Table of Content

15 August 2022 Volume 35 Issue 8
    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 ( 195 )   HTML ( 66 )   PDF (2848KB) ( 120 )  
    Figures and Tables | References | Related Articles | Metrics

    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.

    Power Amplifier Behavior Modeling Based on Deep Temporal Convolutional Network
    ZHOU Fan,ZHAO Xuan,SHAO Jie
    Electronic Science and Technology. 2022, 35(8):  7-13.  doi:10.16180/j.cnki.issn1007-7820.2022.08.002
    Abstract ( 149 )   HTML ( 8 )   PDF (2608KB) ( 37 )  
    Figures and Tables | References | Related Articles | Metrics

    As the core component of the radiation source transmitter, the power amplifier has the characteristics of high non-linearity and strong memory, which makes it difficult to model the behavior of the power amplifier. In view of this problem, this study proposes a method for behavior modeling of power amplifiers based on Deep TCN. The neural network model adopted by this method is composed of multiple multi-dimensional time series convolution blocks, and each time series convolution block is composed of several causal dilation convolutions used to increase the receptive field of the network and residual structures used to improve the efficiency of gradient feedback. Through the parallel convolution operation, the model overcomes the disadvantages of traditional convolutional networks that cannot handle variable-length sequences, and improves the efficiency of behavioral modeling while preserving the memory effect of power amplifiers. The behavior modeling results of measured data show that compared with the existing Volterra series and recurrent neural network modeling methods, the proposed method can significantly improve the accuracy of behavior modeling. Compared with the recurrent neural network modeling method, the proposed method reduces the implementation time by an order of magnitude in terms of the efficiency of behavior modeling.

    Design of a High-Performance SC Decoder for Polar Codes
    WANG Xiaolei,DAI Wujun,DU Gaoming,LI Zhenmin,ZHANG Duoli
    Electronic Science and Technology. 2022, 35(8):  14-20.  doi:10.16180/j.cnki.issn1007-7820.2022.08.003
    Abstract ( 159 )   HTML ( 4 )   PDF (1423KB) ( 30 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of high latency, low throughput and low area efficiency of polar code SC decoder, a high-performance hardware architecture of SC decoder is proposed. The decoder becomes low-latency and high-throughput by pruning frozen bit nodes to simplify the SC decoding binary tree, designing cross-cycle storage for PE, and using 2b-SC algorithm in the last stage. The resource-reused method is adopted to increase the decoder area efficiency. The testing results show that the cycle of the proposed decoder is 330, the throughput is 388.85 Mbit·s-1, and the area efficiency is 2.204 Mbit·s-1·kGE-1. Compared with other SC decoders, latency, throughput and area efficiency of the high-performance SC decoder proposed in this study are significantly improved. Additionally, the decoder has lower power consumption and broad application prospect.

    Optimization Design of Air Gap Structure of Series Compensating Saturated Core Fault Current Limiter
    WANG Ruixin,YAO Lei
    Electronic Science and Technology. 2022, 35(8):  21-26.  doi:10.16180/j.cnki.issn1007-7820.2022.08.004
    Abstract ( 129 )   HTML ( 3 )   PDF (1173KB) ( 23 )  
    Figures and Tables | References | Related Articles | Metrics

    Saturated core fault current limiter will cause higher harmonic pollution when used in series compensation. In order to ensure the safe and stable operation of the power system, the saturated core fault current limiter with improved air gap structure is designed based on the principle of segment saturated core. The simulation models of saturated core fault current limiter with different air gap structures are established by JMAG. The relationship between current and flux of the current limiter is imported into MATLAB/Simulink and the corresponding simulation system model is established to further analyze and compare the control characteristics, harmonic content and fault current limiting ability of the two current limiter models. The results show that the saturated core fault current limiter with improved air gap structure has about 1.5 times of reactance regulation range and lower harmonic distortion rate when compared with the full air gap structure without losing the current limiting capacity.

    Optimization Allocation Strategy of ECU Redundancy under EMP
    JI Zhenjie,WEI Minxiang,ZHA Yueheng,ZHOU Dong,CAO Jie
    Electronic Science and Technology. 2022, 35(8):  27-33.  doi:10.16180/j.cnki.issn1007-7820.2022.08.005
    Abstract ( 94 )   HTML ( 5 )   PDF (935KB) ( 26 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to solve the redundancy allocation problem in the control unit, a quantum chaotic adaptive particle swarm optimization algorithm and a hybrid strategy of thermal backup are proposed. According to the common cause failure under the electromagnetic pulse, electronically controlled unit is simplified into a series and parallel system, and β factor is introduced to build a Markov model with the highest reliability as the objective function and the redundancy number as the constraint condition. The quantum chaos adaptive particle swarm optimization algorithm is used to optimize the maximum reliability of electronically controlled unit under electromagnetic pulse. The simulation results show that the hybrid strategy and optimization algorithm improve the calculation efficiency and the accuracy of redundancy allocation, which provides a reference basis for the redundancy reinforcement of electronically controlled unit under electromagnetic pulse.

    An Optimization Method of K-Barrier Lifetime in Mobile Sensor Network
    XUE Liang,WANG Ran
    Electronic Science and Technology. 2022, 35(8):  34-40.  doi:10.16180/j.cnki.issn1007-7820.2022.08.006
    Abstract ( 82 )   HTML ( 4 )   PDF (1317KB) ( 16 )  
    Figures and Tables | References | Related Articles | Metrics

    In order to improve the lifetime of K-barrier coverage, this study combines energy harvesting technology with mobile sensor network to construct K-barrier coverage, and proposes BCAS algorithm. K+1 barriers are constructed by dividing sub-areas to divide the entire time into multiple time slots. Before the start of each time slot, K barriers are selected with the largest average remaining energy for activation. After each time slot, redundant sensors are scheduled, and the sensors whose remaining energy in the fence is less than the threshold are moved and replaced, and the life of the network is prolonged through multiple rounds of scheduling. Simulation experiments show that compared with the MobiBar algorithm and the Single Sensor algorithm, BCAS algorithm extends the life cycle of the barrier network by an average of 183%. In terms of the average moving distance of the barrier construction, the BCAS algorithm reduces by 20.6% and 12% respectively when compared with the MobiBar algorithm and the Single Sensor algorithm.

    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 ( 190 )   HTML ( 5 )   PDF (1091KB) ( 79 )  
    Figures and Tables | References | Related Articles | Metrics

    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.

    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 ( 273 )   HTML ( 9 )   PDF (2265KB) ( 45 )  
    Figures and Tables | References | Related Articles | Metrics

    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%.

    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 ( 232 )   HTML ( 21 )   PDF (2388KB) ( 52 )  
    Figures and Tables | References | Related Articles | Metrics

    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.

    Short-Term Power Demand Forecasting Based on SARIMA-GS-SVR Combined Model
    LIU Han,WANG Wanxiong
    Electronic Science and Technology. 2022, 35(8):  58-65.  doi:10.16180/j.cnki.issn1007-7820.2022.08.010
    Abstract ( 191 )   HTML ( 6 )   PDF (1169KB) ( 29 )  
    Figures and Tables | References | Related Articles | Metrics

    Short-term power demand forecasting plays an important role in the rational distribution of power utilization, reducing energy waste and enhancing the grid-connected operation of the power system. Using the single model of the seasonal auto regressive integrated moving average to forecast electricity demand will limit its prediction accuracy. In order to improve the prediction accuracy of the SARIMA model, the SARIMA-GS-SVR combined forecasting model is proposed in this study. The grid search algorithm is used to bring the residual predicted by SARIMA into the support vector regression model for parameter training, and the best parameters for optimization are brought into the SVR to predict the residuals. The obtained residual prediction results and the SARIMA prediction results are added together for comprehensive analysis. SARIMA, SVR, GS-SVR and SARIMA-GS-SVR forecasting models are established, and California’s historical electricity demand data is taken as an example to predict the 24-hour electricity demand in California on a certain day. In order to reflect the overall superiority of the model, the exponential smoothing method is selected as an irrelevant benchmark model for experimental comparison. The results show that compared with the SARIMA model, the prediction accuracy of the SARIMA-GS-SVR model is increased by 29.181 2%, and the three error index values of the SARIMA-GS-SVR model such as MAE, MAPE and RMSE are significantly lower than the other four models.

    Research on Dynamic Monitoring Method of Pantograph-Net Contact Position in Complex Environment
    ZHANG Qiaomu,ZHONG Qianwen,SUN Ming,LUO Wencheng,CHAI Xiaodong
    Electronic Science and Technology. 2022, 35(8):  66-72.  doi:10.16180/j.cnki.issn1007-7820.2022.08.011
    Abstract ( 146 )   HTML ( 3 )   PDF (2012KB) ( 38 )  
    Figures and Tables | References | Related Articles | Metrics

    In view of the problem of low detection efficiency of high-speed train pantograph in the complex environment of passing through the support bridge tunnel, a dynamic monitoring method of the pantograph-net contact position under complex environment is proposed. In order to obtain the original training data set, the pantograph video is captured by frame difference. The deep learning network PSPNet is used to semantically segment the contact line and the pantograph of the image, which is used to construct the feature data set with more obvious contact points of pantograph. To obtain the coordinates, the improved YOLOv4 is used for training and detection. The results show that the proposed method can effectively mark the contact point position between pantograph and catenary in each frame image, and can capture the movement state of pantograph and output the relative coordinate position when the train passes through the support frame and bridge, so as to achieve the monitoring purpose of pantograph, and the detection accuracy of the proposed method can reach 96.8%.

    A Multi-Point Calibration Method of Articulated Arm Coordinate Measuring Machine
    ZENG Zhijiang,GAO Guanbin,MA Wenjin
    Electronic Science and Technology. 2022, 35(8):  73-78.  doi:10.16180/j.cnki.issn1007-7820.2022.08.012
    Abstract ( 170 )   HTML ( 8 )   PDF (2374KB) ( 27 )  
    Figures and Tables | References | Related Articles | Metrics

    The articulated arm coordinate measuring machine is a new type of multi-freedom non-orthogonal coordinate measuring machine, which needs to be regularly calibrated to ensure the accuracy and stability. In order to quickly calibrate the articulated arm coordinate measuring machine, a kinematics model is established based on D-H method, and the kinematics error model is established based on the kinematics parameters of the model. Through the design and production of the standard measuring rod device, the articulated arm coordinate measuring machine is repeatedly calibrated and distance is calibrated by the multi-point method. After calibration, the single-point repeatability increases from 0.09 mm to 0.05 mm, and the distance accuracy increases from 0.529 mm to 0.046 9 mm, indicating that the proposed method simplifies the calibration steps and improves the calibration efficiency.


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