Table of Content

15 September 2020 Volume 33 Issue 9

  

Optimal Designing of Permanent-magnet-assisted Single-phase Doubly Salient Motor

SHANGGUAN Xuanfeng,MA Yatao,WANG Shuangping,HU Gangqiang,LI Feixiang

Electronic Science and Technology. 2020, 33(9):  1-9.  doi:10.16180/j.cnki.issn1007-7820.2020.09.001

Abstract ( 384 )   HTML ( 139 )   PDF (1258KB) ( 65 )  

Figures and Tables | References | Related Articles | Metrics

In this paper, the optimization design of permanent-magnet-assisted single-phase doubly salient motor is studied. The basic equations for the ideal operating condition of the motor are derived, and the design step of the motor are summarized by referring to the design principle of the switched reluctance motor.Self-starting of the motor is achieved by using a tapered air gap. A permanent-magnet-assisted single-phase doubly salient motor with power rating of 45 W and rated speed of 2 000 r·min^-1 is designed by using the summarized design step. The influence of the main structural parameters of the motor on the efficiency and cogging torque is calculated by simulation, and its regularity is summarized, which provids a reference for motor optimization. The relationship between the ratio of the tapered air gap and the starting ability of the motor is discussed, and the motor is optimized by Taguchi experimental design method. The optimized motor efficiency is 89.86%, which is 4.46% higher than that before optimization, vorifying the effectiveness of motor design and optimization.

Sentiment Analysis Method of Financial Text Based on Transformer Encoder

LI Fupeng,FU Dongxiang

Electronic Science and Technology. 2020, 33(9):  10-15.  doi:10.16180/j.cnki.issn1007-7820.2020.09.002

Abstract ( 723 )   HTML ( 18 )   PDF (832KB) ( 96 )  

Figures and Tables | References | Related Articles | Metrics

Sentiment analysis plays an important role in many fields, but most of these studies focus on the field of commodity reviews and microblogs, and lack of sentiment analysis of financial texts. To solve this problem, a financial text sentiment analysis method based on Transformer encoder is presented in this paper. Transformer encoder is a feature extraction unit based on the self-attention mechanism. When Transformer encoder processes text sequence information, it can link any two words in a sentence without distance restriction, which overcomes the problem of long-term dependencies. The multi-head attention mechanism is used to calculate the same sentence several times and capture more semantic features implied in the context. The experiment is car+ried out on a balanced corpus data set based on financial news. The experimental results show that the method based on Transformer encoder has best effect in the field of financial text sentiment analysis compared with the models based on convolution neural network and recurrent neural network.

Expression Recognition Method Based on Cascade Network Optimized by SWA

ZHANG Xiang,SHI Zhicai,CHEN Liang

Electronic Science and Technology. 2020, 33(9):  16-20.  doi:10.16180/j.cnki.issn1007-7820.2020.09.003

Abstract ( 299 )   HTML ( 5 )   PDF (823KB) ( 36 )  

Figures and Tables | References | Related Articles | Metrics

In order to improve the detection accuracy of expression recognition technology, a face expression recognition method based on cascade network optimized by SWA is proposed. Compared with a single convolutional network, multi-network cascading reachs higher detection accuracy. With respect to the traditional training method SGD, SWA training method enhances the generalization ability of the sub-network in the cascade network, which further improves the overall performance of the model. By testing on the Fer2013 dataset, the experimental results shows that the detection accuracy of the network cascaded by the way of weighted summation based on SWA training method reachs 74.478%, which is 1.4% higher than the single network model trained by the traditional SGD method. In addition, the improved model proposed in the present study reachs a higher recognition accuracy than other typical methods.

Multi-target Tracking Algorithm by Combining Motion Information and Apparent Information

LI Yang,SHEN Ye,LIU Min,DAI Renyue,JIANG Xiaoyan

Electronic Science and Technology. 2020, 33(9):  21-25.  doi:10.16180/j.cnki.issn1007-7820.2020.09.004

Abstract ( 408 )   HTML ( 14 )   PDF (804KB) ( 61 )  

Figures and Tables | References | Related Articles | Metrics

Multi-target tracking is an important research direction in the field of computer vision. Multi-target tracking plays an important role in the fields of intelligent video surveillance, human-computer interaction, robot navigation, and public safety. At present, the target tracking algorithm still faces many challenges, such as the effects of occlusion, complex background, motion blur, etc., which are difficult to completely avoid. This paper proposes an algorithm that combines multiple types of information, which effectively improves the performance of the tracker. The model focuses on the problem of object detection and data association between frames, which depends on the similarity of the target motion and the apparent between different frames. When the target is lost and there is occlusion, the fusion of multi-source information reduces the related uncertainty. At the same time, the algorithm achieves real-time tracking performance in real-world environments. Experimental evaluation shows that the proposed tracker has good performance on the public data set, greatly reducing the target loss rate and ID switch.

Optimal Design of 6-bar Parallel Machine Tool Based on HyperWorks

CHENG Huaxiang,CHEN Jie,ZHANG Chi

Electronic Science and Technology. 2020, 33(9):  25-30.  doi:10.16180/j.cnki.issn1007-7820.2020.09.005

Abstract ( 270 )   HTML ( 4 )   PDF (1157KB) ( 29 )  

Figures and Tables | References | Related Articles | Metrics

In view of the problem that the resonance phenomenon occurs in the process of parallel machine, which leads to the deformation of the mechanism and affects the machining precision. The 6-bar parallel machine is taken as the research object, and topology optimization method is used to optimize the bed of the parallel machine. Firstly, the optimized parts of the bed are determined as the column, the cross frame and fixed platform, which are optimized by topology optimization module in HyperWorks. The column and cross frame are optimized by adding some reinforcement. The size of the stiffeners of the column is further optimized. Modal analysis and harmonious response analysis are used to verify the whole machine. Comparing the model before and after optimization, it is found that the total mass of the optimized model is reduced by 17.8%, and the first three order resonance frequencies increases by 19.56%, 20.62% and 0.091%, respectively. The resonance peak decreases by 49.454%, 29.036% and 0.0078% in X, Y and Z directions. The analysis of the results show that the optimized parallel machine avoids the occurrence of resonance during processing, and the machining accuracy has been significantly improved.

Simulation and Optimization of Quadruped Robot Trajectory Based on MATLAB Robotics Toolbox

CHEN Mingfang,ZHANG Kaixiang,CHEN Jiupeng,XIONG Bingzhou,LI Qi,YAO Guoyi,LI Pengyu

Electronic Science and Technology. 2020, 33(9):  31-37.  doi:10.16180/j.cnki.issn1007-7820.2020.09.006

Abstract ( 1117 )   HTML ( 28 )   PDF (1380KB) ( 166 )  

Figures and Tables | References | Related Articles | Metrics

The foot end trajectory of the bionic quadruped robot plays an important role in its movement. MATLAB Robotics Toolbox has been used for modeling, solving the forward and reverse solutions and trajectory planning. For a structure such as a quadruped robot with only 3 DOF at the end, there are certain defects in the solution and simulation by this tool. In this study, by exploring the underlying function of the toolbox, the reason for the problem is that the “ikine” function was not applicable. The toolbox is targeted for secondary development by replacing the "ikine" function with the inverse solution formula. At the same time, the problem of increasing the multi-solution of the inverse kinematics of the optimization algorithm is optimized according to the principle of minimum angle change. The real-time dynamic simulation results of the set trajectory shows that the walking process is naturally smooth, and the joint rotation characteristic curve is within a reasonable range, which verifies the effectiveness and rationality of the optimization algorithm.

Reactive Power Control and Delay Algorithm in Microgrid Based on Consistency Algorithm

ZHU Yanxiang,LONG Yingwen

Electronic Science and Technology. 2020, 33(9):  38-43.  doi:10.16180/j.cnki.issn1007-7820.2020.09.007

Abstract ( 399 )   HTML ( 7 )   PDF (1012KB) ( 41 )  

Figures and Tables | References | Related Articles | Metrics

In view of at the problems of reactive power distribution and communication delay in isolated island microgrid, a hierarchical control algorithm based on consistency algorithm is proposed in this paper. Each distributed power supply exchangs voltage information with the neighboring distributed generation supply under the clock cycle, and obtains the average voltage value of the whole network through the local voltage consistency algorithm, which updates the voltage state value with the iteration cycle, and realizes the accurate distribution of reactive power of each distributed generation supply. In the voltage consistency algorithm, the communication delay between local nodes and adjacent nodes is saved. The maximum communication delay time between adjacent nodes can be obtained by the topology structure of the micro-grid system, and the delay error is dynamically compensated by the PI algorithm. The island microgrid simulation model is established on MATLAB/Simulink platform, and the experimental results verifies the effectiveness of the control strategy.

Dangerous Vehicle Early Warning Algorithms Based on Multi-Agent Enhancement Learning

WANG Zexue,WAN Qidong,QIN Yangmei,FAN Senqing,XIAO Zeyi

Electronic Science and Technology. 2020, 33(9):  44-49.  doi:10.16180/j.cnki.issn1007-7820.2020.09.008

Abstract ( 307 )   HTML ( 11 )   PDF (1178KB) ( 27 )  

Figures and Tables | References | Related Articles | Metrics

In view of the current problem that pedestrians are vulnerable to vehicle impact and lack of active protection means, an intelligent wearable device including radar module to protect pedestrians from vehicle impact is proposed in this study. On this basis, a safety intelligent algorithm based on fuzzy comprehensive evaluation is proposed. From the perspective of pedestrians, radar-detected vehicle data, local road traffic conditions, weather, pedestrian status and other factors are considered as evaluation indicators. In order to improve the accuracy and adaptability of the algorithm, a method based on BP neural network and multi-agent reinforcement learning is proposed to give dynamic weights to each index of fuzzy comprehensive evaluation. The simulation results shows that the alarm accuracy of the algorithm is more than 55% higher than that of the weighted method such as AHP, and the learning efficiency of the algorithm is nearly 28 times higher than that of the single agent reinforcement learning, which indicated that intelligent wearing equipment can effectively predict and warn the impact of vehicles on pedestrians.

The Research of Smart Space Power Distribution System Base on PMOS Power Switch

YI Deying,CHEN Hengzhi,YU Lei,WANG Lintao,WU Yiran

Electronic Science and Technology. 2020, 33(9):  50-55.  doi:10.16180/j.cnki.issn1007-7820.2020.09.009

Abstract ( 402 )   HTML ( 3 )   PDF (1320KB) ( 34 )  

Figures and Tables | References | Related Articles | Metrics

The NMOS driving and controlling circuit cost lots of hardware resources in the solid-state smart power distribution system based on the NMOS SSPC of manned spacecraft, and is unable to meet the requirements of telemetry information for self-health management of spacecraft energy system. To solve this problem, a new solid-state smart power distribution system which is based on PMOS SSPC is proposed. Compared with the NMOS, the PMOS which is used as a positive switch, has non-isolated driving characteristic and costs less system resource. In addition, PMOS can simplify the hardware circuit design and get more telemetry information at the same time, and solve the contradiction between limited hardware resources and more telemetry parameters requirement. Aiming at bus voltage instability of solid-state distribution system caused by SSPC load short circuit protection, an auxiliary circuit scheme for improving the reliability of solid-state power distribution is proposed in this paper, which prevents the stability of the busbar from the effect caused by load short-circuit protection fault.

The Orthogonal Wideband Signal Modulation and Demodulation Method Based on Chebyshev Bhaotic Sequence

JIANG Yu,REN Longping,BAI Xingyu,OU Hongfei

Electronic Science and Technology. 2020, 33(9):  56-62.  doi:10.16180/j.cnki.issn1007-7820.2020.09.010

Abstract ( 231 )   HTML ( 3 )   PDF (1008KB) ( 23 )  

Figures and Tables | References | Related Articles | Metrics

An orthogonal wideband signal modulation and demodulation method based on Chebyshev chaotic sequence is proposed in this paper to improve the reliability of underwater acoustic communication. The method is based on the environment and propagation characteristics of ocean underwater acoustic channel. The statistical properties of Chebyshev chaotic sequence are close to environmental noise, and it has sharp autocorrelation and broadband characteristics. Based on the properties, Chebyshev chaotic sequence is used as information carrier and synchronization signal in the proposed method. The received signal is demodulated by Euclidean distance classifier. Experimental results show that the method effectively suppresses the frequency selective fading and inter-symbol interference caused by multi-path propagation of the underwater acoustic channel, and achieves reliable underwater acoustic communication under low SNR conditions. The simulation results verify that the communication method has good communication performance on the underwater acoustic channel with multipath effect in the signal-to-noise ratio environment above -10 dB.

Research on Rail Surface Defect Recognition Based on Faster R-CNN

SU Ye,LI Jun,YANG Haima,LIU Jin,JIANG Shenghua

Electronic Science and Technology. 2020, 33(9):  63-68.  doi:10.16180/j.cnki.issn1007-7820.2020.09.011

Abstract ( 615 )   HTML ( 26 )   PDF (1068KB) ( 99 )  

Figures and Tables | References | Related Articles | Metrics

External factors usually have effects on the instrument used to detect rail surface defect, resulting in poor accuracy and efficiency of instrument. For this problem, a method for detecting rail surface defects based on the Faster R-CNN network is investigated. The method reverses the preprocessed image and realizes the projection of rail image with Radon transform. In the projection curve, the rail surface area is extracted by using the characteristics that the rail length is fixed and the gray value is less than the average value of the image. Then, the candidate region is extracted through the regional proposal network and compared with the regional recommendation of Fast R-CNN network for the detection of surface defects of rail by the Faster R-CNN networks. According to the test data, the accuracy of crack, scar, abrasion and scratch is 92.17%, 91.85%, 93.45% and 93.27% respectively, which verifies the efficiency and accuracy of the proposed method in identify the surface defects of rail.

Simulation of Metro Curved Rail Corrugation Based on Wear Quantification

ZHENG Lingxia,YAO Huiming

Electronic Science and Technology. 2020, 33(9):  69-74.  doi:10.16180/j.cnki.issn1007-7820.2020.09.012

Abstract ( 293 )   HTML ( 3 )   PDF (1188KB) ( 33 )  

Figures and Tables | References | Related Articles | Metrics

In view of the rail corrugation problem commonly existing in subway small radius curves, the influence of wheel-rail mechanical parameters on rail corrugation is studied from the perspective of wheel-rail wear. A single wheel-set simulation model integrating wheel-rail dynamic model, wheel-rail rolling contact mechanics model and Archard material wear model is established using MATLAB/Simulink. The simulation results show that the larger the radius of the curve, the less likely the rail corrugation occurrs. The result is consistent with the frequent corrugation of the small radius curve, which proves the correctness of the model. Subsequently, the model is used to further analyze the influence of vehicle load and curve super-high on the wave grinding.

Research on Substation Integrated Automation Control System Based on DSP

CHEN Guizhou

Electronic Science and Technology. 2020, 33(9):  75-78.  doi:10.16180/j.cnki.issn1007-7820.2020.09.013

Abstract ( 285 )   HTML ( 8 )   PDF (588KB) ( 37 )  

Figures and Tables | References | Related Articles | Metrics

Traditional substation automation system mostly uses single-chip computer as its internal core processor. This system not only has simple functions, but also has poor ability to deal with complex problems. In order to solve the above problems, a set of substation integrated automation control system based on DSP is developed in this paper. The system can monitor, measure, controls and coordinate the real-time operation status of substation equipment by analyzing and processing the collected data by DSP combined with communication and computer technology. Experiments and test results show that the automation system can better complete the functions of automatic monitoring and control of secondary equipment in substation, and significantly improves the efficiency of data transmission and sharing among electrical equipment in substation.