Loading...

Archive

    For Selected: Toggle Thumbnails
    Information & Control
    Research on Positioning of Unmanned Carrier-Based Aircraft Based on Multi-sensor Fusion in Ship’s Surface Environment
    Peng-shuai HOU, Da-peng ZHOU, Da-peng YANG, Jie CHEN
    2024, 45 (1):  1-9.  DOI: 10.12068/j.issn.1005-3026.2024.01.001
    Abstract ( 889 )   HTML ( 182)   PDF (5782KB) ( 590 )  

    The autonomous positioning of unmanned carrier-based aircraft on the aircraft carrier is an important prerequisite for realizing autonomous transfer and improving the efficiency of entry/exit. Among them, how to rely on airborne sensing equipment to realize autonomous positioning in the ship’s surface environment of carrier-based aircraft in GPS-denied environment is the key technology that needs to be solved urgently. Therefore, an autonomous positioning algorithm is proposed for unmanned carrier-based aircraft based on visual and lider fusion. The algorithm performs multi-sensor online calibration by combining the hand-eye calibration and mutual information calibration methods, so that the unmanned carrier-based aircraft can still run stably after the fuselage shakes in the face of wind and waves and the operation of the aircraft carrier causes the sensor external parameter calibration results to change. A factor graph is introduced for multi-sensor pose joint optimization of unmanned carrier-borne aircraft, and a simple and efficient sensor failure criterion is established based on the motion model in the process of autonomous transport, so as to integrate the lidar and visual positioning results effectively so that the algorithm can operate stably even when a single sensor fails. Finally, a multi-sensor-based simulation system of carrier-based aircraft on the ship is established to verify the algorithm. Experimental results show that the positioning error of the algorithm remains within 0.2 m when a single sensor fails, which meets the requirements of practical applications.

    Figures and Tables | References | Related Articles | Metrics
    A Social Recommendation Algorithm Based on Graph Neural Network
    Yan-xia LYU, Shuai HAO, Guang-tong QIAO, Ye XING
    2024, 45 (1):  10-17.  DOI: 10.12068/j.issn.1005-3026.2024.01.002
    Abstract ( 593 )   HTML ( 53)   PDF (1271KB) ( 357 )  

    Most existing social recommendation algorithms focus on the user’s single interaction such as purchase or click, but do not consider different interactions such as collection and browsing simultaneously. Moreover, current social recommendation algorithms only focus on the accuracy of recommendation, ignoring the interpretability of recommendation results. To solve the above problems, a social recommendation algorithm SRGN is proposed based on graph neural network, which injects the social relationships of users and the objectively existing semantic connections between items into the algorithm architecture in a specific way, and jointly encodes the interactive multi-behavior through message transmission, so as to improve the accuracy of recommendation. In addition, an explainable module is designed to provide reasons for the recommendation results. Compared with other eight algorithms on two real datasets, the results show that the proposed algorithm has obvious advantages in recommendation performance and user friendliness.

    Figures and Tables | References | Related Articles | Metrics
    MMCSC: A Cross-Modal Approach to Fake News Detection
    Yue ZHAO, Kun HAO, Jing ZHAO, Jun-chang XIN
    2024, 45 (1):  18-25.  DOI: 10.12068/j.issn.1005-3026.2024.01.003
    Abstract ( 471 )   HTML ( 38)   PDF (947KB) ( 240 )  

    Current fake news detection methods based on news content do not take into account the higher-level semantic correlation of different modalities, and lack information that can be used to judge news, thus lacking effective use of social network information for news with important distinguishing features. Address to this problem, a fake news detection method based on news content is proposed. By extracting high-level semantic features of multi-modal news such as text, images and videos, the high-level semantic information of different modalities is analyzed, and the cross-modal topic consistency and cross-modal emotional consistency are designed. On this basis, a fake news detection model MMCSC (multi-modal feature content semantic consistency) is designed with cross-modal content semantic consistency. Experiments show that the proposed MMCSC has better detection effect than the traditional method.

    Figures and Tables | References | Related Articles | Metrics
    Gait Recognition Based on Key Point Motion Trajectory Modeling
    Jiu-qiang XU, Xiao-xiao ZHAO, Long-fei QIAN
    2024, 45 (1):  33-39.  DOI: 10.12068/j.issn.1005-3026.2024.01.005
    Abstract ( 609 )   HTML ( 29)   PDF (1264KB) ( 212 )  

    Gait information is a new biological characteristic with wide application prospects in medical and forensic fields, making it a hot spot in current research. Although researchers have proposed a variety of gait recognition methods, there are still some problems such as poor adaptability, overly complex feature description, and lack of interpretability. To solve this problem, firstly, the three-frame difference algorithm is improved to extract the human contour from video images. Then, a central structure model of human body is established based on the human body contour diagram, allowing for the identification of key points and the modeling of trajectory curves based on their locations in the video. Finally, a new gait feature description method is proposed using the previous curve model, with appropriate model parameters selected as gait feature vectors and suitable classification methods chosen for gait recognition and classification. Experimental results show that the proposed gait feature expression based on the trajectory model of key points can describe human gait information well and the recognition rate is relatively high.

    Figures and Tables | References | Related Articles | Metrics
    Speech Emotion Recognition Fusing Functional Paralanguage Proportion Coefficient
    Ying SUN, Ya-ru ZHOU, Xue-ying ZHANG
    2024, 45 (1):  40-48.  DOI: 10.12068/j.issn.1005-3026.2024.01.006
    Abstract ( 566 )   HTML ( 27)   PDF (1610KB) ( 151 )  

    Nonverbal vocalizations such as laughter, sighs, and sobs in speech are called functional paralanguage and play an important role in emotional expression. However, existing research has rarely considered the synergistic effect of multiple functional paralanguages in a single emotion. To address this issue, an emotion recognition system integrating functional paralanguage proportion coefficients (FPPC) is proposed. Firstly, FPPC features that reflect the frequency and duration of multiple functional paralanguages appearing in emotional statements are extracted. Then, an attention mechanism-based ensemble learning is constructed to assign different weights to different base classifiers and train the FPPC features. Finally, the adaptive entropy weight decision fusion method is used to fuse traditional speech emotion recognition with emotion recognition based on FPPC features. Experimental results show a 16.84% improvement in emotion recognition after integrating FPPC features, proving that integrating FPPC features can effectively improve the overall recognition rate of the system.

    Figures and Tables | References | Related Articles | Metrics
    Research on the Utilization of Mean Value Information in Optimization Algorithm
    Fang WANG, Peng WANG, Yu-wei JIAO
    2024, 45 (1):  49-57.  DOI: 10.12068/j.issn.1005-3026.2024.01.007
    Abstract ( 475 )   HTML ( 21)   PDF (1458KB) ( 79 )  

    The strategy of population migration towards the mean point in heuristic optimization algorithms is investigated, and the strategy is found that it has significant impact on the algorithm’s performance and has both physical and mathematical implications. By using the maximum likelihood estimation method, the parameters of the ground state wave function are estimated, and the connection between the probability density function of the optimal solution when the quantum system reaches the ground state and the population mean point is established. The physical significance of the population mean point is explained from a dynamic perspective. The operations that utilize the information of the mean point’s position is added to several classical optimization algorithms and a comparative experiment is carried out on the CEC2013 test set and the engineering application of camera layout optimization. Experimental results show that reasonable use of the mean point position information can effectively improve the performance of the algorithm.

    Figures and Tables | References | Related Articles | Metrics
    Research on the AGV Scheduling Problem in the No-buffer Assembly Line
    Xing-kai WANG, Wei-min WU, Zi-chao XING, Hao-yi NIU
    2024, 45 (1):  58-67.  DOI: 10.12068/j.issn.1005-3026.2024.01.008
    Abstract ( 462 )   HTML ( 23)   PDF (2636KB) ( 157 )  

    To solve the AGV(automated guided vehicle) scheduling problem in the no-buffer assembly line, a heuristic scheduling algorithm base on composite score is proposed, reducing the waiting time of AGVs when execute tasks in the system. Firstly, the classical AGV fleet size determination algorithm based on the mathematical model is improved. Then, an improved tabu search-based AGV look-ahead scheduling algorithm (LSA) is proposed, which has a composite score strategy. Different from the most reported algorithms, LSA takes parts delay time, AGV empty travel distance and other objects into account. Finally, the proposed algorithms are compared with other reported algorithms. The simulation experiments prove that LSA has better performance than other algorithms. The robotic experiments prove that the proposed algorithm works well in actual production scenarios.

    Figures and Tables | References | Related Articles | Metrics
    Mechanical Engineering
    Effect of Transverse Load and Preload on the Fracture Life of Bolts
    Xing-lin MIAO, Xian-zhen HUANG, Peng-fei DING, Zhi-qun ZHENG
    2024, 45 (1):  68-75.  DOI: 10.12068/j.issn.1005-3026.2024.01.009
    Abstract ( 725 )   HTML ( 26)   PDF (1938KB) ( 249 )  

    Bolted joints are widely used in various industries for their simplicity and reliability, but the fatigue fracture of bolts is still a very prominent problem. Therefore, to accurately predict the bolt fracture failure life, the fatigue crack propagation experiments of bolt materials are conducted to obtain the fracture parameters of bolt materials, so that the Paris model can be established. Then the finite element method is applied with fatigue crack propagation experiments for calibration and achieves better results, which provides a basis for the calculation of the bolt fracture failure life. Finally, considering the influence of bolt pretension and transverse load on bolt fractures, a cracked bolt finite element model is established and the bolt failure life is quantitatively analyzed by the finite element method. The results show that the transverse load and bolt preload have a large effect on the stress intensity factor and bolt life.

    Figures and Tables | References | Related Articles | Metrics
    Finite Element Analysis of Thermal Deformation of Worm Gears’ Meta-action in Numerical Control Turntables
    Xin YANG, Zhen-gang FAN, Gen-bao ZHANG, Yan RAN
    2024, 45 (1):  76-84.  DOI: 10.12068/j.issn.1005-3026.2024.01.010
    Abstract ( 500 )   HTML ( 26)   PDF (3629KB) ( 153 )  

    In order to study the thermal error modeling method of the transmission system meta-action in numerical control turntable. Firstly, the meta-action theory and the temperature field model assumptions and boundary condition of finite element simulation are introduced. Then, the mechanism of the friction temperature field simulation and the parameter calculation method of the ANSYS simulation are analyzed the rotation meta-action is numerically simulated from the two aspects of steady state and transient state, and the temperature rising curve of key meta-action is given. The temperature distribution and temperature rising and thermal deformation are obtained by coupling the temperature field and deformation field of meta-action transient state, steady state and thermal-structure. The thermal error model of the transmission system is obtained by the theoretical calculation and finite element analysis of thermal deformation.

    Figures and Tables | References | Related Articles | Metrics
    Research and Optimization of Multi-axis Linkage Interpolation Algorithm for 3D Printer
    Fei WU, Meng-hui WANG, Yi-neng LI
    2024, 45 (1):  85-92.  DOI: 10.12068/j.issn.1005-3026.2024.01.011
    Abstract ( 504 )   HTML ( 20)   PDF (1494KB) ( 171 )  

    Aiming at the problem of low computational efficiency of printer multi-axis linkage interpolation algorithm in 3D printing process, the shortcomings of Bresenham algorithm in 3D printing motion control are analyzed. Step Bresenham algorithm and velocity adaptive algorithm are proposed on the basis of existing algorithms to complete the nozzle forming scanning motion and slurry extrusion motion respectively. The multi-axis linkage of 3D printer is controlled by combining the two algorithms to improve the interpolation speed of 3D printer. At the same time, the implementation flow of the control method in microcontrollers is analyzed, and it is then transplanted into microcontroller. Linear interpolation simulation experiments and 3D printing experiments with different algorithms are designed which prove that the control method can improve the printing efficiency on the premise of constant printing accuracy.

    Figures and Tables | References | Related Articles | Metrics
    Resources & Civil Engineering
    Effect of Acid Etching on the Floatability of Dolomite and Its Mechanism of Action
    Jun GUO, Wan-zhong YIN, Bin YANG, Zhang-lei ZHU
    2024, 45 (1):  93-100.  DOI: 10.12068/j.issn.1005-3026.2024.01.012
    Abstract ( 430 )   HTML ( 26)   PDF (2226KB) ( 107 )  

    The effect of acid etching on the floatability of dolomite and its mechanism of action were investigated by flotation tests, flotation kinetic fitting, surface roughness characterization, specific surface area analysis, XPS analysis, adsorption performance analysis and wettability analysis under sodium oleate system. The research results showed that acid etching increased the surface roughness and specific surface area of dolomite, exposing more active sites, strengthened the adsorption sodium oleate, enhanced the hydrophobic of dolomite, and thus improved the performance of dolomite. Moreover, regarding flotation kinetic fitting, the classical first-order model, first-order model with rectangular distribution of floatability, and the second-order kinetic model all displayed the R2 values higher than 95%. Compare with other models, the classical first-order model exhibited the best fit. At a sodium oleate mass concentration of 60 mg/L, the k value of classical first-order for dolomite reached a maximum value of 1.88 min-1. However, in this case, before acid etching, the k value of classical first-order model for dolomite was only 1.15 min-1. These results further confirmed that acid etching could improve the flotation rate of dolomite. In summary, this study can provide a new research perspective for dolomite flotation, with a certain theoretical and practical significance.

    Figures and Tables | References | Related Articles | Metrics
    Intelligent Identification and Parameter Extraction of Key Joints in Rock (Mass) Based on AttentionR2U-net
    Hao SUN, Zong-sheng DAI, Ai-bing JIN, Yan CHEN
    2024, 45 (1):  101-110.  DOI: 10.12068/j.issn.1005-3026.2024.01.013
    Abstract ( 439 )   HTML ( 25)   PDF (2319KB) ( 106 )  

    Aiming at the problem of intelligent identification and parameter extraction of key joints in complex joint networks on surfaces of rock (mass), a method based on AttentionR2U-net network and joint geometric feature model is proposed. The attention gate was introduced on the basis of R2U-net network to improve the network, and then the accuracy test and generalization ability study of the recognition results of slope joint images and fracture images in concrete, cracked soil and common brittle rocks were carried out by qualitative and quantitative methods. Finally, the AttentionR2U-net network was used to identify the key joints by coupling the geometric features of the joints. The geometric parameters of the original and key joints are extracted, and then the trace length, area and inclination angle are analyzed. The results show that for joint identification of rock (mass), the Dice similarity coefficient of the proposed algorithm is increased from 0.965 to 0.990 in U-net network, outperforming the traditional algorithm significantly. Therefore, the proposed algorithm has stronger reliability and superiority in joint identification of rock (mass). For crack identification in concrete, cracked soil and brittle rocks such as marble, granite and sandstone, the similarity coefficientDice of the proposed algorithm is above 0.953, so the proposed algorithm has strong generalization ability. Compared with the original joint network, the dominant trace length of the key joint network increased significantly from 0.732 m to 1.835 m, the distribution pattern of joint dip angle and the dominant dip angle group remained unchanged, and the proportion of joints with dominant trace length and dip angle increased significantly.

    Figures and Tables | References | Related Articles | Metrics
    Dynamic Splitting Characteristics of Freeze-Thawed Sandstone at Different Loading Rates
    Peng JIA, Song-ze MAO, Yi-jin QIAN, Jia-liang LU
    2024, 45 (1):  111-119.  DOI: 10.12068/j.issn.1005-3026.2024.01.014
    Abstract ( 403 )   HTML ( 23)   PDF (2975KB) ( 163 )  

    In order to study the effects of loading rate and freeze-thaw cycles on the dynamic splitting characteristics of sandstone,static and dynamic splitting tests with different loading rates were conducted on sandstone subjected to 0, 25, 50, 75 and 100 freeze-thaw cycles,and the static and dynamic tensile strength of freeze-thaw sandstone,as well as the change law of dissipation energy under impact load were discussed.The results show that the static and dynamic tensile strength,the P-wave velocity and the mass loss rate of freeze-thaw sandstone deteriorate with an increase in the number of freeze-thaws cycles.The dynamic strength increase factor(DIF)increases with the increase of freeze-thaw cycles and loading rate,and a higher degree of the freeze-thawing damage in sandstone results in a more significant increase in DIF with loading rate.The dynamic tensile strength prediction model based on freeze-thaw damage and loading rate can reflect the strength change of sandstone effectively.The greater the freeze-thaw damage of sandstone,the faster the change of dynamic tensile strength with loading rate.The dissipation energy under impact load decreases with the increase of freeze-thaw cycles and increases with higher loading rate.

    Figures and Tables | References | Related Articles | Metrics
    Critical Slip Surface Search for Pile-Anchor Supported Deep Foundation Pits Based on Hybrid Fruit Fly Algorithm
    Ze-ning MA, Cheng-man SHA, Ming-hao LU
    2024, 45 (1):  120-128.  DOI: 10.12068/j.issn.1005-3026.2024.01.015
    Abstract ( 388 )   HTML ( 18)   PDF (1666KB) ( 66 )  

    The limit equilibrium method is used for the overall stability analysis of the pit,requiring iterative calculation of various potential slip surfaces.The slip surface with the smallest safety factor is identified as the most dangerous slip surface.The fruit fly optimization algorithm (FOA) with the tabu search (TS) algorithm is fused,and the hybrid fruit fly optimization algorithm (HFOA) with adaptive step size is proposed to overcome the limitations of the fruit fly optimization algorithm,such as lower accuracy and susceptibility to local optimum.In order to ensure that the global optimal solution is obtained,the simplified Bishop algorithm for the search of critical slip surfaces is combined.By comparing with the six heuristic algorithms,it is shown that the HFOA is applicable to cantilever-supported pits with homogeneous soil,layered soil and pile-anchored supported pits with soft soil.It is more accurate and efficient compared with the six algorithms such as genetic algorithm,and provides a new solution strategy for identifying critical sliding surface in deep foundation pits.

    Figures and Tables | References | Related Articles | Metrics
    Study on Deformation Response Caused by Large-Section Excavation Under the Support of Pipe-Roof and Beam
    Qian BAI, Wen ZHAO, Wen-xin CAO, Yan-jun LU
    2024, 45 (1):  129-136.  DOI: 10.12068/j.issn.1005-3026.2024.01.016
    Abstract ( 419 )   HTML ( 17)   PDF (1442KB) ( 74 )  

    Based on the similar model test of large-section excavation under the action of pipe-roof and beam,the variation law of pipe-roof deformation and surface settlement caused by excavation was studied. In order to fully study the influence of parameter changes on the pipe-roof deformation and surface settlement,a three-dimensional numerical model was established by using the finite element software. Based on this model,the effects of the flexural stiffness of the pipe-roof and the beam on the pipe-roof deformation and surface settlement were analyzed,and the optimal stiffness matching was studied according to the fuzzy mathematical theory. The results indicate that the overall deformation of the pipe-roof structure resembles a “plate”and exhibits symmetry about the middle pipe-roof. The surface settlement of the cross section of the pipe-roof forms a “grooved”pattern,conforming to the Peck curve distribution. The pipe-roof deformation and surface settlement are exponential functions of the beam stiffness and the pipe-roof stiffness,with greater sensitivity to changes in the beam stiffness. The safety and economy can be taken into account when the beam stiffness and the pipe-roof stiffness are 0.5D and 2K respectively.

    Figures and Tables | References | Related Articles | Metrics
    Evaluation and Optimization of Development Efficiency of State-Owned Construction Enterprises
    Xi-jing QI, Sheng-jin ZHANG, Meng-xing ZHANG
    2024, 45 (1):  137-144.  DOI: 10.12068/j.issn.1005-3026.2024.01.017
    Abstract ( 474 )   HTML ( 19)   PDF (1471KB) ( 76 )  

    To assist the high-quality development of state-owned construction enterprises and improve the development efficiency of enterprise and industry,the current development status of the construction industry was analyzed to recognize the trend of industry transformation and upgrading,and the concept of development efficiency of state-owned construction enterprises was defined. The static and dynamic development efficiency of different ownership construction enterprises and regional state-owned construction enterprises was assessed by using the super SBM-Malmquist model. The results show that the overall development efficiency of construction enterprises is relatively effective in 2012-2020,but shows a declining trend,primarily due to constraints in technological innovation and progress.The development efficiency of state-owned construction enterprises is relatively effective and rising,and is positively related to the comprehensive development level of the region. By analyzing the identified problems and conclusions during the research process,suggestions are proposed to optimize the development efficiency of state-owned construction enterprises from both policy and enterprise perspectives.

    Figures and Tables | References | Related Articles | Metrics
    Management Science
    Quality Measurement Based on Expected Earnings Growth and Pricing Power
    Yue-li LIU, Xiu JIN, Jin-ming YU
    2024, 45 (1):  145-152.  DOI: 10.12068/j.issn.1005-3026.2024.01.018
    Abstract ( 471 )   HTML ( 24)   PDF (668KB) ( 108 )  

    From the perspective of quality premium drivers, a quality indicator based on expected earnings growth (EEG) is constructed. The relationship between the indicator and expected stock return is analyzed. Then, an EEG quality factor is constructed and incorporated into the Fama-French three-factor model for the purpose of studying the pricing power of this factor. The results show that the EEG quality indicator can measure a company’s expected earnings growth. There is a significantly positive correlation between the EEG quality indicator and expected stock returns, reflecting the significant presence of the EEG quality premium. The EEG quality factor has a strong explanatory power for cross-sectional portfolio returns. The four-factor model that introduces the EEG quality factor has higher pricing efficiency than the Fama-French class model, which may enrich the theories related to asset pricing and provide valuable references for investors to make rational decisions, and regulators to cultivate good investment philosophy and improve market pricing efficiency.

    Figures and Tables | References | Related Articles | Metrics