Loading...

Archive

    For Selected: Toggle Thumbnails
    Information & Control
    CT Diagnosis Method for Coronavirus Pneumonia with Integrated Multi-scale Attention Mechanism
    Peng SHAN, Lin ZHANG, Hong-ming XIAO, Yu-liang ZHAO
    2024, 45 (12):  1673-1679.  DOI: 10.12068/j.issn.1005-3026.2024.12.001
    Abstract ( 354 )   HTML ( 9)   PDF (2222KB) ( 49 )  

    Artificial intelligence (AI)‑based diagnosis has become an important auxiliary method for detecting lung infections. However, most existing approaches rely on deep learning, which are often plagued by issues such as insufficient model stability, high complexity, and low accuracy. This paper presents a shallow model which incorporates a multi‑scale attention mechanism to achieve both high accuracy and a simple structure for diagnosing COVID‑19 from CT scans. Firstly, two datasets of COVID‑19 CT images are combined into a single dataset to address the issue of model instability caused by insufficient data. Secondly, by introducing multi‑scale attention(MA) in the final three layers of the shallow ResNet18 network, the model’s feature extraction capability is enhanced. Finally, classifier with three fully connected layers (CTFCL) is constructed to improve the classification performance of the model, thereby increasing the accuracy of lung CT classification. Experimental results show that the proposed model achieves an accuracy of 95.41%, outperforming networks such as ResNet50, ResNet101, VGG16, and DenseNet169. Furthermore, the model has only 12.24×106 parameters, which is approximately 50% fewer than networks like ResNet50 and VGG16.

    Figures and Tables | References | Related Articles | Metrics
    Three-Dimensional Reconstruction Method of Monocular Video Image Sequences
    Xiao-peng SHA, Jia-qi CAO, Wen-jing LI, Ye QIN
    2024, 45 (12):  1680-1687.  DOI: 10.12068/j.issn.1005-3026.2024.12.002
    Abstract ( 234 )   HTML ( 4)   PDF (2964KB) ( 64 )  

    For 3D reconstruction in uncalibrated monocular scene, due to the existence of motion blur and small baseline image, there are still problems such as blurred image, low feature matching, and reconstruction accuracy. A 3D reconstruction method of monocular vision system is proposed. Firstly, the fuzzy image in the original data is detected and removed by wavelet transform algorithm according to the edge information of the image, and the wide baseline image is screened by geometric robustness criterion to obtain clear images for 3D reconstruction. Then, an algorithm for eliminating mismatched feature points based on region division is proposed to eliminate repeated matching and mismatched feature points. Finally, three different regional growth methods are proposed to obtain more feature points for three‑dimensional point calculation. The results show that the proposed method can effectively remove mismatched feature points, improve the accuracy of feature point matching, obtain more point clouds, and improve the integrity and accuracy of the reconstructed model.

    Figures and Tables | References | Related Articles | Metrics
    Resource Allocation Algorithm Based on Edge Server Task Migration
    Jing-jing WU, Zi-xuan ZHANG
    2024, 45 (12):  1688-1695.  DOI: 10.12068/j.issn.1005-3026.2024.12.003
    Abstract ( 193 )   HTML ( 0)   PDF (1168KB) ( 38 )  

    IIoT (industrial Internet of Things) devices send tasks that cannot be computed locally to edge servers for processing. However, different device densities result in imbalanced computational workloads among various edge servers, leading to significant computation latency. To solve this problem, a task migration algorithm based on modified deep deterministic policy gradient (MDDPG) is proposed. The algorithm has a mechanism of priority empirical replay and random weight averaging based on depth deterministic strategy gradient to find the best migration strategy and reduce the computation delay of the task. Experimental results show that MDDPG algorithm has a better performance than the traditional algorithms.

    Figures and Tables | References | Related Articles | Metrics
    Transformer-based Multi-scale Underwater Image Enhancement Network
    Ai-ping YANG, Si-jie FANG, Ming-fu SHAO, Teng-fei ZHANG
    2024, 45 (12):  1696-1705.  DOI: 10.12068/j.issn.1005-3026.2024.12.004
    Abstract ( 277 )   HTML ( 3)   PDF (2486KB) ( 31 )  

    CNN(convolutional neural network)‑based underwater image enhancement methods neglect global visual perception, leading to color distortion and contrast degradation.

    A Transformer‑based multi‑scale underwater image enhancement network (MTransNet) is proposed. To address the problem of lacking global visual perception, a position encoding module is designed based on underwater image priors and a Swin Transformer module which is applicable to underwater scenes is constructed. Furthermore, self‑attention mechanism is built to improve global perception performance. As for the detail blurring that exists in current methods, a CNN module is developed to capture local features such as textures or edges, to improve local perception performance. The transfer fusion module is built to transfer global attention of Swin Transformer to local convolutional feature, achieving full fusion and utilization of global feature and local feature. The PSNR value on subsets of EUVP can reach up to 23.47 dB, which demonstrates the method can significantly enhance global visual perception and increase image visual quality.

    Figures and Tables | References | Related Articles | Metrics
    Unsupervised Feature Selection Based on Sparse Self-representation with Manifold Regularization
    Jie LIU, Wen-jing TAN, Zhan-shan LI
    2024, 45 (12):  1706-1716.  DOI: 10.12068/j.issn.1005-3026.2024.12.005
    Abstract ( 202 )   HTML ( 1)   PDF (7989KB) ( 34 )  

    Self‑representation based unsupervised feature selection can handle unlabeled data without being affected by pseudo‑labeling. To ensure that such methods simultaneously achieve good robustness, preserve the local structure of samples, and select the most representative features, a new approach is proposed, and a corresponding iterative optimization algorithm is designed to compute its objective function. The method first identifies and processes outliers of samples, then combines the traditional self‑representation model with non‑convex sparse constraint and manifold regularization to form the target model, and puts the preprocessed data into the model for feature selection. Finally, the method uses the selected features for clustering. The proposed method is compared with seven methods on nine real data sets for experiments, and the experimental results show that the proposed method can effectively solve the unsupervised feature selection problem.

    Figures and Tables | References | Related Articles | Metrics
    Robust Secure Communication Method for Intelligent Reflecting Surface-Assisted Cognitive UAV Network
    An LI, Tao GUO, Hao LI, Sheng HONG
    2024, 45 (12):  1717-1725.  DOI: 10.12068/j.issn.1005-3026.2024.12.006
    Abstract ( 268 )   HTML ( 2)   PDF (974KB) ( 24 )  

    To address the problem that it is difficult for the secondary unmanned aerial vehicle (UAV) to acquire the accurate channel state information (CSI) of the eavesdropping channel in UAV cognitive radio systems, which reduces the security performance of the secondary system, this paper proposes a robust method to enhance the security transmit performance of the secondary user (SU) by using intelligent reflecting surface (IRS) to assist UAV cognitive communication. Under the constraints of the interference temperature of the primary user (PU), a deterministic model is established to describe the uncertainty of the CSI of the eavesdropping channel, and the phase shift matrix of IRS, the flight trajectory and transmit power of the UAV are jointly optimized to maximize the average worst‑case secrecy rate of the SU. To tackle the non‑convexity of the formulated optimization problem, an effective three‑stage iterative algorithm is presented based on alternating optimization, successive convex approximation, S-Procedure, and semi‑definite relaxation methods. The simulation results show that compared to non‑robust scheme, the proposed robust scheme can significantly improve the secure performance of the SU.

    Figures and Tables | References | Related Articles | Metrics
    Mechanical Engineering
    3-D Surface Morphology Detection Method Based on Motion Error
    Guan-yao QIAO, Jia-yi XU, Chun-yu ZHAO
    2024, 45 (12):  1726-1733.  DOI: 10.12068/j.issn.1005-3026.2024.12.007
    Abstract ( 299 )   HTML ( 1)   PDF (2337KB) ( 25 )  

    The spindle motion error will reduce the quality of the machined surface and the dynamic accuracy of the machined profile. A 3-D surface morphology detection method for turning workpieces based on motion error was proposed after analyzing and studying the spindle motion error of the CNC lathe. The simulation results showed that the detection method has high calculation accuracy in solving spindle rotation error and workpiece surface profile and can separate the workpiece surface profile from spindle radial runout error and tilt swing error. In order to verify the reliability of the detection method, a 3-D surface topography detection platform was built to collect experimental data, and then the workpiece surface topography data and the motion error of the CNC lathe spindle were obtained by a separation algorithm. Finally, the effect of asynchronous error and sensor error on the results of surface morphology inspection of the artifacts in the experiment were analyzed.

    Figures and Tables | References | Related Articles | Metrics
    Experimental Study on the Micro-scale Grinding Force of High-Entropy Alloys
    Xue-long WEN, Hong-ze GUI, Ya-dong GONG, Meng-shan WANG
    2024, 45 (12):  1734-1743.  DOI: 10.12068/j.issn.1005-3026.2024.12.008
    Abstract ( 206 )   HTML ( 0)   PDF (3760KB) ( 24 )  

    By analyzing the formation mechanism of grinding chips, a theoretical model of micro‑grinding force of high‑entropy alloys was established, and the formula of grinding force was derived. Through orthogonal and single‑factor experiments, the influencing laws of grinding parameters, particle sizes and surface coating of micro‑grinding tools on the grinding force were explored, as well as the grinding force comparison of different high‑entropy alloys. The effects of grain size, processing parameters and grinding force on the morphology of grinding chips were analyzed. The results showed that the feed speed has the greatest effect on grinding force and the least effect on grinding depth. With the increase of feed speed and grinding depth, the grinding force gradually increases, and the grinding force gradually decreases with the increase of grinding speed. The micro‑grinding force of the 500# abrasive particle is larger, and the grinding chips produced are bar spacing sawteeth. The tangential grinding force of the coated microabrades is smaller than that of the uncoated microabrades, while the normal grinding force is larger. The increase of Al content and the addition of Mo element will lead to the increase of the micro‑grinding force. Finally, the calculated values of the theoretical model were compared with the experimental values, and the accuracy of the micro‑grinding force model was verified.

    Figures and Tables | References | Related Articles | Metrics
    Reliability Sensitivity Analysis of Pressure Fluctuations for Direct-Acting Relief Valves
    Cong-yi ZHA, Zhi-li SUN, Qin LIU, Peng-fei DONG
    2024, 45 (12):  1744-1750.  DOI: 10.12068/j.issn.1005-3026.2024.12.009
    Abstract ( 182 )   HTML ( 0)   PDF (1158KB) ( 26 )  

    Hydraulic equipment commonly is operated under complex conditions, characterized by adverse factors such as intense vibration and impact. These factors, combined with the uncertainty of structural parameters, can easily lead to pressure fluctuations in relief valves, potentially resulting in equipment failure. To address this issue, a reliability analysis model for the pressure fluctuation failure of direct‑acting relief valves is presented, considering the influence of environmental vibration and uncertainty factors. A dynamic model for the relief valve under environmental vibration is developed, and then its corresponding dynamic characteristics are analyzed. Moreover, based on the dynamic characteristics analysis of the relief valve and the released value of the national standard, a limit‑state function for pressure fluctuation failure is established. Furthermore, the reliability sensitivity analysis is performed using the Kriging model to evaluate the contribution of each parameter to the occurrence of pressure fluctuation failure. The results indicate that the vibration frequency has the most significant impact on reliability, followed by the spool mass and vibration amplitude, while the controlled chamber volume and sensitive chamber volume show a minimal contribution. The research results can provide a theoretical basis for regulating the pressure fluctuation failure of relief valves under environmental vibration.

    Figures and Tables | References | Related Articles | Metrics
    Analysis of Fatigue Life of Slewing Bearings Considering Size Effect
    Zhong LUO, Yao-jia YANG, Si-jia ZHENG, Ji-lai ZHOU
    2024, 45 (12):  1751-1758.  DOI: 10.12068/j.issn.1005-3026.2024.12.010
    Abstract ( 195 )   HTML ( 0)   PDF (1181KB) ( 18 )  

    Aiming at the problem of size effect in the process of fatigue life analysis of slewing bearings, the fatigue life analysis of slewing bearings is carried out and the influencing law of size effect is studied in depth. By establishing the contact load calculation model and determining the contact force distribution, combined with the Lundberg-Palmgren theory, the fatigue life of slewing bearings with different sizes is calculated. The coupling relationship between ball number and diameter, the influence of raceway center circle diameter and other parameters on the fatigue life of slewing bearings are analyzed, and the size effect of slewing bearings on the fatigue life is discussed, which provides reference for the design and selection of slewing bearings. The results show that reducing the groove curvature coefficient, increasing the contact angle and the raceway center circle diameter can increase the service life of slewing bearings. The influence of ball diameter change on the service life of slewing bearings is greater than that of the change of the raceway center circle diameter, and the increase of contact angle will enhance the size effect, while the increase of groove curvature coefficient will weaken the effect.

    Figures and Tables | References | Related Articles | Metrics
    Resources & Civil Engineering
    Analytical Solution of Surrounding Rock Stress and Displacement in Bidirectional Unequal Pressure Stope Under Supporting Stress
    Zhi-peng XIONG, Yuan-hui LI, Kun-meng LI, Gui-xuan XIAO
    2024, 45 (12):  1759-1768.  DOI: 10.12068/j.issn.1005-3026.2024.12.011
    Abstract ( 443 )   HTML ( 2)   PDF (1644KB) ( 30 )  

    The stability of inclined rectangular stope is closely related to the stress and displacement distribution of stope roof in underground mines. However, the current theoretical method for stress and displacement of surrounding rock in rectangular excavation has a significant error when applied to inclined rectangular stopes with large width‑height ratio, and the influence of excavation dip angle and supporting stress is not considered. Based on the complex function theory, this paper puts forward the mapping function expression of inclined rectangular stope with large width‑height ratio, and derives the analytical solution of stress and displacement of surrounding rock in stope under bidirectional unequal pressure and supporting stress. Besides, the influence of stope dip angle, width‑height ratio and supporting stress on stress and displacement distribution of stope roof is analyzed. The results show that the deviation between analytical solution and FLAC simulation solution is less than 5%. In addition, the asymmetric distribution trend of stress and displacement around stope roof intensifies as the stope dip angle increases, and the degree of pressure relief and vertical displacement gradually decreases. With the increase of stope width‑height ratio, the pressure relief degree and the displacement of stope roof gradually increase. The supporting stress exerted by supporting bodies can improve the stress environment of surrounding rock and reduce the roof subsidence.

    Figures and Tables | References | Related Articles | Metrics
    Prediction of Soil Conditioners for Sandy Soil Shield Based on Optuna-XGBoost
    Xiu-mei CAO, Wen ZHAO, Zhi-guo WANG, Peng HE
    2024, 45 (12):  1769-1777.  DOI: 10.12068/j.issn.1005-3026.2024.12.012
    Abstract ( 158 )   HTML ( 1)   PDF (1779KB) ( 33 )  

    Soil conditioning is an effective measure to solve the problems in the construction process of earth pressure balance (EPB) shield, such as cutter clogging and cutter abrasions. The use of machine learning models to predict soil conditioners varying with geological conditions can not only reduce the aforementioned construction risks, but also make up for the lag in determining the amount of modifier by test method. Based on the shield project of Shenyang Metro Line 4, the excavation data of 1 396 ring are preprocessed, and torque penetration index (TPI) and field penetration index (FPI) are used as the criteria for the soil conditioning effect to select good datasets. The Optuna-XGBoost model is established to predict the soil conditioners. The results show that Optuna algorithm owns obvious advantages over other methods in hyperparameters optimization. Compared with the other five prediction models, Optuna-XGBoost model owns higher accuracy under changeable geological conditions.

    Figures and Tables | References | Related Articles | Metrics
    Analytical Solution for Steady-State Seepage in Pits During Water Stop Curtain Leakage
    Jun YU, Wei-jie ZHANG, Dong-kai LI
    2024, 45 (12):  1778-1786.  DOI: 10.12068/j.issn.1005-3026.2024.12.013
    Abstract ( 260 )   HTML ( 2)   PDF (1398KB) ( 14 )  

    To study the two‑dimensional steady‑state seepage in a pit with isotropic soil during water stop curtain leakage, half the pit’s cross‑section is analyzed due to symmetry. The soil around the water curtain is divided into five regions, and the head distribution is solved using superposition and separation of variables, leading to an explicit analytical solution for the seepage field, considering continuity between regions. Results for head, water pressure, and seepage flow volume at leakage are compared with that of finite element software and references, confirming the analytical solution’s accuracy and efficiency. Parameter analysis shows that vertical leakage crack location and width have minimal impact on head and pressure but significantly affect seepage flow volume.

    Figures and Tables | References | Related Articles | Metrics
    Seismic Behavior Analysis of Single Side Bolt Joint of CFST Column-Composite Beam Under High Axial Compression
    Fa-xing DING, Kai-yuan LUO, Jian-xiong LEI, Fei LYU
    2024, 45 (12):  1787-1797.  DOI: 10.12068/j.issn.1005-3026.2024.12.014
    Abstract ( 258 )   HTML ( 0)   PDF (3314KB) ( 38 )  

    A three‑dimensional solid finite element model is used to analyze the seismic performance of 9 CFST(concrete‑filled steel tubular) column-composite beam single side bolt joints. The concrete triaxial plastic‑damage and steel mixed reinforcing‑toughness damage models are used to discuss the effects of tensile reinforcement, axial compression ratio, beam height and stiffener on the seismic performance and failure forms of the joints. The results show that the finite element model of steel with ductile damage is more consistent with the test results, and the increases of the end plate stiffener and the steel beam height can greatly improve the joint stiffness, bearing capacity and energy dissipation capacity. Then, the effects of different steel beam sizes and reinforcement structures on the bearing capacity, stiffness and plastic energy dissipation distribution and failure mechanism of concrete‑filled steel tubular column-composite beam unilateral bolted joints are investigated. The analysis results show that the tensile reinforcement greatly improves the flexural bearing capacity and energy dissipation capacity of the column end, making the joint maintain the failure mode of the beam end when the axial compression ratio is 0.8. When the joint beam‑column bending capacity ratio is between 1.57 and 2.04, the beam energy dissipation will change to column energy dissipation. Therefore, according to the definition of strong column and weak beam, it is suggested to raise the ratio of beam to column flexural bearing capacity from 1.0 to 1.5 for this kind of joint.

    Figures and Tables | References | Related Articles | Metrics
    Experimental Study on the Characteristics of Bicarbonate Inhibiting Soybean Meal Dust Explosion
    Jia-ling XU, Kai-li XU, Bo LIU
    2024, 45 (12):  1798-1804.  DOI: 10.12068/j.issn.1005-3026.2024.12.015
    Abstract ( 239 )   HTML ( 2)   PDF (4737KB) ( 28 )  

    To investigate the explosion suppression characteristics of bicarbonate on soybean meal dust explosion, NaHCO3, KHCO3, and NH4HCO3 bicarbonate were selected as explosion suppression powders. The inhibitory effect of bicarbonate on soybean meal dust explosion was analyzed from parameters such as maximum explosion pressure Pex, maximum explosion pressure rise rate (dP/dtex, and explosion index Kst. The results showed that the explosion characteristic parameters of soybean meal dust with a mass concentration of 400 g/m³ were the highest, with a maximum explosion pressure of 0.763 MPa, a maximum explosion pressure rise rate of 24.8 MPa/s, and an explosion index of 6.7 MPa·m/s. As the mass fraction of bicarbonate powder increased, the explosion characteristic parameters showed a decreasing trend, and the inhibitory effect continued to increase. Under the same conditions, the explosion suppression performance of NH4HCO3>KHCO3>NaHCO3. Combined with thermogravimetric analysis and infrared spectroscopy analysis of explosion suppression powders, the explosion suppression mechanisms of three types of powders and the differences caused by different ions were explored.

    Figures and Tables | References | Related Articles | Metrics