by about 55% and the training time by about 60%. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Battery Grid Connection Based on Voltage and Current Double Loop Control SUN Sinan,HAO Zhenghang Electronic Science and Technology    2023, 36 (2): 13-21.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.003 Abstract （133）   HTML （444）    PDF（pc） （1087KB）（40）       Knowledge map    Save In view of problems such as low accuracy, poor reliability, and difficulty in operation caused by the performance test of conventional battery discharge using variable resistors, a battery performance test method for grid-connected charging and discharging is proposed in the present study. Through the analysis of the differential expressions of charge, temperature and current in lead-acid batteries, a third-order equivalent mathematical model composed of the main reaction branch and parasitic branch is established. The charging and discharging of the battery adopts the constant current mode in which the step signal triggers the on-off of the Buck-Boost bidirectional conversion circuit switch. The inverter circuit adopts double closed-loop control of voltage and current, and is merged into the analog power grid after being filtered by inductance. Simulation experiments on MATLAB/Simulink software show that the various performance indicators of the battery and the grid-connected current dynamic response are good, which proves the effectiveness and environmental protection of the proposed method. Table and Figures | Reference | Related Articles | Metrics

Select

Distribution Network Dispatching Optimization Strategy Energy Storage Based on Time-of-Use Electricity Price and User-Side WANG Yumei,WANG Lulu Electronic Science and Technology    2023, 36 (2): 7-12.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.002 Abstract （129）   HTML （517）    PDF（pc） （906KB）（52）       Knowledge map    Save In view of the problem of loss increase of distribution network caused by the access of distributed power and the fluctuation of load, this study proposes an optimal operation model that integrates the time-of-use electricity price mechanism with user-side energy storage to participate in the distribution network. Based on the time-of-use electricity price, a user load response model is established, and a distribution network operation optimization model is constructed with the user's daily electricity cost and the minimum distribution network loss as the objective function. The evaluation function method is used to convert multiple objectives into single objectives, and the simulated annealing Metropolis criterion is introduced into the traditional genetic algorithm to optimize the charging and discharging strategy of the user-side energy storage. The simulation results prove that the proposed strategy can effectively reduce the power loss of the distribution network and the cost of user electricity, which verifies that proposed algorithm has a faster optimization speed and better convergence performance. Table and Figures | Reference | Related Articles | Metrics

Select

An Improved Obstacle Detection Method for AGV YANG Yingying,LIU Xiang,SHI Yunyu Electronic Science and Technology    2022, 35 (9): 1-6.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.001 Abstract （122）   HTML （8）    PDF（pc） （1193KB）（29）       Knowledge map    Save To solve the problem that AGV obstacle detection algorithm performs poorly under the interference of uneven illumination and background texture in smart factories, this study proposes an improved Canny operator for obstacle detection. The method achieves the optimization of AGV obstacle detection in terms of color space, filtering method, gradient direction and adaptive threshold. Through Lab color space conversion, the b component is extracted and then filtered. The improved median filter and bilateral filter are merged to replace the Gaussian filter in the traditional Canny operator, which reduces the loss of edge details while achieving noise reduction, and improves the speed of the algorithm. The edge information is enhanced by increasing the gradient direction, and adaptive thresholding is obtained using Otsu algorithm. Experiments show that the proposed method can improve the accuracy of edge detection and reduce noise interference, thus achieving stable detection of obstacles. Table and Figures | Reference | Related Articles | Metrics

Select

Trackside Signal Light Recognition Based on Image Processing FENG Junyi,SHEN Tuo,ZHANG Xuanxiong Electronic Science and Technology    2022, 35 (8): 53-57.   DOI: 10.16180/j.cnki.issn1007-7820.2022.08.009 Abstract （122）   HTML （18）    PDF（pc） （2388KB）（34）       Knowledge map    Save The trackside signal light is one of the important components for prompt train operation. In order to ensure train operation safety, a method based on image processing technique is proposed to effectively locate the trackside signal light and identify its color information. The trackside signal light ROI is extracted through the empirical value, and then the color segmentation is carried out to the ROI in the RGB color space to avoid the influence of irrelevant background, and remaining noise is removed through morphology processing. Hough-circle transform is performed on the processed image for the extracted candidate region of signal light, and the operating trackside signal light related to the running train is located according to the position characteristics between the signal light and the track. The pixel value information in the signal light area is analyzed for signal color recognition. The experimental results indicate that the method can precisely locate and recognize trackside signals, and the color correction ratio is 91.42% for red, 85.00% for yellow, and 94.29% for green, respectively. Table and Figures | Reference | Related Articles | Metrics

Select

Wideband Nonlinear Behavior Modeling of Receiver with Neural Network LIU Guohua,LU Hongmin,CHEN Chongchong,LI Wanyu,WAN Jianpeng Electronic Science and Technology    2022, 35 (8): 1-6.   DOI: 10.16180/j.cnki.issn1007-7820.2022.08.001 Abstract （121）   HTML （63）    PDF（pc） （2848KB）（108）       Knowledge map    Save In order to predict the nonlinear effect of receiver in complex electromagnetic environment, a nonlinear behavior model of receiver with memory effect is constructed based on real-value time-delay radial basis function neural network. The K-means clustering algorithm and the orthogonal least square method are respectively used to select and learn the center of the hidden layer and weight of the model, and the model is trained with the input and output measured data of the receiver. The model is verified by the in-phase and quadrature components of wideband signals. The simulation results are in good agreement with the measured data, and the normalized mean square errors of the model reaches -41.88 dB. The verification results show that the neural network model has fast convergence speed, good modeling accuracy and generalization ability. Table and Figures | Reference | Related Articles | Metrics

Select

Photovoltaic Grid-Connected System Based on Adaptive VSG Control SUN Sinan,HAO Zhenghang Electronic Science and Technology    2022, 35 (9): 22-29.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.004 Abstract （120）   HTML （1）    PDF（pc） （998KB）（16）       Knowledge map    Save In traditional VSG control, the introduction of the inertia moment and damping coefficient of the synchronous generator into the photovoltaic inverter will result in poor dynamic adjustment capabilities of the photovoltaic grid-connected system. In view of this problem, this study proposes an improved VSG control strategy. The relationship between power angle and active power and the transient process of the rotor angular frequency oscillation period are discussed through the mathematical model of the converter. The principles for selecting moment of inertia and damping coefficient are given, and the rate of change of moment of inertia and angular frequency as well as damping coefficient and angular frequency are analyzed. The relationship between the changes leads to the improvement strategy of photovoltaic grid-connected under the control of adaptive VSG. The simulation results show that the photovoltaic grid-connected system based on the adaptive VSG control strategy has a good dynamic response, which proves the effectiveness and superiority of the improved strategy. Table and Figures | Reference | Related Articles | Metrics

Select

Design and Analysis of Spaceborne 5G Miniaturized Antenna LI Kai,ZUO Wencheng,ZHAO Ziwen,TAN Kangbo Electronic Science and Technology    2022, 35 (11): 7-12.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.002 Abstract （120）   HTML （7）    PDF（pc） （3124KB）（29）       Knowledge map    Save In view of the limitation of the installation space and structure size of 5G antenna in satellite communication, this study realizes the miniaturization design of the satellite-borne 5G antenna based on the trapezoidal oscillator structure and L-shaped bending mode. By transforming the vibrator of the log-period antenna from a rectangle to a shorter-length trapezoid, two trapezoids combined with a 90° sector structure are used to further synthesize the antenna, and the vibrator structure is optimized to achieve a horizontal reduction in antenna size and a miniaturized design. The designed antenna is applied to a certain type of satellite platform, and the antenna coupling degree under different placement positions is studied. The results show that compared with the traditional structure, the transverse size of the miniaturized LPDA is reduced from 90 mm to 65 mm, and it has better port impedance matching characteristics and radiation performance, which can better meet the application requirements of compact load, lightweight and frequency band intensification in 5G satellite communication. Table and Figures | Reference | Related Articles | Metrics

Select

Quantitative Analysis and Evaluation of the Disturbance Degree of Vehicle-Mounted VHF Radio WANG Wen,LU Hongmin,ZHANG Guangshuo,CHEN Chongchong,ZHANG Shiwei Electronic Science and Technology    2022, 35 (11): 1-6.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.001 Abstract （116）   HTML （12）    PDF（pc） （827KB）（49）       Knowledge map    Save As one of the core components of the in-vehicle communication system, the vehicle-mounted radio is susceptible to interference from the complex electromagnetic environment in the vehicle, resulting in a decrease in communication quality or loss of performance. This study uses experimental data to establish a quantitative model and evaluation method that can describe the degree of interference of the vehicle-mounted radio station, and studies the degree of interference of the vehicle-mounted radio station in the complex electromagnetic environment of the vehicle. By analyzing the receiver desensitization mechanism, based on the test data of a certain model of ultrashort wave radio, a quantitative model of receiver desensitization and antenna port interference voltage is established. And using the established model, an evaluation method to characterize the communication performance of the disturbed vehicle radio is proposed using analytic hierarchy process. The experimental data verification shows that the proposed model has high accuracy, and the quantization error of more than 85% of the test frequency points is within the 6 dB limit, indicating that the proposed evaluation method is effective and feasible. Table and Figures | Reference | Related Articles | Metrics

Select

Fractional Order PIλDμ Control of DC Converter Based on Ant Lion Optimization Algorithm XIAO Haifei,ZENG Guohui,DU Tao,HUANG Bo,LIU Jin Electronic Science and Technology    2022, 35 (11): 29-35.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.005 Abstract （115）   HTML （3）    PDF（pc） （1673KB）（10）       Knowledge map    Save In order to improve the response speed and stability of the output voltage of the DC converter, a method using ALO algorithm to improve the fractional order PIλDμ controller of the dual active bridge DC converter is proposed in this study. The parameter to be optimized is regarded as the spatial position of the individual ant lion, and the error performance index ITAE of the double active bridge DC converter is used as the objective function. The ALO algorithm is used to search for the global optimal solution of the parameters of the fractional-order PIλDμ controller, and then the control optimization of the output voltage is realized. The output voltage performance of dual active bridge DC converters with traditional engineering experience setting integer-order PID, particle swarm algorithm setting fractional PIλDμ, and ALO algorithm setting fractional-order PIλDμ are simulated and experimentally compared. The results show that the proposed method can shorten the adjustment time, improve the response speed, and enhance the anti-interference ability of the system, which proves the effectiveness and feasibility of the optimization method. Table and Figures | Reference | Related Articles | Metrics

Select

Software Design for Calibration of Gas Flow Standard Facility with Master Meter Method YU Zihan,JIAN Xianzhong Electronic Science and Technology    2022, 35 (10): 27-32.   DOI: 10.16180/j.cnki.issn1007-7820.2022.10.005 Abstract （114）   HTML （6）    PDF（pc） （1542KB）（7）       Knowledge map    Save This study introduces a calibration software system applied to the gas flow standard facility with master meter method. In view of the complicated design of programming software such as MFC and C#, this study uses configuration software with simpler programming as the development environment, and designs a set of calibration software to realize the functions of data collection, process visualization display, calibration data storage, calibration report generation and calibration historical data query during the gas flow calibration process of the standard meter method. The actual environment test shows that the software can be competent to monitor the flow calibration. The error of the calibrated value is within ±0.2%, and the repeatability is below 0.02%, which is consistent with the previous calibration certificate data and meets the 0.2-level accuracy turbine flowmeter national standard. After the uncertainty evaluation, the system uncertainty is below 0.4%, which meets the requirements of the standard facility. Table and Figures | Reference | Related Articles | Metrics

Select

An Effective Segmentation Method for COVID-19 CT Image Based on Attention Mechanism and Inf-Net ZUO Bin,LI Feifei Electronic Science and Technology    2023, 36 (2): 22-28.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.004 Abstract （113）   HTML （510）    PDF（pc） （2320KB）（50）       Knowledge map    Save COVID-19 pandemic has recently ravaged the world, seriously affecting the life and health of human society. CT imaging technology is an important diagnostic method for detecting COVID-19. Automatic and accurate segmentation of the lesion is of great significance for diagnosis, treatment and prognosis. In view of the segmentation of new coronary pneumonia lesions, an improved automatic segmentation method based on the Inf-Net algorithm is proposed, which introduces the channel attention module to improve feature representation and attention gate model to better fuse edge information. The experimental results on COVID-19 CT segmentation datasets show that the Dice similarity coefficient, sensitivity and specificity of the proposed method are 75.1%, 75.4% and 95.4%, respectively, and the algorithm performance is also better than some mainstream methods. Table and Figures | Reference | Related Articles | Metrics

Select

A Research on Distance Measurement Between Trains in Rail Transit Based on Machine Vision BI Jiazhen,SHEN Tuo,ZHANG Xuanxiong Electronic Science and Technology    2022, 35 (9): 37-43.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.006 Abstract （111）   HTML （4）    PDF（pc） （1587KB）（22）       Knowledge map    Save A safe distance between two moving trains is an important condition to avoid train rear-end collision. Since the image data obtained by machine vision is rich in information and can be integrated in many aspects based on the collected images, this study proposes a distance measurement method based on monocular machine vision. This method uses the constant distance between the two tracks of the train (1 435 mm) as a benchmark to estimate the distance between trains. The images collected by the monocular camera are processed and analyzed by the convolution neural network to extract the track features. Based on the existing small hole imaging principle, the mapping relationship between the world coordinate system and the pixel coordinate system is derived, so as to optimize the calculation formula of the distance between trains. The experimental results show that the error rate of the system is less than 6%, and the measurement time of the system is within 40 ms, indicating that the method realizes the effective fusion and integration of ranging and other information obtained in the image, and can be used to judge the braking distance of the train. Table and Figures | Reference | Related Articles | Metrics

Select

An Online-Method of Multiple Change Points Detection Based on Random and Overlapping Strategy ZHU Junjun,QI Jinpeng,ZHONG Jinmei,REN Qing,CAO Yitong Electronic Science and Technology    2022, 35 (12): 1-9.   DOI: 10.16180/j.cnki.issn1007-7820.2022.12.001 Abstract （110）   HTML （7）    PDF（pc） （5527KB）（28）       Knowledge map    Save The traditional detection methods of multiple change points are mainly off-line, and cannot detect large-scale time series data online. To solve this problem, this study proposes an online detection method of multiple change points based on the buffer model and the sliding window random overlapping strategy. This method is based on TSTKS algorithm and sliding window model, receives online time series data stream in real time through buffer model, and transfers the data to the data receiver. Subsequently, the data stream is segmented using a sliding window random overlap strategy in the data sink. Finally, in the sub-data stream, TSTKS algorithm is used to perform online detection of multiple change points on the data. The experimental results of simulation data and EMG data of epilepsy patients show that the proposed method has the advantages of shorter time consumption and higher accuracy, and can be considered as an alternative for online analysis of large-scale time series data streams. Table and Figures | Reference | Related Articles | Metrics

Select

Servo Control for the Dual Three-Phase Permanent Magnet Synchronous Motor Based on FPGA YUAN Qingqing,HU Xu,LIU Zhiyong,MA Ting,JIANG Quan Electronic Science and Technology    2022, 35 (12): 49-56.   DOI: 10.16180/j.cnki.issn1007-7820.2022.12.007 Abstract （109）   HTML （6）    PDF（pc） （3742KB）（20）       Knowledge map    Save Dual three-phase permanent magnet synchronous motor has been widely used for its reliable performance, high control precision, small output torque ripple and other advantages. In view of the control requirements of high reliability, high precision and small volume of servo motor in aerospace field, this study proposes a servo control algorithm and a specific implementation scheme of dual three-phase permanent magnet synchronous motor based on monolithic FPGA. Based on the hardware platform of Xilinx Kintex7 series XC7K325TFFG900 FPGA chip, the vector control algorithm of dual three-phase three-ring permanent magnet synchronous motor based on double DQ coordinate transformation is realized by Verilog hardware description language. In the verification of the experimental platform, the core control indicators of the current loop bandwidth of 600 Hz and the servo position loop bandwidth of 12 Hz have been a chieved. Table and Figures | Reference | Related Articles | Metrics

Select

Research on Network Public Opinion Monitoring System Based on Deep Learning DENG Lei,SUN Peiyang Electronic Science and Technology    2022, 35 (12): 97-102.   DOI: 10.16180/j.cnki.issn1007-7820.2022.12.014 Abstract （109）   HTML （3）    PDF（pc） （2042KB）（32）       Knowledge map    Save With the rapid development of the domestic Internet, network public opinion monitoring has become a part of the work of relevant departments and enterprises. Establishment of a public opinion monitoring system can detect public opinion crises in advance and deal with crisis public relations in time. The current study presents a complete framework of network public opinion monitoring system, which consists of four parts: information collection layer, data resource layer, data analysis application layer and application service layer. First, the proposed system can automatically collect data from most portals, microblogs and WeChat accounts, including articles and comments according to keywords. Then, these data are cleaned, segmented and filtered, and the word is embedded using Word2Vec model to obtain the vectorized text. The vectorized text is imported into LSTM deep learning model for sentiment analysis, and the data can be divided into sensitive data, neutral data and non-sensitive data. Finally, the public opinion warning information is displayed by visualization technology. The proposed network public opinion monitoring system can help regulators to monitor and guide relevant public opinions in a timely manner, and promote the harmonious development of society. Table and Figures | Reference | Related Articles | Metrics

Select

Study on Compliance Control for Falling Prevention of Smart Walking-Aids ZHANG Yuwen,WANG Yagang,DING Damin,LIN Yanzhao Electronic Science and Technology    2023, 36 (2): 46-52.   DOI: 10.16180/j.cnki.issn1007-7820.2023.02.007 Abstract （108）   HTML （515）    PDF（pc） （1432KB）（12）       Knowledge map    Save When users tend to fall down during the process of using walking-aids, it is necessary to quickly restore the human body to a normal standing posture and buffer the inertial force of the emergency braking of walking-aids. However, the compliance control is widely used in the mechanical arms, and the anti-fall control strategy applied to the walker model is relatively insufficient. To solve this problem, a new falling prevention compliance control strategy based on adaptive sliding mode impedance control is proposed and used in the walking-aids model to improve the performance of the walker through the fusion of array film pressure sensors and ultrasonic sensors. This strategy can improve the trajectory tracking effect of the walker and realize the safety protection for the users. The simulation results of two different operating conditions and two different terrain simulation experiments show that the human body can recover to stand upright in about 4 s, which proves that the strategy can achieve the motion flexibility of the walker. Table and Figures | Reference | Related Articles | Metrics

Select

UWB/PDR Integrated Indoor Pedestrian Positioning GUO Wei,ZHANG Xuanxiong Electronic Science and Technology    2022, 35 (8): 41-46.   DOI: 10.16180/j.cnki.issn1007-7820.2022.08.007 Abstract （106）   HTML （3）    PDF（pc） （1091KB）（56）       Knowledge map    Save In view of the problems of the UWB positioning system's positioning accuracy decline and the accumulated error of the pedestrian trajectory estimation algorithm caused by the NLOS in the complex indoor scene, a UWB/PDR integrated indoor positioning algorithm is proposed in this study. The PDR algorithm is applied to estimate the step length and heading of pedestrian. Then, the UWB’s ranging information is used to calculate the absolute position. Finally, a Kalman Filter is used to fuse measurements from the UWB and PDR. Experimental results show that the proposed combined positioning system can effectively solve the problem of excessive errors caused by UWB NLOS effects, improve positioning accuracy and system robustness, and the overall positioning error is below 12 cm. Table and Figures | Reference | Related Articles | Metrics

Select

Analysis and Research of Electromagnetic Environment in Space Station Cabin Based on 5G Communication ZUO Wencheng,ZHAO Ziwen,XU Zhijiang,TAN Kangbo Electronic Science and Technology    2022, 35 (10): 1-7.   DOI: 10.16180/j.cnki.issn1007-7820.2022.10.001 Abstract （101）   HTML （5）    PDF（pc） （3850KB）（30）       Knowledge map    Save In view of the complex multipath effect of 5G communication in the space station cabin, this study proposes a method to analyze the electromagnetic environment and antenna coupling degree in the space station based on the equivalent space station model. By extracting the main characteristics of the space station, the cabin model is obtained. The typical 5G communication equipment is used as the transceiver system to detect the electromagnetic distribution in the cabin. The alternative scheme of reasonably arranging the communication equipment in the cabin is studied in different regions, and the coupling degree of the transceiver antenna in the working frequency band is studied. The results show that the communication transmitting equipment placed in the connecting area of three cabins has the best electromagnetic coverage in the space station, and the coupling degree can be obtained when the two antennas are placed vertically. Table and Figures | Reference | Related Articles | Metrics

Select

Eight-Section Brocade Sequence Action Recognition and Evaluation Based on Pose Estimation SU Bo,CHAI Ziqiang,WANG Li,CUI Shuaihua Electronic Science and Technology    2022, 35 (12): 84-90.   DOI: 10.16180/j.cnki.issn1007-7820.2022.12.012 Abstract （100）   HTML （3）    PDF（pc） （2728KB）（19）       Knowledge map    Save Action evaluation and feedback can assist fitness exercisers to improve exercise benefits effectively. In order to realize the automatic quantitative evaluation of eight-section brocade movement, a method of recognition and evaluation of human body sequence movements is proposed. The pose estimation algorithm OpenPose is used to extract the coordinates of the key points of the human body, and then normalize them and eliminate redundant points. According to the characteristics of the action, the feature vector of the fusion key points position, distance, joint angle and key points speed is constructed, and the multi-layer perceptron is employed to train the action classification. The accuracy of action recognition on the KTH and self-made eight-section brocade data sets attains to 96.7% and 98.7%, respectively. Based on the eight-section brocade action recognition results, an action sequence is constructed, and the dynamic time warping algorithm is used to calculate the similarity of the two groups of eight-section brocade action sequences. The comparative experimental results show that the similarity can effectively evaluate the integrity and synchronization of actions. Table and Figures | Reference | Related Articles | Metrics

Select

Multi-Objective Optimization of Active Distribution Network Based on Particle Swarm Optimization SHI Zhenli,WEI Yewen Electronic Science and Technology    2022, 35 (9): 7-14.   DOI: 10.16180/j.cnki.issn1007-7820.2022.09.002 Abstract （98）   HTML （4）    PDF（pc） （1041KB）（24）       Knowledge map    Save With the large-scale grid integration of distributed renewable energy, the traditional distribution network has gradually developed from a single flow to a complex two-way flow. In view of the problem that the traditional dispatching method in active distribution network technology cannot be directly applied, this study explores improvement measures from two aspects of intelligent algorithm and optimization model. On the basis of considering the relevance of “source network load and storage”, aiming at improving the effect of peak shaving and valley filling, improving the economy of distribution network, and reducing the loss of distribution network, the forecast of wind and solar output has been carried out to improve the validity of the data, and a two-stage two-layer joint optimal dispatch model has been established. The study analyzes the advantages and disadvantages of the traditional particle swarm algorithm, and proposes to use the improved HE-MOPSO algorithm to solve the model. By solving the ZDT1~4 test function and using the extended IEEE33 node to perform the simulation calculation, the experimental results proved the superiority of the improved algorithm and model. Table and Figures | Reference | Related Articles | Metrics

Select

Improved YOLOv3 Model Based on New Feature Extraction and Fusion Module ZHAO Xuan,ZHOU Fan,YU Hancheng Electronic Science and Technology    2022, 35 (7): 40-45.   DOI: 10.16180/j.cnki.issn1007-7820.2022.07.007 Abstract （97）   HTML （1）    PDF（pc） （1663KB）（13）       Knowledge map    Save There is a certain optimization space for the feature extraction branch and multi-scale detection branch of YOLOv3 model. To solve this problem, this study proposes two structural improvement methods to improve the detection accuracy of the model on the target detection data set. For the three scales (13×13, 26×26, 52×52) of the YOLOv3 model, a priori anchor frames of different lengths and widths are used, and the label frames of the three scales are the same, and the feature fusion method between the design scales is used to improve the accuracy of the model. In view of the problem of convolutional layer spatial view sharing, the original convolutional layer can be replaced with deformable convolution to improve the accuracy of the model. The test result on the industrial tool library proves that the accuracy of the test set of the improved model is increased by 3.6 MAP when compared with the original YOLOv3. Table and Figures | Reference | Related Articles | Metrics

Select

Crop Height Measurement Based on Ruler Image Recognition SUN Xiang,PEI Xiaofang,ZHOU Wang,ZHU Ping Electronic Science and Technology    2022, 35 (7): 32-39.   DOI: 10.16180/j.cnki.issn1007-7820.2022.07.006 Abstract （97）   HTML （0）    PDF（pc） （1393KB）（8）       Knowledge map    Save Crop height measurement is an important part of automatic crop observation, which can directly reflect the growth of crops. To solve the problem that the cost of artificial measurement of crop height is higher and the subjective influence of individual is greater, this study presents a method of measuring crop height by image processing. The ruler is placed behind the main stalk of the crop to take the photo of the ruler. The obtained images were converted to HSV color space on MATLAB to divide and filter the color blocks of the ruler. The pixel height of the color block is calculated by the connected domain analysis method. The plant height is calculated by the ratio relation between the ruler pixel height and the actual height. The shrubbery is taken as the experimental object to take photos and make measurement. Comparing the measured plant height data with manual measurement data, the results show that the measurement error is less than 0.0173 m, which meets the standard of automatic observation of plant height. Table and Figures | Reference | Related Articles | Metrics

Select

Infant Expression Recognition Algorithm Based on MobileNetV2 and LBP Feature Fusion DENG Yuan,SHI Yiping,JIANG Yueying,ZHU Yamei,LIU Jin Electronic Science and Technology    2022, 35 (8): 47-52.   DOI: 10.16180/j.cnki.issn1007-7820.2022.08.008 Abstract （96）   HTML （3）    PDF（pc） （2265KB）（22）       Knowledge map    Save In view of the problems of low rate of infant expression recognition and the insufficient extraction of complex features, an infant expression recognition algorithm based on MobileNetV2 and LBP dual-channel feature fusion is proposed. The first channel uses the improved MobileNetV2 network to quickly and accurately extract the global features of facial expressions. The second channel divides the original input image into blocks, and uses image information entropy to construct weights, and extracts block-weighted LBP histogram features to highlight the regions with rich expression information. The output vector of the dual-channel model is fused to improve the feature expression ability, and the support vector machine is used to replace the Softmax layer for expression classification. Experiments show that the use of fusion features has a better classification effect than a single feature, and in the self-built infant expression data set, the accuracy of expression recognition can reach 85.71%. Table and Figures | Reference | Related Articles | Metrics

Select

Progress in Electrocatalysis Oxygen Reduction for Hydrogen Peroxide Production over Single-Atom Catalysts JIN Tao,HU Xia,YU Lanlan,ZHAO Wenjun,YANG Qi,TUO Ya Electronic Science and Technology    2022, 35 (11): 90-97.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.013 Abstract （96）   HTML （1）    PDF（pc） （3589KB）（21）       Knowledge map    Save Hydrogen peroxide production via electrocatalytic two-electron oxygen reduction is an effective alternative to traditional centralized anthraquinone processes. However, this process depends on a catalyst with low cost, high activity and high selectivity. In recent years, SACs have been considered as potential catalysts for oxygen reduction and hydrogen peroxide production due to their nearly 100% atom utilization efficiency, tunable electronic structure, and excellent catalytic performance, but the regulation of SAC activity remains a challenge. Starting from the mechanism of the ORR, the influence of the binding strength of the active metal center and *OOH on the oxygen reduction reaction pathway is elucidated. This study systematically illustrates the effect of adjusting the structure of the SAC on the binding of the metal center to *OOH from three aspects: metal center atom, coordination atom and the surrounding environment of the active center, and reveals the activity and selectivity of H2O2 production. Table and Figures | Reference | Related Articles | Metrics

Select

Improved Remote Incremental Update Scheme Based on BSDiff CHEN Dirong,BAO Xiaoan,DU Peng,HU Yifei,SU Hongbin Electronic Science and Technology    2022, 35 (7): 52-57.   DOI: 10.16180/j.cnki.issn1007-7820.2022.07.009 Abstract （95）   HTML （1）    PDF（pc） （955KB）（9）       Knowledge map    Save The traditional incremental update solution has weak cross-version update performance, and multiple incremental update packages need to be generated and issued, resulting in low terminal device update efficiency. In view of this problem, an improved remote incremental update scheme based on BSDiff is proposed in the present study. The scheme optimizes the firmware management method of the update server, and uses the BSDiff algorithm to instantly generate a unique incremental update package to reduce the amount of update data that needs to be transmitted. The BSDiff algorithm is improved to speed up the generation of incremental update packages. The simulation experiments show that the improved incremental update scheme has the same compression performance as the traditional incremental update scheme. It can reduce the time by 31.19% on average when generating incremental update packages and reduce the data transfer amount by 2.07% on average when updating across versions. Table and Figures | Reference | Related Articles | Metrics

Select

Design and Implement of a High-Performance RLWE Cryptoprocessor WANG Chunhua,LI Bin,DU Gaoming,LI Zhenmin Electronic Science and Technology    2022, 35 (11): 13-20.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.003 Abstract （93）   HTML （2）    PDF（pc） （1262KB）（23）       Knowledge map    Save The RLWE encryption scheme is one of the most potential candidates in the lattice cryptosystem in the post-quantum era. In view of the problem of high latency and low throughput in RLWE cryptoprocessor, this study proposes a high-performance RLWE cryptoprocessor hardware architecture. The parallel circuit structure of two NTT modules and four butterfly modules are adopted in the proposed architecture. In the pre-calculation and post-calculation process, the multipliers in the four butterfly modules are used for parallel calculation. In the encryption process, NTT calculation and ciphertext calculation are performed in parallel. In the processing of NTT and INTT operations, the data read and write process and calculation process are ping-pong operations, thereby hiding the data read and write cycle, reducing the delay of the RLWE encryption processor, and improving the throughput of the RLWE encryption processor. A hardware architecture is designed for resource reuse, the multiplier and adder are reused in the butterfly module during the encryption and decryption process, and the circuit structure of NTT is reused by INTT, thereby reducing the hardware resource consumption of the encryption processor. The cryptoprocessor with parameters of n=256 and q=65 537 is implemented on the Spartan-6 FPGA development platform. The results indicate that the encryption time is only 12.18 μs, the throughput is 21.01 Mbit·s-1, the decryption time is only 8.65 μs, and the throughput is 29.60 Mbit·s-1. Compared with other cryptoprocessor, the proposed design has improved the delay and throughput of the cryptoprocessor. Table and Figures | Reference | Related Articles | Metrics

Select

Joint Modulation Recognition Based on Instantaneous Feature and Power Spectrum Entropy XIE Aiping,ZHANG Yusheng,LIU Ying,HE Ziang,GAO Rui Electronic Science and Technology    2022, 35 (11): 104-110.   DOI: 10.16180/j.cnki.issn1007-7820.2022.11.015 Abstract （90）   HTML （7）    PDF（pc） （2091KB）（14）       Knowledge map    Save To solve the problem that the traditional instantaneous characteristic parameter recognition method has few signal types and low recognition rate under low SNR, a modulation recognition method based on the combination of instantaneous characteristic parameter and power spectrum entropy is proposed in this study. The improved instantaneous amplitude and phase characteristic parameters are used to identify the modulation signals, and the power spectrum entropy characteristic parameters are introduced to further realize the in-class recognition of more signals. The decision tree classification method is used to identify and classify the 9 common digital modulation signals {ASK, 4ASK, 2FSK, 4FSK, 8FSK, BPSK, QPSK, 8PSK, 16QAM} with appropriate threshold values. Monte Carlo experiment results show that compared with the existing recognition methods, the proposed method increases the number of signal types, and improves the signal recognition accuracy in the case of low SNR. Table and Figures | Reference | Related Articles | Metrics