Table of Content

15 November 2023 Volume 36 Issue 11

  

A Bayesian Network Structure Learning Algorithm with Structure Priors

TONG Zhaojing,LI Jinxiang,QIAO Zhengrui

Electronic Science and Technology. 2023, 36(11):  1-7.  doi:10.16180/j.cnki.issn1007-7820.2023.11.001

Abstract ( 180 )   HTML ( 9 )   PDF (947KB) ( 50 )  

Figures and Tables | References | Related Articles | Metrics

The computational complexity of Bayesian Networks(BN) increases with the increase of the number of nodes, and the optimal structure of BN is still a NP(Non-deterministic Polynomial Time)-hard problem. To optimize the BN structure and improve the computing power of the complex BN structure, the BN structure is optimized through the hybrid learning method of constraints and scores. In the constrained learning, PC (Peter-Clark) algorithm is used to generate the initial network structure to improve the initial score of the network. Score-based learning uses the sparrow search algorithm to find the optimal structure of BN to enhance its scoring search ability in BN. The sparrow search algorithm and PC algorithm are applied to BN to optimize its structure, and the standard BN is used to conduct experiments, which proves the feasibility and effectiveness of the proposed algorithm in BN structure learning. Experiments on networks with different complexities show that the proposed method obtains better BIC scores than other algorithms, and in the test of 2 000 samples on the ASIA network, the error from the standard score is only 0.2.

Permanent Magnet Synchronous Motor Control Based on Super-Twisting Sliding Film Observer

HUANG Chengcheng,JIN Hai,LU Wenqi

Electronic Science and Technology. 2023, 36(11):  8-13.  doi:10.16180/j.cnki.issn1007-7820.2023.11.002

Abstract ( 140 )   HTML ( 5 )   PDF (1217KB) ( 43 )  

Figures and Tables | References | Related Articles | Metrics

In view of the high precision requirement of permanent magnet synchronous motor in some workplaces, an algorithm based on second-order Super-Twisting synovium theory is proposed based on the mathematical model of permanent magnet synchronous motor. In this method, the motor speed and position information are obtained by calculating the observed value of the back electromotive force of the motor, so as to realize the sensorless control of the permanent magnet synchronous motor. According to Lyapunov stability theory, the observer converges. MATLAB/Simulink is used to build a simulation model of the control system to verify the feasibility of the control system. The simulation results show that compared with the traditional synovial film observer, the proposed algorithm can effectively reduce the chattering of synovial film, improve the estimation accuracy and response speed of the system, and enables it to track the rotor position and velocity information better.

Design of High-Dynamic-Range Vector Impedance Measurement Module Based on Directional Coupler

WANG Peng,LI Xiangyu

Electronic Science and Technology. 2023, 36(11):  14-18.  doi:10.16180/j.cnki.issn1007-7820.2023.11.003

Abstract ( 74 )   HTML ( 3 )   PDF (2081KB) ( 44 )  

Figures and Tables | References | Related Articles | Metrics

In view of the design difficulties of the vector impedance measurement module with a high dynamic range, this study designs a vector impedance measurement module based on the directional coupler using the directional coupler combined with the high-dynamic-range RF (Radio Frequency) logarithmic amplifier. The hardware and software design framework is given, the mathematical principle of the module is deduced, and the experimental verification and testing of the module are completed. The design makes full use of the characteristics of directional coupler, and the test system is small in size, good in scalability, fast in test speed and high in efficiency. The design can also be extended to a monitoring and measuring module, which can be used in communication equipment as an antenna monitoring component or power intensity control component of communication transmitter. After the verification, a number of practical applications have been developed using this design scheme. The high dynamic range of the proposed designed covers the application scenarios from 20~400 W, and obtains good application effect, which proves that the proposed design has good application, expansibility and high practical value.

Scene Recognition Algorithm Based on Deep Transfer Learning and Multi-Scale Feature Fusion

WANG Qiao,HU Chunyan,LI Feifei

Electronic Science and Technology. 2023, 36(11):  19-27.  doi:10.16180/j.cnki.issn1007-7820.2023.11.004

Abstract ( 231 )   HTML ( 6 )   PDF (2190KB) ( 68 )  

Figures and Tables | References | Related Articles | Metrics

CNN(Convolutional Neural Networks) hase achieved excellent results in the field of scene recognition research, but this method do not fully take into account the particularity of the scene. Due to different scales, viewpoints, and backgrounds, there exists large intra-class variation within the same scene class. On the other hand, the common objects also result in a certain inter-class similarities among heterogeneous scenes as well. Considering that scene images of different scales will affect the size of objects in them, this study proposes a scene recognition algorithm based on deep transfer learning and multi-scale feature fusion. First, the network parameters pre-trained on the Places data set are migrated to the CNN model used in this study using migration learning, and then the network is fine-tuned and retrained to reduce the training cost. Secondly, the multi-scale image blocks obtained from the class activation map are fed into the CNN for feature extraction, and the obtained feature vectors are fused to make the final scene image features more comprehensive. Experiment results carried out on the SUN397 data set show that compared with other CNN-based algorithms, the proposed algorithm significantly improves the accuracy of scene recognition.

Advances in Application of Deep Learning in Centroid Localization and Vertebrae Segmentation of Spine

SUN Hong,MO Guangping,XU Guanghui,YANG Chen

Electronic Science and Technology. 2023, 36(11):  28-34.  doi:10.16180/j.cnki.issn1007-7820.2023.11.005

Abstract ( 124 )   HTML ( 4 )   PDF (972KB) ( 44 )  

Figures and Tables | References | Related Articles | Metrics

Spinal centroid localization and vertebral segmentation have great significance in the guidance of spinal surgery. Accurately locate the spinal centroid and segment vertebrae has become an important research topic.In recent years, with the improvement of GPU computing power and the accumulation of medical image data, the application of deep learning in spinal imaging has made a major breakthrough. In order to study the application status and development of deep learning in the task of spinal medical image localization and segmentation, this study storts out and studies the models of spinal localization and segmentation in this field in recent years. This study collects the commonly used data sets and evaluation indexes of the spine, discusses the application of a deep learning model in spinal centroid location and segmentation, and analyzes the realization process and shortcomings of the model. This study also outlines the countermeasures for the problems faced by the current application of deep learning in spinal centroid location and segmentation and outlines the feasible development direction in the future.

Named Entity Recognition of Automobile Production Equipment Fault Domain Based on BERT

NI Ji,WANG Yujia,ZHAO Bo

Electronic Science and Technology. 2023, 36(11):  35-40.  doi:10.16180/j.cnki.issn1007-7820.2023.11.006

Abstract ( 99 )   HTML ( 5 )   PDF (872KB) ( 45 )  

Figures and Tables | References | Related Articles | Metrics

In the field of automobile production equipment fault, the entity category of Chinese named entity is complicated, and the traditional word vector can not solve the polysemy of one word. In view of these problems, this study proposes a named entity recognition model in the field of automobile production equipment fault based on BERT(Bidirectional Encoder Representations From Transformer). First, the semantic information and syntactic features are extracted by BERT pretraining model to generate dynamic word vectors. Then, the word vector is input into bidirectional long-short term memory for bidirectional encoding to obtain the semantic features of long sequences. Finally, the conditional random field is used for sequence decoding to learn the dependency relationship between labels and obtain the optimal label sequence. Experiments are carried out on the self-built real automobile production equipment fault data set, and the accuracy, recall rate and F1 value are 87.9 %, 89.6 % and 88.7 %, respectively.

Research on Internal Positioning of Transformer Partial Discharge Ultrasound Based on Whale Algorithm

QIAN Dingdong,SONG Ke,WANG Wei

Electronic Science and Technology. 2023, 36(11):  41-46.  doi:10.16180/j.cnki.issn1007-7820.2023.11.007

Abstract ( 90 )   HTML ( 3 )   PDF (2809KB) ( 30 )  

Figures and Tables | References | Related Articles | Metrics

The partial discharge caused by the insulation defect of the transformer winding endangers the safe operation of the power supply system, and the current detection of partial discharge is greatly affected by factors such as electromagnetic interference and sensor arrangement. Therefore, this study proposes an arrangement of built-in sensors at the transformer inspection port, and uses the whale optimization algorithm (WOA) to estimate the location of partial discharge points. By establishing a three-phase transformer winding model through COMSOL, the propagation law of ultrasonic waves in the transformer winding is simulated and analyzed, and the time delay information required by the WOA algorithm for positioning is obtained. The simulation results show that for the partial discharge points of the B-phase high and low voltage windings, the layout of the asymmetric quadrilateral array using the WOA algorithm has a smaller positioning error than the symmetrical quadrilateral array, and the average error is 3.9 cm. Additionally, for A-phase, two built-in detection points at the mouth can effectively locate the partial discharge point, and the average error is 5.1 cm. The obtained results can provide a certain reference value for the partial discharge positioning of the on-site transformer.

Study on Outdoor Anti-Jamming Identification and Location System Based on Apriltag

DAI Jinhong,XIANG Zhenwen,YU Huifu

Electronic Science and Technology. 2023, 36(11):  47-55.  doi:10.16180/j.cnki.issn1007-7820.2023.11.008

Abstract ( 136 )   HTML ( 2 )   PDF (2784KB) ( 42 )  

Figures and Tables | References | Related Articles | Metrics

Image recognition and positioning technology is the key to realize industrial automation and intelligence. However,in practical applications, the target is often partially occluded in the outdoor interference environment, which results in the invalidation of the image recognition and positioning system. To solve the problem of invalidation of image recognition and positioning system in outdoor interference environment, an outdoor anti-jamming recognition and positioning system based on Apriltag is proposed to replace the conventional system. Combining Apriltag feature with monocular vision principle, an image recognition and positioning system based on Apriltag is established. The Apriltag detection algorithm and the occluded target recognition algorithm based on SURF feature detection are used to achieve all-weather and anti-interference outdoor target recognition and positioning. The experimental system is established with the positioning target based on Apriltag, industrial camera and industrial computer. The experimental results show that the positioning errors of the XY plane are 1.44 mm and 1.36 mm, respectively, the recognition time is 90 ms, The error fluctuation under repeated experiments is less than 0.5 mm, which indicates that the recognition positioning system has high accuracy, rapidity and stability.

Bearing Fault Diagnosis Based on SC-CNN-BiLSTM

YU Guangzeng,ZHANG Qiaoling,ZHOU Yurong

Electronic Science and Technology. 2023, 36(11):  56-65.  doi:10.16180/j.cnki.issn1007-7820.2023.11.009

Abstract ( 130 )   HTML ( 4 )   PDF (2435KB) ( 33 )  

Figures and Tables | References | Related Articles | Metrics

In view of the problem that bearing fault data contains irrelevant components such as noise and most bearing fault diagnosis methods cannot make full use of fault data, a fault diagnosis model based on skip connection- convolutional neural network- bidirectional long short-term memory network is proposed. The original vibration signal is converted into a two-dimensional time-frequency image using short-time Fourier transform, and the spatial and temporal features of the time-frequency image are extracted by convolutional neural network and long-short-term memory network respectively, and the classification is realized by combining the fully connected layer. Adding the structure of soft threshold attention and skip connection can make full use of the output features of different network levels while filtering out irrelevant components. The proposed diagnostic model is verified by MFPT(Machinery Failure Prevention Technology) bearing data, and the experimental results show that the proposed model can achieve a fault identification accuracy of 99.79%.

Circulating Current Suppression Strategy for MMC-HVDC Converter Station under Asymmetric Grid Voltage

WANG Zhongyang,YAO Lei,LI Tianhao,GAO Shang

Electronic Science and Technology. 2023, 36(11):  66-75.  doi:10.16180/j.cnki.issn1007-7820.2023.11.010

Abstract ( 77 )   HTML ( 2 )   PDF (1278KB) ( 31 )  

Figures and Tables | References | Related Articles | Metrics

The flexible DC transmission system using modular multilevel converter technology has the problem of bridge arm circulation when the system is running. By analyzing the instantaneous energy of the bridge arm under the asymmetric grid voltage, it is concluded that there are double-frequency positive, negative and zero sequence AC components and DC components in the bridge arm circulating current, and the distribution of the DC components is not equal. To solve the problem of the precise control of AC components, an AC controller based on expected transient amplitude response is proposed. By analyzing the open and closed loop characteristics of the system, it is theoretically proved that the AC controller has the advantages of high control accuracy and good stability. Furtherly, a new circulating current suppression strategy based on the controller is proposed. This strategy can directly control the bridge arm of each phase independently in abc three-phase stationary coordinate without coordinate transformation and phase lock loop. The control structure is simple and can eliminate double-frequency positive, negative and zero sequence circulations at the same time. A 51-level back-to-back transmission system model is built in the MATLAB/Simulink simulation platform, and the correctness and effectiveness of the circulation suppression strategy are verified.

Study on the Transmission Characteristics of Oblique Incident Sound Waves in One-Dimensional Phononic Crystals with Defects

SHEN Jiamin,FAN Zhetao,XU Guidong,XU Chenguang

Electronic Science and Technology. 2023, 36(11):  76-82.  doi:10.16180/j.cnki.issn1007-7820.2023.11.011

Abstract ( 53 )   HTML ( 3 )   PDF (1832KB) ( 37 )  

Figures and Tables | References | Related Articles | Metrics

The propagation of acoustic waves in the periodic structure of phononic crystals has energy band effects, and phononic crystals containing defects can form new defect modes in the original forbidden band. In this study, the omnidirectional transmission spectra of phononic crystals with and without defects in obliquely incident acoustic waves are calculated respectively by the transfer matrix method, and the defect modes caused by solid defects are found by comparative analysis. On this basis, the influence of the thickness and position of the defect layer on the transmittance of the defect state is studied in this study. The existence of defect modes caused by solid defects and their angle-dependent characteristics are verified by underwater acoustic transmission experiments. The experimental results show that there is a new transmission passband in the first Bragg forbidden band of the omnidirectional transmission spectrum of the defect-containing structure, and with the increase of the incident angle within a certain range, the frequency corresponding to this passband is shifted to the high frequency direction. This study improves the propagation characteristics of obliquely incident acoustic waves in one-dimensional phononic crystals containing defects, and provides a theoretical and experimental basis for the practical application of defect states.

Optimization of Automotive Permanent Magnet Brush DC Motor Efficiency Based on Maxwell Software

CHEN Fanfan,SUN Ning

Electronic Science and Technology. 2023, 36(11):  83-88.  doi:10.16180/j.cnki.issn1007-7820.2023.11.012

Abstract ( 272 )   HTML ( 1 )   PDF (1648KB) ( 40 )  

Figures and Tables | References | Related Articles | Metrics

Permanent magnet brush DC motor is widely used in the automotive field. "Carbon sink Plan" requires the further reduction of automotive energy consumption, so the optimization problem of motor efficiency is becoming increasingly prominent. Based on vehicle cooling fan with permanent magnet brush DC motor as the research object, in view of the motor inefficiencies, using the finite element analysis software Maxwell, through simulation and parametric analysis of the rotor lamination length, laminated slots, winding wire diameter, winding pitch, winding circle number influences the performance of motor, combined with the simulation results and actual production conditions, determine the feasible motor efficiency optimization scheme. According to the optimization scheme, the sample is made and measured. The test data show that the motor efficiency is improved by 4.8%, and the optimization effect of motor efficiency is obvious.

Research Progress on Control Technology of Multi-Degree of Freedom Parallel Robot

LUO Xiaoqing

Electronic Science and Technology. 2023, 36(11):  89-94.  doi:10.16180/j.cnki.issn1007-7820.2023.11.013

Abstract ( 242 )   HTML ( 12 )   PDF (665KB) ( 76 )  

References | Related Articles | Metrics

In order to further improve the control accuracy and stability of the multi degree of freedom parallel robot, the control optimization methods based on technical models such as dynamics and redundant drive branches have gradually attracted extensive attention and research in the academic community, and a certain number of research results and conclusions have been proposed. In recent years, with the mathematical expression of dynamics and driving branch model becoming clear and refined, the control accuracy and stability of parallel robots with multi-degree of freedom have been further improved. By reviewing the research history of parallel robot control technology, the current research ideas and status quo of parallel robot control technology are summarized. On this basis, the existing problems of parallel robot control technology are deeply explored, and the research trend and development direction of future parallel robot control technology are proposed.