Table of Content

15 July 2023 Volume 36 Issue 7
    Design and FPGA Implementation of Large Scale Matrix Inversion Accelerator Based on LDL Algorithm
    YU Haoran,XIAO Hao
    Electronic Science and Technology. 2023, 36(7):  1-7.  doi:10.16180/j.cnki.issn1007-7820.2023.07.001
    Abstract ( 471 )   HTML ( 498 )   PDF (1252KB) ( 302 )  
    Figures and Tables | References | Related Articles | Metrics

    Matrix inversion is a basic problem in engineering calculation. In large-scale MIMO systems, array signal processing, image signal processing and other applications, the processing speed of large-scale matrix inversion is very important to the system performance. However, the traditional matrix inversion method has high computational complexity, low parallelism and consumes a lot of storage space, which is not conducive to hardware acceleration. Aiming at the hardware acceleration problem of large-scale matrix inversion, this study studies the matrix inversion algorithm based on LDL decomposition and proposes a large-scale matrix inversion acceleration architecture based on this algorithm. Using the characteristic that the diagonal elements of triangular matrix after LDL decomposition are all 1, the matrix is designed by block iteration, which reduces the amount of calculation and improves the calculation speed. This study designs and implements the accelerator based on Xilinx Virtex7 FPGA. The experimental results show that under the 128 order matrix, the throughput is 105.2 Inv·s-1 and the maximum clock frequency is 200 MHz. Compared with the existing matrix inversion acceleration scheme, this design occupies less hardware resources and has higher performance.

    Recognition Method of the Combined Trackside Signal Light Based on Image Processing
    GUO Qicheng,SHEN Tuo,ZHANG Xuanxiong
    Electronic Science and Technology. 2023, 36(7):  8-15.  doi:10.16180/j.cnki.issn1007-7820.2023.07.002
    Abstract ( 103 )   HTML ( 11 )   PDF (5287KB) ( 50 )  
    Figures and Tables | References | Related Articles | Metrics

    The trackside signal light is an important guidance for a running train in a rail transportation system. However, the combined trackside signal light included two colors is also used as a specific sign in addition to the usual single color signal light. In order to solve the recognition problem of the combined trackside signal light, a method based on image processing technology is employed to recognize the combined trackside signal light located within 150 m in front of train. As a result, the candidate region characteristics of the combined trackside signal light are extracted by color segmentation, morphological processing, and Hough transform. On the other hand, the combined trackside signal light can be positioned on the right of running rail train. The central spacing between two single lights can determine whether or not existing combined trackside signal light to remove the possible interferences from other lights or environment. The experimental results indicate that this method can accurately locate and recognize the combined trackside signal light, and the color correction ratio is 94.14% for green and yellow light, 96.21% for two green lights, 86.67% for two yellow lights.

    Research on MMC Circulation Suppression Strategy Based on SOGI
    WEI Shenghui,HAO Zhenghang,CHEN Zhuo
    Electronic Science and Technology. 2023, 36(7):  16-23.  doi:10.16180/j.cnki.issn1007-7820.2023.07.003
    Abstract ( 99 )   HTML ( 5 )   PDF (1012KB) ( 29 )  
    Figures and Tables | References | Related Articles | Metrics

    MMC is widely used in high-voltage DC transmission applications due to its highly symmetrical sub-module cascade structure and good output waveform quality. The presence of MMC circulating current will aggravate the bridge arm loss, distort the bridge arm current and generate high harmonic components, which will seriously damage the power quality. In view of this problem, this study adopts the method of extracting the AC component of the circulating current by a multi-harmonic filter based on the interplay of SOGI and DC integrator and suppressing the circulating current by a new circulating current suppressor composed of three quasi-PR controllers connected in parallel. An 11-level MMC inverter simulation model is established on MATLAB/Simulink platform, and the simulation results show that the proposed control strategy can effectively complete the control of the system. Compared with the traditional circulating current suppression method, the circulating current suppression effect of the proposed method is more obvious, and the capacitor voltage fluctuation range is reduced by about 60%, which verifies the correctness and effectiveness of the proposed control circulating current control strategy.

    Optimization Method of Planar Microphone Array Configuration Based on Genetic Algorithm
    ZHANG Dagui,ZHOU Zhifeng,ZHANG Yi
    Electronic Science and Technology. 2023, 36(7):  24-31.  doi:10.16180/j.cnki.issn1007-7820.2023.07.004
    Abstract ( 121 )   HTML ( 12 )   PDF (1993KB) ( 51 )  
    Figures and Tables | References | Related Articles | Metrics

    In the sound source localization system, the first problem to be solved is to use a smaller number of microphones and design an array configuration with better performance in a limited plane range. This sutdy proposes an array optimization method based on genetic algorithm to solve the problem. The design of the fitness objective function of the genetic algorithm comprehensively considers the array beam pattern, the width of the main lobe, the level of the side lobe and the number of microphones. By improving the genetic algorithm, the genetic algorithm can be realized in the application of microphone array optimization. The simulation results show that: compared with the traditional cross-shaped and rectangular planar regular arrays, the optimized array configuration can reduce the number of microphones used while ensuring the performance of the array. Compared with the particle swarm optimization algorithm, the array optimized by the improved genetic algorithm has better performance.

    Lightweight Generative Adversarial Networks Based on Multi-Scale Gradient
    SUN Hong,ZHAO Yingzhi
    Electronic Science and Technology. 2023, 36(7):  32-38.  doi:10.16180/j.cnki.issn1007-7820.2023.07.005
    Abstract ( 102 )   HTML ( 3 )   PDF (1562KB) ( 51 )  
    Figures and Tables | References | Related Articles | Metrics

    With the advancement of generative adversarial network research, the computational amount of the network model increases sharply, its own training instability still exists, and the quality of the generated image also needs to be improved. To solve the problems, a lightweight generative adversarial network is proposed, which introduces multi-scale gradient structure to solve the problem of unstable training. By combining the ideas of self-attention mechanism and dynamic convolution, the cyclic module and image enhancement module are used to improve the learning ability of the model under the premise of keeping fewer parameters. The verification experimental results show that the inception score is 2.75 and the FID is 70.1 on CelebA data set, the inception score is 2.61 and the FID is 73.2 on LUSN data set, which is better than that of the classical models such as SAGAN and DCGAN, and verifies the feasibility and performance of the proposed algorithm.

    Multi-UAV Path Planning Algorithm Based on Formation Change
    WANG Yangbin,ZHANG Wei,HU Zhi
    Electronic Science and Technology. 2023, 36(7):  39-48.  doi:10.16180/j.cnki.issn1007-7820.2023.07.006
    Abstract ( 120 )   HTML ( 5 )   PDF (4822KB) ( 28 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problem of trajectory planning of multiple UAVs in complex environments, a multi-UAV trajectory planning algorithm based on formation changes is proposed. Based on the topology of pilot-following UAV, a cost function with time and range as the metrics is designed to solve the optimal formation rendezvous point. The improved Informed-RRT* algorithm is used to solve the asymptotic optimal track of the leader, and the track planning and obstacle avoidance of the follower is realized by combining the formation change strategy. On the basis of defining formation variation, path length ratio, and heading stability performance indicators, simulation experiments are carried out and the generated tracks are evaluated and compared. The simulation results show that the UAV formation can achieve trajectory planning and obstacle avoidance in complex environments, and at the same time plan the optimal trajectory planning for the follower, which is less than 1% away from the optimal trajectory length of the leader, which improves the practicality and effectiveness of the algorithm.

    Fault Diagnosis of Few Shot Industrial Process Based on Transfer BN-CNN Framework
    OU Jingyi,TIAN Ying,XIANG Xin,SONG Qizhe
    Electronic Science and Technology. 2023, 36(7):  49-55.  doi:10.16180/j.cnki.issn1007-7820.2023.07.007
    Abstract ( 141 )   HTML ( 7 )   PDF (912KB) ( 42 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problem of weak diagnosis performance caused by insufficient training samples in industrial process fault diagnosis, a transfer BN-CNN framework is proposed based on transfer learning and deep learning in this study. In order to reduce the dependence of the network on the initialization method, a batch normalization layer is introduced into the convolution neural network to normalize the hidden layer of the model. To solve the problem of insufficient label data in the target domain, the sample-based transfer learning method is used to expand the labeled data volume of the target domain. By introducing the model based transfer learning method, the BN-CNN network is pre-trained with sufficient source domain data, and some parameters of the network are fine-tuned by using the expanded target domain. The difficulty of training the deep neural network with a small number of samples is reduced, and a fault diagnosis model suitable for target domain is obtained. The comparison experiments on TE industrial data set show that the proposed has good diagnostic performance for small samples of industrial process faults, and its average accuracy is 0.804.

    Dynamic Receptive Field Feature Selection Dehazing Network
    ZHA Junwei,ZHANG Hongyan
    Electronic Science and Technology. 2023, 36(7):  56-63.  doi:10.16180/j.cnki.issn1007-7820.2023.07.008
    Abstract ( 75 )   HTML ( 1 )   PDF (2512KB) ( 36 )  
    Figures and Tables | References | Related Articles | Metrics

    Most of the deep-learning based dehazing models have fixed receptive filed after the parameter are fixed. As a result, the dehazing network cannot adopt the optimal mode for dehazing each specific scene, resulting in ambiguity and distortion in the results. In view of these problems, this study proposes a dynamic receptive field feature selection dehazing network. A feature-attention atrous block with atrous convolution is designed as the basic module of the network. Multiple feature attention atrous blocks with different atrous rates are used in parallel to extract multi-scale features. Dynamic feature fusion is performed on these features to form a dynamic receptive field block. Multiple dynamic receptive field blocks are combined with residual connections to form a deep network. The features from different levels are dynamically mixed and decoded to obtain a haze-free image. The experimental results show that the proposed algorithm has a good dehazing performance on indoor, outdoor, and real hazy images, and can generate clear and natural dehazing images.

    Research on Radio Wave Propagation Prediction Model of Vehicle-Mounted Ultrashort Wave Radio
    LI Min,ZHANG Guangshuo,XU Zhijiang,XIE Hongxing,LU Hongmin
    Electronic Science and Technology. 2023, 36(7):  64-69.  doi:10.16180/j.cnki.issn1007-7820.2023.07.009
    Abstract ( 198 )   HTML ( 6 )   PDF (1434KB) ( 34 )  
    Figures and Tables | References | Related Articles | Metrics

    Given the problem that the communication distance and quality of the vehicle-mounted ultrashort wave radio are affected by ground attachments and topography in the actual combat environment, a radio wave propagation prediction model of vehicle-mounted ultrashort wave radio is established based on ray tracing and machine learning. The integrated modeling of armored combat vehicle and vehicle antenna is established to obtain the antenna radiation pattern, and combined with electronic images, the radio wave propagation simulation model based on ray tracing technology is established. Based on the machine learning algorithm of the random forest and data results for the simulation model, the radio wave propagation prediction model based on the random forest was established. Compared with traditional classical radio wave propagation models such as the Egli and Okumura-Hata models, the radio wave propagation prediction model based on the random forest has higher accuracy. The root mean square error reaches 2.190 1 dB, and the coefficient of determination reaches 0.960 1. It can accurately predict radio wave propagation in the tactical communication environment.

    A Farmland Parcel Extraction Network Based on Multi-Scale Semantic Information Enhancement
    ZENG Xinxin,ZHANG Hongyan
    Electronic Science and Technology. 2023, 36(7):  70-74.  doi:10.16180/j.cnki.issn1007-7820.2023.07.010
    Abstract ( 146 )   HTML ( 7 )   PDF (2273KB) ( 69 )  
    Figures and Tables | References | Related Articles | Metrics

    Facing the problems of adhesion of adjacent parcels and incomplete parcels due to the high heterogeneity and the small region among neighbor parcels, a farmland parcel extraction network based on multi-scale semantic information enhancement is proposed in this study. To alleviate the adhesion between parcels, the multi-scale feature extraction module with parallel structure is used, which retained the high-resolution feature maps to maintain high-precision edge information and reduce the loss of spatial location information due to downsampling. Furthermore, to reduce the phenomenon of incomplete parcels, the global semantic information enhancement module based on attentional mechanism is utilized to enhance the classification ability of the network by capture global semantic information instead of local semantic information. According to the experimental results, it is shown that the proposed method is 1%~13% better than the four typical algorithms in existing studies in terms of IoU, OA, and F1-score evaluation indexes.

    Sparrow Search Algorithm Based on Adaptive t-Distribution and Random Walk
    NIE Fangxin,WANG Yujia
    Electronic Science and Technology. 2023, 36(7):  75-80.  doi:10.16180/j.cnki.issn1007-7820.2023.07.011
    Abstract ( 106 )   HTML ( 3 )   PDF (699KB) ( 34 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problems of low convergence accuracy and falling into local optimum when solving complex problems, a sparrow search algorithm based on adaptive t-distribution and random walk is proposed in this study. In the initialization process, the algorithm uses reverse learning to generate reverse solutions from which excellent individuals are selected to form the initial population. In the original sparrow search algorithm, the adaptive t-distribution strategy and Gaussian random walk strategy are used to improve the optimization ability of the sparrow individuals, and can prevent the algorithm from premature. The simulation results show that the proposed algorithm improves the convergence accuracy and convergence speed when compared with the comparison algorithm.

    Modeling and Simulation Research of Electromagnetic Interference Source in Vehicle Electric Drive System
    REN Yongda,XU Qiang,XIE Hongxing,ZHANG Jiahai,LU Hongmin
    Electronic Science and Technology. 2023, 36(7):  81-86.  doi:10.16180/j.cnki.issn1007-7820.2023.07.012
    Abstract ( 103 )   HTML ( 5 )   PDF (1422KB) ( 34 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problem of vehicle electromagnetic interference caused by electric drive system, an Electromagnetic Interference (EMI) prediction model of the electric drive system is established using precise modeling method of modules. The model consists of the high-frequency equivalent circuit model of the motor and the inverter model. Based on vector-fitting method, the motor impedance amplitude-frequency curve is fitted, and a high-frequency equivalent circuit model of the motor is established. In the inverter model, the influence of the parasitic parameters between IGBT and radiator on the system EMI is considered. The common mode interference voltage of the electric drive system is predicted using the established EMI model. The results show that the error between the simulated and measured results is less than 10 dB in the range of 0.1~100 MHz.


Monthly,Founded in September 1987
Competent Authorities:
Ministry of Education of the People's Republic of China
Sponsored by:Xidian University
Chief Editor:Liao Guisheng
Executive Editor:Wan Liancheng
Editor:Hei Lei
Editor and Publisher:
The Editorial Department of Electronic Science and Technology
Distribution Abroad:
China Intermational Book Trading Corporation
P.O.BOx 399,Beijing 100044,China
P.O.Box 375,2 Taibai Road(South),Xi'an 710071,China
Unit Price:$20.00