Table of Content

15 August 2024 Volume 37 Issue 8

  

Research on Object Detection Based on Radar and Video Fusion

ZHU Yong, HUANG Yongming, HE Xing

Electronic Science and Technology. 2024, 37(8):  1-7.  doi:10.16180/j.cnki.issn1007-7820.2024.08.001

Abstract ( 113 )   HTML ( 10 )   PDF (3310KB) ( 61 )  

Figures and Tables | References | Related Articles | Metrics

The object detection based on video has the problem of poor recognition effect in bad weather, so it is necessary to make up for video defects and improve the robustness of detection framework. In view of this problem, this study designs an object detection framework based on radar and video fusion. YOLOv5 (You Only Look Once version 5) network is used to obtain image feature map and image detection frame, density-based clustering is used to obtain radar detection frame, and radar data is encoded to get object detection results based on radar information. Finally, the detection boxes of the two are superimposed to obtain a new ROI (Region of Interest), and the classification vector after fusion radar information is obtained, which improves the detection accuracy in extreme weather. The experimental results show that the mAP(mean Average Precision) of the framework reaches 60.07%, and the parameter number is only 7.64×10⁶, which indicates that the framework has the characteristics of lightweight, fast computing speed and high robustness, and can be widely used in embedded and mobile platforms.

Adaptive Golden Eagle Algorithm Based on Symmetric Mapping Search Strategy and its Application

ZHOU Xuhu, LI Shigang, LUO Yi, ZHANG Wei

Electronic Science and Technology. 2024, 37(8):  8-16.  doi:10.16180/j.cnki.issn1007-7820.2024.08.002

Abstract ( 47 )   HTML ( 5 )   PDF (1165KB) ( 26 )  

Figures and Tables | References | Related Articles | Metrics

The GEO(Golden Eagle Optimizer) is a population-based meta-heuristic algorithm that simulates the cooperative hunting behavior of golden eagles. In view of the problem of poor solution accuracy and local optima traps in the GEO algorithm, this study proposes an improved MERGEO (Mapped Elitist Reverse GEO) algorithm. Based on the original algorithm, symmetric mapping search strategy, adaptive elite strategy and random backward learning mechanism, are used to balance the exploration and development stages of the algorithm, and obtain the ability to avoid local optimal and better optimization accuracy. The independent strategy effectiveness analysis, scalability analysis and optimization performance comparison with other algorithms are carried out on 10 benchmark test functions. The experimental results show that the improved MERGEO algorithm has strong competitiveness and good optimization ability. The improved algorithm is applied to the coverage optimization problem of wireless sensor networks and pressure vessel design problem, which verifies the practical application value of improved algorithm.

HOT-FSMO Sensorless Control Based on Improved Tracking Differentiator

CHEN Zhipeng, ZHANG Huilin, CHENG Wenbin, WANG Zhongyang

Electronic Science and Technology. 2024, 37(8):  17-25.  doi:10.16180/j.cnki.issn1007-7820.2024.08.003

Abstract ( 39 )   HTML ( 1 )   PDF (1427KB) ( 25 )  

Figures and Tables | References | Related Articles | Metrics

To address the problems of large sliding mode chatter and phase delay in the traditional first-order flux sliding mode observer, a HOT-FSMO(High-Order Terminal Flux Sliding Mode Observer)based on an improved tracking differentiator is proposed in this study. A high-order sliding mode control law is designed to achieve chatter suppression of flux linkage estimation, and a new tracking differentiator with low chatter containing a terminal attractor is combined to replace the conventional low-pass filter to achieve accurate tracking of the flux linkage and rotor position, as well as filtering functions. The experimental results show that the HOT-FSMO based on the novel tracking differentiator can effectively reduce the sliding mode chattering and decrease the position estimation error, while speeding up the system response and improving the system dynamic performance under different speed and load conditions when compared with the traditional linear flux linkage sliding mode observer.

Blockchain Mobile Edge Computing Offloading Model Based on Bird Swarm Artificial Fish Swarm Algorithm

KONG Xiaoshuang, YUAN Jian

Electronic Science and Technology. 2024, 37(8):  26-33.  doi:10.16180/j.cnki.issn1007-7820.2024.08.004

Abstract ( 48 )   HTML ( 4 )   PDF (1701KB) ( 28 )  

Figures and Tables | References | Related Articles | Metrics

The rapid increase in the number of computing-intensive tasks has led to an overload of SMD(Smart Mobile Devices) computing tasks. By using MEC(Mobile Edge Computing Servers) and idle ED(Edge Devices) in the network, SMD with limited computing power can offload computing tasks to MEC and ED collaboration, and enhance system security based on the DPoR(Delegated Proof of Reputation) consensus mechanism. This study proposes a blockchain mobile edge computing offloading model based on BS-AFSA(Bird Swarm-Artificial Fish Swarm Algorithm), which transforms the task offloading problem into an optimization objective function to reduce the computational overhead. The improved BS-AFSA is used to optimize the task delay and energy consumption, and the behavior parameters in the algorithm are constructed and the crowding factor is improved to elevate the local search accuracy in the later iteration. The simulation results show that compared with other benchmark algorithms, the proposed algorithm reduces the possibility of falling into local optimum and effectively reduces the total system cost of the joint offloading scheme.

A Bayesian Network Optimization Method for Transformer Fault Diagnosis

TONG Zhaojing, JING Lifei, LAN Mengyue

Electronic Science and Technology. 2024, 37(8):  34-39.  doi:10.16180/j.cnki.issn1007-7820.2024.08.005

Abstract ( 55 )   HTML ( 6 )   PDF (2052KB) ( 29 )  

Figures and Tables | References | Related Articles | Metrics

In view of the low efficiency of transformer fault diagnosis, an improved grasshopper optimization algorithm is proposed by combining dissolved gas analysis in oil with artificial intelligence method to optimize the transformer fault diagnosis method of Bayesian network. The differential evolution algorithm and simulated annealing algorithm are used to improve the locust algorithm, which improve the optimization ability of the algorithm. The improved locust algorithm is applied to the Bayesian network structure learning to construct the transformer fault diagnosis model, and the method proposed in this study is used to diagnose the transformer fault. The experimental results show that the diagnosis accuracy of this method is 92.7%, which is higher than that of other algorithms.

Energy Management Strategy of Island Microgrid with Photothermal Power Station Including Carbon Trading Mechanism

GAO Xiangyu, CHEN Bei, HUANG Shuaibo

Electronic Science and Technology. 2024, 37(8):  40-46.  doi:10.16180/j.cnki.issn1007-7820.2024.08.006

Abstract ( 36 )   HTML ( 1 )   PDF (965KB) ( 17 )  

Figures and Tables | References | Related Articles | Metrics

In view of the low carbon economy of energy supply and the stable operation of "heat to power" of cogeneration units in offshore islands, an energy management strategy of island micro-grid of photothermal power stations with carbon trading mechanism is proposed. Based on the multi-energy island micro-grid system integrating power collection, heat and water, such as solar thermal power station, heat pump, wind power, micro gas turbine unit and seawater desalination equipment, the heat pump achieves the bi-directional conversion of electric-thermal energy with solar thermal power station to improve the power generation capacity of solar thermal power station and meet part of the heat load demand. Carbon trading mechanism is introduced to limit carbon emissions, and low-carbon economic model of island micro-grid is established to study the economy of different operation modes of island micro-grid with the participation of photothermal power stations. The multi-scenario comparison experiment verifies that the island micro-grid low-carbon economic dispatching can better balance economy and environmental protection, and generate less carbon emissions while operating at a lower economic cost.

Stress Relaxation Characteristics and Numerical Simulation of Mn-Cu Alloy under Different Deformation Conditions

XIONG Yajun, LIU Yan, YUAN Xianpu

Electronic Science and Technology. 2024, 37(8):  47-53.  doi:10.16180/j.cnki.issn1007-7820.2024.08.007

Abstract ( 41 )   HTML ( 3 )   PDF (1529KB) ( 25 )  

Figures and Tables | References | Related Articles | Metrics

The improvement of computing power provides a support for finite element simulation analysis, which can solve more complex structures and nonlinear problems more efficiently. In this study, based on the finite element simulation analysis technology, the complex mechanical properties of Mn-Cu alloy are simulated. Prony series constitutive model and parallel rheological constitutive model are respectively adopted to simulate the stress relaxation test of Mn-Cu alloy under different deformation conditions. The stress relaxation experimental data are extracted and converted into the corresponding model parameters and the finite element simulation calculation is carried out. The simulation model parameters which can accurately describe the nonlinear mechanical properties of Mn-Cu alloy are obtained. By comparing the simulation and experimental results, it is concluded that the parallel rheological framework can more accurately characterize the stress relaxation behavior of Mn-Cu alloy. Under different initial strain conditions, the relative error of the simulation results and the test results under corresponding working conditions is less than 1%. Compared with Prony series constitutive model, parallel rheological framework is more suitable for the simulation of Mn-Cu alloy under complex working conditions.

Research on Large Twin-Rotor UAV Based on Fuzzy PID

JIN Rui, JIN Hai, MO Songnan

Electronic Science and Technology. 2024, 37(8):  54-59.  doi:10.16180/j.cnki.issn1007-7820.2024.08.008

Abstract ( 60 )   HTML ( 6 )   PDF (1606KB) ( 38 )  

Figures and Tables | References | Related Articles | Metrics

Compared with the quad-rotor UAV(Unmanned Aerial Vehicle), the large twin-rotor UAV has the advantages of lower price, longer endurance and higher efficiency, but it has serious coupling and poor anti-interference ability. To solve these problems, this study proposes a dual-rotor control algorithm using variable universe fuzzy PID (Proportional Integration Differentiation). In this study, the UAV system is divided into position control and attitude control. In attitude control, fuzzy PID is used to adjust the parameters of PID in real time to improve the stability of UAV. According to the motion mode of UAV, a new type of UAV structure is proposed, and the dynamic model of double-rotor is established, and the simulation model is built on Simulink for verification. The results show that the proposed algorithm reduces the overshoot by 50% when compared with the ordinary PID control algorithm, which indicates that the proposed algorithm has better stability on large twin-rotor UAV and can recover faster in case of interference.

Prediction of Degradation Trend of IGBT Modules Based on CSSA-LSTM

LIU Hangqing, ZHAO Guoshuai, HAN Sumin

Electronic Science and Technology. 2024, 37(8):  60-67.  doi:10.16180/j.cnki.issn1007-7820.2024.08.009

Abstract ( 42 )   HTML ( 1 )   PDF (2659KB) ( 28 )  

Figures and Tables | References | Related Articles | Metrics

In view of the problem of high failure efficiency of IGBT(Insulated Gate Bipolar Transistor) modules in inverters, which are most prone to damage and aging, and the device degradation process is difficult to predict, a neural network prediction model combining LSTM(Long Short-Term Memory) and chaotic sparrow is proposed. By introducing the two-dimensional Pearson correlation coefficient method to obtain the combined degradation features, the LSTM-based voltage degradation prediction model is constructed. The model is used to adaptively extract the internal correlations of degradation features to realize the screening of key information and digging deep degradation features. In the feasible domain of sparrow search algorithm, Gaussian random numbers with normal distribution and chaotic sequence corresponding to Tent mapping are introduced to improve the accuracy and stability of prediction. The learning rate, number of neurons and batch-size of the model are optimized to find the optimal value to match the network topology. The LSTM with the optimal structural parameters is used to predict each original data separately and obtain the final degradation prediction value. The accelerated degradation data set of NANS experimental center is analyzed and compared with the conventional prediction algorithm to verify the effectiveness and accuracy of the proposed algorithm.

Research on Power Grid Dispatching Considering Demand Response and Wind Power Uncertainty

WANG Yumei, ZHANG Jiqin, ZHOU Yongxin

Electronic Science and Technology. 2024, 37(8):  68-74.  doi:10.16180/j.cnki.issn1007-7820.2024.08.010

Abstract ( 43 )   HTML ( 2 )   PDF (2148KB) ( 22 )  

Figures and Tables | References | Related Articles | Metrics

In view of the increasing influence of wind power uncertainty on power system, this study proposes an economic dispatching method of power grid source-load network considering demand response. According to the price elasticity theory of demand and the principle of consumer psychology, a price-based demand response model is constructed. Based on flexible compensation incentive demand response, the complementary characteristics of the two types of demand responses are fully considered, and the reserve constraints of the two types of demand responses on the system are increased. The general probability distribution is introduced to describe the output characteristics of wind power, and the expected cost is used to quantify the uncertainty of wind power to punish the cost. The nonlinear variables in the objective function are linearized, and the mixed integer linear programming problem is used to solve the model. The simulation results show that the proposed model can effectively reduce the peak-valley difference of load and improve the absorptive capacity of wind power.

Non-Local Support Attention Network for Few-Shot Object Detection

XIE Xijun, LI Feifei

Electronic Science and Technology. 2024, 37(8):  75-83.  doi:10.16180/j.cnki.issn1007-7820.2024.08.011

Abstract ( 54 )   HTML ( 5 )   PDF (4016KB) ( 34 )  

Figures and Tables | References | Related Articles | Metrics

The key point of current research on few-shot object detection based on meta-learning is how to make better use of the information of support branch to help query branch to recognize novel objects more effectively. However, many current methods fuse the features from support branch and query branch in the depth direction, ignoring the spatial position relationship between features. Therefore, this study proposes non-local support attention network. This method not only adds support information into the proposals features, but also fuses the support information with the features that fed into region proposal network. The spatial position relationship between features is considered at the same time. It also adds the information of negative supports to the detection module to help the model distinguish the objects from different categories. This method obtains good performance on base classes and novel classes of COCO2017 dataset, particularly under the case of incremental learning. Compared with method before improvement, 3.3/3.8/4.7 mAP is increased in AP/AP50/AP75 of novel classes. 2.7/0.5/3.3 mAP is increased in AP/AP50/AP75 of the base classes, and outperformed the performance of SOTA(Sort-Of-The-Art) model DAnA(Dual-Awareness Attention) under the same setting.

Real-Time Hybrid Task Scheduling Algorithm in Embedded Multicore System

LUO Guang, MAO Hang, ZHU Yangshuo, ZHANG Fengdeng

Electronic Science and Technology. 2024, 37(8):  84-91.  doi:10.16180/j.cnki.issn1007-7820.2024.08.012

Abstract ( 107 )   HTML ( 6 )   PDF (996KB) ( 51 )  

Figures and Tables | References | Related Articles | Metrics

In this study, an algorithm based on BFZL(Boundary Fair until Zero Laxit) is proposed to solve the problem of reasonable scheduling of real-time mixed task set formed by periodic task and sporadic task. Based on the I-BF(Improved Boundary Fair) real-time mixed task algorithm, the relaxation parameter of LLF(Least Laxity First) algorithm is introduced to improve the priority of decision task. A heuristic algorithm based on relaxation and heuristic strategy is proposed to improve task assignment strategy. The experimental results show that the BFZL algorithm can satisfy the real-time performance of the system and achieve the purpose of algorithm optimization. Through data comparative analysis, compared with the original algorithm, the proposed algorithm reduces the average response time of sporadic tasks by about 26%, reduces the context switch and migration by about 28% and 50%, respectively. Additionally, the algorithm also has advantages in scheduling overhead.

Overview of Research on Network Security Situation Prediction Technology

LU Zhenyang

Electronic Science and Technology. 2024, 37(8):  92-96.  doi:10.16180/j.cnki.issn1007-7820.2024.08.013

Abstract ( 86 )   HTML ( 7 )   PDF (607KB) ( 41 )  

References | Related Articles | Metrics

In order to further reduce the probability of multiple networks being attacked, different types of network security situation prediction models have received widespread attention and in-depth research from scholars both domestically and internationally. With the rapid development of situational awareness modeling technology, various novel technical solutions such as neural networks, time series, and support vector machines have been introduced into the prediction model of network security situations, deeply optimizing and improving the means and methods of situational prediction models, thereby further improving the accuracy of situational prediction models. This study reviews and sorts out the research history and development process of network security situation prediction technology, elaborates on the main principles and current development status of situation prediction models, analyzes the shortcomings and deficiencies of current technical solutions, and points out the future research directions of network security situation prediction model technology.

A Design of 6~18 GHz Ultra-Wideband T/R Module with 4 GHz Instantaneous Bandwidth

WANG Jie, WU Huafeng, LI Ning, LIAO Yuan, ZHOU Shenghua

Electronic Science and Technology. 2024, 37(8):  97-102.  doi:10.16180/j.cnki.issn1007-7820.2024.08.014

Abstract ( 39 )   HTML ( 4 )   PDF (2821KB) ( 30 )  

Figures and Tables | References | Related Articles | Metrics

In view of the high instantaneous bandwidth requirement of modern electronic countermeasures equipment, a 6~18 GHz ultra-wideband T/R module with instantaneous bandwidth of 4 GHz is designed in this study. The MCM(Multi-Chip Module) and ultra-wideband signal transmission technologies are used to realize the requirements of high integration, miniaturization and modularization of T/R components. The structure of T/R components, the index budget of transceiver channel, the simulation of broadband signal transmission characteristics and the design of electromagnetic compatibility are described in detail. The test results show that the T/R module has a good performance in the 12 GHz operating bandwidth, the transmit power is greater than 35 dBm, the receive gain is greater than 20 dB, the noise factor is less than 5 dB, and the total delay time is up to 762 ps.