Archive

18 May 2022, Volume 43 Issue 3 Previous Issue    Next Issue
---
Information & Control
Mechanical Engineering
Resources & Civil Engineering
Management Science


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Information & Control

Select

Recognition Method of Arrhythmia Based on Variable Weight Singular Spectrum Analysis LI Hong-ru， REN Zi-yang， HUANG You-he， YU Xia 2022, 43 (3):  305-312.  DOI: 10.12068/j.issn.1005-3026.2022.03.001 Abstract ( 699 )   HTML ( 17)   PDF (1535KB) ( 214 )   Many existing arrhythmia researches focus on the separation of different frequency characteristic components in the ECG signal. However， the contribution of different subsequences to the final target decision-making is lack of research and analysis. In order to enhance the impact of high-contribution subsequences on the classifier， a recognition method combining variable weight singular spectrum analysis and deep learning is proposed. Multiple subsequences are obtained through singular spectrum analysis.The Gini coefficient under the random forest is calculated by the singular value of each sequence and used as the weight. The sequence samples with variable weights are used to train the neural network model， which can mine useful information more efficiently and further improve the recognition accuracy. The accuracy rate of final arrhythmia recognition is 98.35%， and Macro-F1 is 97.95%. Compared with the traditional fixed weight， the proposed recognition method of variable weight has a significant improvement in various performance indicators. References | Related Articles | Metrics

Select

Actuator Fault Reconstruction of Vehicle Electronic Stability Control System Based on Observer WANG Hong-wei， WANG Qian-yu， HAN Jie， ZHANG Hao-tian 2022, 43 (3):  313-320.  DOI: 10.12068/j.issn.1005-3026.2022.03.002 Abstract ( 415 )   HTML ( 5)   PDF (1472KB) ( 167 )   In order to improve the stability of vehicles under complex operating conditions when the actuator fails， a fault reconstruction strategy based on observer was designed for the electronic stability control system of uncertain vehicles.Considering the uncertain factors in the four-wheel steering system， a dual-input and dual-output mathematical model was established.An augmented system is constructed and the observer gain matrix is obtained by Lyapunov function and linear matrix inequality techniques. The effectiveness of the proposed method is verified by MATLAB/Simulink and Carsim joint simulation. The results indicate that there is some certain deviation between the observer state estimated value and the real value when the fault occurs. However，the estimated value can quickly track the real value to realize fault diagnosis. Compared with the front-wheel steering system， the four-wheel steering system can significantly enhance the stability and safety of the vehicle at high speed. References | Related Articles | Metrics

Select

Fuzzy Similarity Join Algorithm Based on Dynamic Double Prefixes YU Chang-yong， WANG Wen-han， WEN Xiu-jing， ZHAO Yu-hai 2022, 43 (3):  321-327.  DOI: 10.12068/j.issn.1005-3026.2022.03.003 Abstract ( 334 )   HTML ( 4)   PDF (678KB) ( 116 )   Focusing on the similarity join problem， a fuzzy similarity join algorithm was proposed based on dynamic double. The difference from the previous algorithms is that double prefixes are introduced， which improves the filtering efficiency when searching for candidates and building indexes due to the differences of prefixes. On this basis， optimization is realized. First， the candidate set is narrowed by taking the intersection of the candidate sets generated by each prefix. Afterwards， the maximum distinguishing arbitrary-selected prefix is proposed， and this prefix is used for pre-verification to reduce the final candidate pairs that enter the verification process， thereby reducing the join time. Experiments are conducted on three real datasets， and the proposed algorithm is compared with the Silkmoth and MF-Join. The results show that the proposed algorithm can generate a smaller set of candidate set and requires less join time. References | Related Articles | Metrics

Select

Vehicle 3D Space Detection Method Based on Monocular Vision GU De-ying， ZHANG Song， MENG Fan-wei 2022, 43 (3):  328-334.  DOI: 10.12068/j.issn.1005-3026.2022.03.004 Abstract ( 473 )   HTML ( 10)   PDF (1074KB) ( 163 )   Aiming at the problem of low detection precision of 3D bounding box based on monocular vehicle detection， a new network method based on improved FPN (feature pyramid networks) feature fusion， ResNet residual unit， and fully connected layer was proposed. In the training phase， the three-dimensional size of vehicles， residual angle and confidence are regressed. In the reasoning phase， the three-dimensional size and local angle(α)of vehicles are detected. The 3D bounding box of vehicles are reconstructed and drawn from the center coordinates， the three-dimensional size of vehicles， the yaw angle(θ)， and the camera intrinsic matrix. The proposed method is tested on the KITTI verification set. Compared with the results of the original method， the proposed method improves the average precision of 3D bounding box of vehicles(AP3D)to 0.60%， 1.37%， and 1.41%， respectively， under the three detection levels of easy， moderate and difficult. References | Related Articles | Metrics

Select

Train Target Recognition and Ranging Technology Based on Binocular Stereoscopic Vision YUAN Pei-xin， CAI Da， CAO Wen-wei， CHEN Chao 2022, 43 (3):  335-343.  DOI: 10.12068/j.issn.1005-3026.2022.03.005 Abstract ( 664 )   HTML ( 16)   PDF (6054KB) ( 2037 )   With the substantial increase of railway transportation volume in recent years， railway transportation automation has been scheduled. Nowadays， the efficiency of train shunting and marshalling has been greatly improved. However， the unhooking and decomposition operation of trains still need to be completed manually. In view of short time unhooking operation and the need to accurately identify the target handle and ranging when the robot is synchronized with the carriage， a method of automatic unhooking using binocular stereoscopic vision technology combined with the manipulator is proposed， and the vision part is deeply studied: identifying the target handle through image preprocessing and template matching technology， recovering the pose information between binocular cameras by feature detection and matching algorithm， and correcting the pose information of binocular cameras. In order to overcome the influence of uneven illumination in stereoscopic matching， a stereoscopic matching algorithm based on local fusion is proposed to obtain the disparity map. Finally， triangulation is used to calculate the depth information of the target handle in the train decomposition area to realize three-dimensional reconstruction. This method can measure the physical distance between the handles and the binocular vision system after identifying the position of the handles， so as to provide data basis for the automatic unhooking of the robot. References | Related Articles | Metrics

Select

Prison Term Prediction of Judicial Cases Based on Hierarchical Attentive Recurrent Neural Network LI Da-peng， ZHAO Qi-hui， XING Tie-jun， ZHAO Da-zhe 2022, 43 (3):  344-349.  DOI: 10.12068/j.issn.1005-3026.2022.03.006 Abstract ( 389 )   HTML ( 10)   PDF (521KB) ( 263 )   In order to solve the problem of poor accuracy of prison term prediction， a prison term prediction model was proposed on the basis of multi-channel hierarchical attentive recurrent neural network. The model improves the traditional recurrent neural network， introduces BERT word embedding， multichannel mode and hierarchical attention mechanism， and transforms the prison term prediction task into text classification problem. The model uses hierarchical bidirectional recurrent neural network to model the legal case text， and captures the importance of different words and sentences at word level and sentence level through hierarchical attention mechanism. Finally， a multi-channel embedding vector that effectively represents the case text is generated. The experimental results show that the proposed model has higher prediction performance compared with the existing prison term prediction model based on deep learning. References | Related Articles | Metrics

Select

Security Scheduling Algorithm of CAN Bus Based on Dynamic ID Hopping DING Shan， ZANG Shi-yi， CAO Dian-ming， SHE Li-huang 2022, 43 (3):  350-358.  DOI: 10.12068/j.issn.1005-3026.2022.03.007 Abstract ( 402 )   HTML ( 7)   PDF (1008KB) ( 180 )   CAN(controller area network) bus is the most widely used field bus. Due to the lack of authentication and message checking mechanism， CAN bus has great security risks， so it is necessary to design a defense mechanism for CAN bus. In this paper， a priority hopping mechanism is designed， which introduces the dynamic hopping of identifiers by Hash function into a real-time scheduling algorithm. The fixed priority is calculated by a genetic algorithm， and the compromise range of priority is found out. Each frame is grouped， and the ID segment of data frame is segmented and reconstructed. The former part of the ID segment determines the priority and performs priority hopping， while the latter part of the ID segment hops dynamically at one time. Experimental results show that using dynamic priority and one-time ID Hopping to hop has a greater security improvement than the existing ID Hopping mechanism. References | Related Articles | Metrics

Select

Recommendation Algorithm Based on Multi-dimensional Feature Representation Learning in Complex Networks DING Lai-xu， LIU Hong-juan 2022, 43 (3):  359-367.  DOI: 10.12068/j.issn.1005-3026.2022.03.008 Abstract ( 519 )   HTML ( 9)   PDF (719KB) ( 171 )   Network representation learning can effectively solve the problem of data sparsity in recommendation. In this paper， LINE and DeepWalk in network representation learning were improved， and a hybrid recommendation algorithm was proposed to be applied to movie recommendation scene. The new algorithm generates three low dimensional feature vectors by learning user preference feature， user aversion feature and similar user feature. Three low dimensional feature vectors are linearly combined to form a user representation vector， and cosine similarity is used as the similarity index to recommend the movies associated with similar users to target users. Experimental results show that， compared with the suboptimal algorithm， the accuracy and F1 index of the proposed algorithm are improved by 12% and 7% respectively on MovieLens dataset， and 16% and 18% respectively on MovieTweetings dataset. The recommendation algorithm based on multi-dimensional feature representation learning proposed in this paper has significant advantages in movie recommendation scenes. References | Related Articles | Metrics

Select

A Cascaded Adaptive Local Projection Denoising Method XU Li-sheng， CUI Hui-ying， WU Jun-ding， WANG Zhong-yi 2022, 43 (3):  368-375.  DOI: 10.12068/j.issn.1005-3026.2022.03.009 Abstract ( 395 )   HTML ( 1)   PDF (1217KB) ( 223 )   For signals with nonlinear and nonstationary characteristics， denoising method based on the cascade of neighborhood radius adaptive local projection and wavelet threshold denoising was proposed. Firstly， the high-frequency component of the signal was obtained by empirical mode decomposition(EMD)， and the noise level was estimated. Then， the neighborhood radius was determined according to the noise level. Finally， the radius was used for local projection processing and combined with wavelet threshold method for detail smoothing. The denoising results of Lorenz system time series show that this method can improve the signal-to-noise ratio， reduce the mean square error and restore the original attractor shape when the signal structure is distorted. The ability of the proposed method in denoising and restoring the signal characteristics is better than that of the wavelet threshold denoising method. The denoising results of radial， carotid and brachial artery pulse signals and electrocardiogram(ECG)signals show the superior performance of this method in physiological signal noise suppression and feature retention. References | Related Articles | Metrics

Select

Computational Offloading Algorithm Oriented to the Space-Earth Integration Network GENG Rong， WANG Hong-yan， LIU Chang， XU Sai 2022, 43 (3):  376-383.  DOI: 10.12068/j.issn.1005-3026.2022.03.010 Abstract ( 496 )   HTML ( 10)   PDF (778KB) ( 185 )   Due to the limited computing resources and very different capabilities of the space-earth integration network， the processing power of complex tasks is not strong and important tasks fail to be processed. Therefore， a three-layer computational offloading overhead model that offloads tasks to local-backbone-edge access nodes was established and the optimal offloading strategy was formulated through the optimal offloading algorithm based on DQN(deep Q-learning network). Firstly， based on the characteristics of the three types of computing nodes(offloading sites)in the network， including the space-based backbone nodes， edge access nodes and ground-based backbone nodes， the expressions of the delay， energy consumption and the corresponding expressions of different offload sites were given. Then， based on this， the DQN algorithm was proposed to complete the low-delay， low-energy offloading process. Finally， simulation results show that the DQN algorithm can improve the speed of task execution， reduce the energy consumption of terminal equipment， and effectively improve the current situation of computing node resources in the network. References | Related Articles | Metrics

Mechanical Engineering

Select

Fault Diagnosis of Variable Speed Bearings Based on GADF and ResNet34 Introduced Transfer Learning HOU Dong-xiao， MU Jin-tao， FANG Cheng， SHI Pei-ming 2022, 43 (3):  383-389.  DOI: 10.12068/j.issn.1005-3026.2022.03.011 Abstract ( 786 )   HTML ( 17)   PDF (1749KB) ( 439 )   Aiming at the problem that traditional analysis methods are difficult for fault diagnosis of bearings under variable speeds， a fault diagnosis method was proposed for variable speed bearings based on GADF(Gramian angular difference field) and ResNet34 model introduced transfer learning. Firstly， a one-dimensional time-series vibration signal was encoded by using GADF and converted into a two-dimensional image to generate the corresponding fault maps， which were then input into a residual network (ResNet) using transfer learning to automatically extract and classify fault features. To verify the effectiveness of the method， the results of comprehensive comparison with other methods showed that the proposed method performs better on the Western Reserve University bearing dataset. Finally， the variable speed bearing dataset from the University of Ottawa in Canada was diagnosed to examine its classification performance in the variable speed case. The results showed that a high diagnostic accuracy can be achieved in the variable speed case. References | Related Articles | Metrics

Select

Microstepping Control of Stepper Motors Using the Smart Regulation in Decay Mode JIN Bo-pi， WANG Hong， LI Tan， ZHANG Liang 2022, 43 (3):  390-397.  DOI: 10.12068/j.issn.1005-3026.2022.03.012 Abstract ( 497 )   HTML ( 11)   PDF (2696KB) ( 269 )   Aiming at the problems of response time and current ripple caused by the traditional decay modes of stepper motors under the microstepping control， a strategy for the smart regulation of decay mode were proposed. First， the traditional slow decay mode， fast decay mode and fix mixed decay mode were analyzed in detail. Second， a smart regulation scheme of decay mode was designed， which can automatically calculate the optimal decay mode. This scheme can dynamically adjust the fast decay percentage of the total fixed off time within a PWM (pulse width modulation) cycle to improve the performance of the microstepping control. Finally， a test platform was built to compare and analyze the current ripple of the traditional decay modes and the smart regulation in decay mode. This method was successfully applied to SADA of ALNES S7 satellite. The experimental results show that the proposed method achieves a balance between response time and current ripple， which makes the microstepping control more stable. References | Related Articles | Metrics

Select

Finite Element Analysis of Tensile Failure of Open-Pored Carbon Fiber Composite Laminates CHEN Xiao-hui， ZHANG Heng， LIU Ming-yue， HOU Dong-xiao 2022, 43 (3):  397-403.  DOI: 10.12068/j.issn.1005-3026.2022.03.013 Abstract ( 1055 )   HTML ( 16)   PDF (2253KB) ( 573 )   The failure process of the open-pored T300/1034-C carbon fiber composite laminate with a ply angle of ［0°/(±45°)3/(90°)3］s under tensile load was studied by using 2-D shell elements and 3-D solid elements in the ABAQUS finite element software. First， the shell element and continuous shell element carbon fiber composite material models were established with the ABAQUS finite element software， and the internal failure of the layer was simulated using the built-in 2-D Hashin criterion and degradation model. However， the 2-D model did not consider the interaction between the failures of each layer， and by writing the material subroutine VUMAT， the 3-D Hashin criterion and the equivalent stress-strain bilinear degradation method based on the fracture energy were introduced， and the solid element was used to simulate the carbon fiber composite material failure behavior. Through the simulation of three element models， the results showed that the stress concentration caused by the opening will make the fiber and matrix of the laminate more likely to fail during the stretching process and become the source of cracks; during the failure process of laminates， they all show a failure development trend from "X-shape" to "hourglass-shape"， and eventually break in the width direction; compared with the traditional shell element and continuous shell element， the simulation accuracy of the solid model is closer to the experimental value. The simulation limit failure loads of the three elements differ from the literature data by 26.1%， 31.1%， and 8.64%， respectively. References | Related Articles | Metrics

Resources & Civil Engineering

Select

Uniaxial Compressive Strength Characteristics and Crack Evolution Laws of Rock-Like Samples with Flaws SUN Hao， CHEN Shuai-jun， JIN Ai-bing， ZHU Dong-feng 2022, 43 (3):  404-413.  DOI: 10.12068/j.issn.1005-3026.2022.03.014 Abstract ( 642 )   HTML ( 2)   PDF (2731KB) ( 208 )   The fracture network was simplified by studying the properties of rock mass with complex fractures and identifying key fractures in rock mass. Based on 3D printing technology， rock-like samples with different flaws were respectively made. The digital image correlation(DIC)technology was used to monitor the strain field in the sample during loading. The particle flow code(PFC)was used to study the local stress distribution and failure mode in the samples. The main research results show that: 1) Compared with the intact sample， the peak strength of sample with horizontal flaws is reduced by 20.9%， and the peak strength of sample with vertical flaws is only reduced by about 3%. The degradation effect of horizontal flaws on the sample is more significant. 2) The tensile stress in the middle of the horizontal flaw is far greater than that in the end of the vertical flaw， so it is easier and earlier for the sample with horizontal flaw to produce tensile cracks， resulting in that the strength of the sample with horizontal flaw is lower than the sample with vertical flaw under the condition of equal flaw length. 3)When the length of vertical flaw in cross flaws is 1~2 times of the horizontal flaw length， the horizontal flaw in cross flaws is the key flaw to control the crack evolution and strength characteristics of samples， and the change of vertical flaw length has no significant effect on the crack evolution and strength characteristics of samples. Therefore， the cross flaws can be simplified as a horizontal flaw. References | Related Articles | Metrics

Select

Novel Leaching Process of Vanadium and Tungsten from Spent SCR Catalyst at Normal Temperature and Pressure LIU Na-na， XU Xin-yang， CHEN Xi， LIU Yuan 2022, 43 (3):  414-423.  DOI: 10.12068/j.issn.1005-3026.2022.03.015 Abstract ( 395 )   HTML ( 0)   PDF (2497KB) ( 199 )   Based on SEM-EDS and XPS， a novel two-stage leaching process of spent SCR(selective catalytic reduction) catalyst under normal temperature and pressure was proposed. Box-Behnken design(BBD)was used to study the effects of various factors and their interactions on the leaching of vanadium and tungsten， then，the optimal process parameters were obtained and the leaching mechanism was studied. The results showed that: during the two-stage leaching process， the order of influence factors on the leaching rate is temperature >time>leaching agent concentration in the first stage(vanadium extraction process) and temperature>leaching agent concentration>time in the second stage(tungsten extraction process). In the first stage， when the NaOH concentration is 0.5mol·L-1and reacts at 60℃ for 10min， the vanadium leaching rate is(61.40±0.24)%. In the second stage， when the NaOH concentration is 2.5mol·L-1and reacts at 90℃ for 50min， the tungsten leaching rate is(55.73±0.22)%. Vanadium in the spent catalyst exists in the form of V2O3， VOSO4 and V2O5， and reacts with NaOH to form soluble vanadate. A small part of V2O3 and V2O5 are dissolved after forming VOSO4. References | Related Articles | Metrics

Select

Effects of Combined Dephosphorization Agents on Reduction Roasting-Magnetic Separation of High Phosphorus Iron Ore WU Shi-chao， SUN Ti-chang， KOU Jue， CHEN Ze-kun 2022, 43 (3):  423-430.  DOI: 10.12068/j.issn.1005-3026.2022.03.016 Abstract ( 384 )   HTML ( 4)   PDF (3327KB) ( 130 )   In view of the problems such as high cost and large amount of dephosphorization agents in the process of dephosphorization by reduction roasting of high phosphorus iron ore， to better develop and utilize high phosphorus iron ore， the effect of combined dephosphorization agents on iron improvement and dephosphorization of high phosphorus iron ore was studied via reduction roasting-magnetic separation process. X-ray diffraction(XRD)and scanning electron microscope-energy dispersive spectroscopy(SEM-EDS)were used to reveal the mechanism of dephosphorization. The results showed that adding 13% CaCO3 and 2% Na2CO3 as a combined dephosphorization agent can replace the traditional dephosphorization agent， and good dephosphorization effect is obtained. Under the recommended experimental conditions， powdery reduced iron with iron grade of 93.25%， iron recovery of 90.75%， phosphorus content of 0.09%， and dephosphorization of 91.46%can be obtained when iron grade is 55.58% and phosphorus content of raw ore is 0.57%. The added combined dephosphorization agent not only promotes the transformation of phosphorus components in the iron oxides into calcium phosphate， and makes the boundary between metallic iron particles and calcium phosphate distinct， but also prevents the formation of hercynite and fayalite， which is difficult to reduce. Finally， the deep removal of phosphorus and the effective recovery of iron are realized. References | Related Articles | Metrics

Management Science

Select

Platform Dual-Channel Strategy Considering Quality Sensitivity Under Differentiated Slotting Fees LI Chun-yu， ZHANG Cui-hua 2022, 43 (3):  431-440.  DOI: 10.12068/j.issn.1005-3026.2022.03.017 Abstract ( 379 )   HTML ( 2)   PDF (776KB) ( 129 )   Under the online retail environment， the online platform channel strategy was investigated considering service quality sensitivity and channel substitution rate. The decision models of supply chain were constructed based on the fixed and variable slotting fees. With the numerical analysis， the effect of channel competition and quality sensitivity on firms’ decision making was explored， and the boundary conditions of channel selection were defined. The result showed that the channel competition improves quality investment of suppliers and platforms; furthermore， the profits increase. The increment of commissions is not always beneficial to platforms. Excessive commission rates would lead to the withdrawal of suppliers from platforms， which is not conducive to the long-term operation of platforms. For small-scale platforms， the supply chain doesn’t implement a double-channel structure when the fixed slotting fee is high. For large-scale platforms， the slotting fee has little impact on channel operations. When the operating cost of platforms is within a certain range， the dual-channel can achieve a win-win situation. References | Related Articles | Metrics

Select

Impact of Enterprises’Human Capital Structure on International M&A Performance: Based on Moderating Effect of Entrepreneurs′ Educational Background LIU Ye， WEI Xin-li， QIAO Lei 2022, 43 (3):  440-447.  DOI: 10.12068/j.issn.1005-3026.2022.03.018 Abstract ( 382 )   HTML ( 4)   PDF (421KB) ( 106 )   The human capital structure of enterprises is divided into four dimensions: employee educational level， employee salary， employee training and employee turnover. The listed enterprises with international mergers and acquisitions(M&A) since 2004 are used as the research sample to study the impact of enterprises’ human capital structure on the international M&A performance. The results show that the relation between employees’ average educational level and international M&A performance in high-tech enterprises presents a U structure， employee turnover has a negative impact on the international M&A performance of high-tech enterprises and non-high-tech enterprises， entrepreneurs’educational backgrounds have a positive moderating effect on enterprises’ human capital structure and international M&A performance. References | Related Articles | Metrics

Select

Influence of Organization-Employee Work-Family Boundary Integration Fit on Job Well-Being and Thriving at Work YU Bo-ming， ZHANG Lan-xia， YANG Shuo， LI Shuang 2022, 43 (3):  448-456.  DOI: 10.12068/j.issn.1005-3026.2022.03.019 Abstract ( 456 )   HTML ( 5)   PDF (860KB) ( 367 )   Based on the person-environment fit theory and 345 paired survey data of organizations and employees， multiple regression analysis， response surface analysis and block variable analysis were used to explore the effects of the work-family boundary integration fit on the job well-being and thriving at work of employees. The results showed that the consistency fit of the organization-employee work-family boundary has positive effect on employees’ job well-being and thriving at work. The high organization-high employee fit has a stronger positive effect on employees’ job well-being and thriving at work than the low organization-low employee fit. The different fit of organization-employee work-family boundary integration has negative effect on employees’ job well-being and thriving at work， and the negative effect of low organization-high employee fit on employees’ job well-being and thriving at work is stronger than high organization-low employee fit. Job well-being played a mediating role in the relationship between work-family boundary integration and thriving at work. The results of this research enrich the studies on the antecedents of job well-being and thriving at work from the perspective of organization-employee work-family boundary integration fit， and also provide useful guidance for enterprises to formulate differentiated work-family boundary management strategies. References | Related Articles | Metrics