Most Down Articles

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

In last 3 years

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Real-Time Template Matching Method for Edge Features WANG Shiyong, QIAN Guokang, LI Di, et al. Journal of South China University of Technology(Natural Science Edition)    2023, 51 (9): 1-10.   DOI: 10.12141/j.issn.1000-565X.220745 Abstract （656）   HTML （21）    PDF（pc） （5488KB）（2058）       Knowledge map    Save Template matching is a common key technology in the field of machine vision. Currently, edge feature-based template matching methods are facing challenges such as time-consuming searching and low matching accuracy in a complex environment. In order to ensure the robustness while improving the real-time performance, this paper proposed a real-time edge feature-based template matching method. Firstly, in the stage of template creation, a new edge sparse method was proposed, and it can screen out the strong invariant edge points from the template image. It reduces the redundancy of template information while retaining the key template features to ensure the stability and improve the computing efficiency. Secondly, in the stage of pyramid search-based image-matching, a top-level pre-screening method was proposed. Normalized Manhattan distance was used as a constraint to exclude incorrect target poses from the top search results to speed up the search in subsequent layers. Five datasets with different working conditions were constructed, and the proposed template matching method was compared and applied to the fast visual dispensing process for free plane pose. The experimental results show that the proposed matching method can significantly improve the matching speed while ensuring high accuracy. And it can overcome interference factors such as illumination change, rotation, defects, multiple targets, and occlusion, enabling practical applications that require both high robustness and real-time performance. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Operational Reliability Optimization Strategies of Multi-type Bus Lines ZHAO Xiaomei, ZHU Xiangyuan, WANG Qin, et al Journal of South China University of Technology(Natural Science Edition)    2023, 51 (8): 32-39.   DOI: 10.12141/j.issn.1000-565X.220493 Abstract （1465）   HTML （32）    PDF（pc） （894KB）（1351）       Knowledge map    Save The unstable running time and the difficulty to accurately estimate the arrival time reduce passengers’ satisfaction with bus traveling. With the diversification of cities, bus line types are gradually becoming more diverse, and the variations in bus operating time of the various bus line types cause trouble in bus scheduling and inconvenience for passengers. To solve above problems, firstly, this paper used K-means ++ algorithm to cluster the stations with the sum of squares of error (SSE) as the measurement index. The operation characteristics and reliability influencing factors of different types of bus lines were taken into consideration to determine the alternative station sets of limited-stop bus service. Then, a joint optimization strategy model of limited-stop bus service and speed regulation was proposed to determine the limited-stop bus station, the departure time, and the running speed of all buses. This model took the minimization of bus operation cost, passenger travel cost, and reliability cost as the objectives, and took the constraints of operation process and headway of limited-stop bus service and all-stop bus service into consideration. Finally, genetic algorithm was used to solve the optimization model and Beijing bus system was selected for case analysis. The results show that the limited-stop bus service can reduce the operation cost of public transport, the speed regulation strategy can better lower the passenger travel cost and reliability cost, and the joint optimization strategy of limited-stop bus service and speed regulation can effectively reduce the total cost of the bus system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Optimized Design of the Main Structure of a Wall-Climbing Robot for Bridge Detection Based on Negative Pressure Adsorption HUANG Haixin, WANG Zheng, CHENG Shoushan, et al Journal of South China University of Technology(Natural Science Edition)    2023, 51 (12): 21-33.   DOI: 10.12141/j.issn.1000-565X.220695 Abstract （342）   HTML （8）    PDF（pc） （5565KB）（1218）       Knowledge map    Save To address the challenging task of inspecting hard-to-reach areas, such as high piers and the bottom of bridges, the paper developed a wall-climbing robot for bridge disease detection based on negative pressure adsorption. For the robot’s own adsorption stability, this paper established and derived a formula for calculating the adsorption force index under conditions of anti-slip and anti-overturning, based on which the minimum adsorption force required by the robot to achieve stable wall adsorption at all angles was determined. The results show that to ensure the reliable operation of the robot, the adsorption module needs to provide 53.0 N adsorption force. The preliminary design of the centrifugal impeller was formulated based on empirical principles, followed by fluid mechanics simulation and response surface optimization of the impeller basin using Fluent. An evaluation function, comprising adsorption force and torque, was established to optimize the impeller design parameters to maximize the comprehensive evaluation function value of the adsorption module. Compared to the initial design scheme, the optimized design achieved a 3.4% increase in the evaluation function value while maintaining stability. Taking into consideration the aerodynamic performance of the chamber along with the topology optimization results, topology optimization of the negative pressure chamber was performed. The structure and arrangement of reinforcing ribs inside the chamber were obtained, with the reinforcing ribs connected to the wheel support arm designed in “八”-shaped and linear hollow structures. This optimization reduced the maximum vertical displacement of the negative pressure chamber to 18.5% of the original model, with a minimal increase in mass of 16.9%. It shows that the precise layout effect of the strengthening rib is obvious, and the vertical deformation is successfully controlled within a reasonable range. Finally, a prototype was constructed using UTR6180 photosensitive resin and 3D printing technology, with approximate dimensions of 300 mm×280 mm×15 mm and a mass of approximately 1.15 kg. The performance test of the prototype was conducted under various working conditions, demonstrating that the wall-climbing robot can stably adsorb and move on various bridge walls without slipping or drifting. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Stuby on the Activity Patterns and Regularity of Public Transport Passengers CHEN Yanyan, WANG Zifan, SUN Haodong, et al Journal of South China University of Technology(Natural Science Edition)    2023, 51 (8): 40-50.   DOI: 10.12141/j.issn.1000-565X.220658 Abstract （592）   HTML （17）    PDF（pc） （2146KB）（1179）       Knowledge map    Save In order to explore the activity pattern and regularity of public transport passengers, this study constructed multi-day passenger travel activity sequences using three weeks smart card data in Beijing in October 2020. The frequent activity pattern sequences of passengers were mined through the PrefixSpan algorithm, and the similarity measure method of activity patterns was defined based on the longest common subsequence. The day-to-day activity sequence similarity of individual and activity pattern similarities among different passengers were calculated respectively, and passengers were classified according to activity pattern similarities among passengers by using the hierarchical clustering algorithm. The results show that the similarity between workdays and weekends is significantly lower than that within workdays or weekends. In workdays, the activity sequence similarity between Friday and the other days is low. Meanwhile, the activity sequence similarity of the same days in different weeks is high. The result of hierarchical clustering shows that there are four typical activity patterns, including entertainment and shopping orientation, life orientation, work orientation and personal affair orientation. Moreover, the day-to-day activity sequence similarity of passenger with work orientation pattern is higher than that of passenger with other activity patterns. The research results in this paper are helpful to scientifically formulate accurate public transport operation management and service policies. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Study on Accident Risk Based on Driving Behavior and Traffic Operating Status GUO Miao, ZHAO Xiaohua, YAO Ying, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 29-38.   DOI: 10.12141/j.issn.1000-565X.210629 Abstract （4295）   HTML （29）    PDF（pc） （2302KB）（1149）       Knowledge map    Save Accurate identification of traffic accident risk and timely mastering the change of traffic crash risk are of great significance for proactive prevention and reduction of traffic accident. Most of the existing traffic crash identification studies are based on real-time and dynamic parameters such as traffic flow and traffic conflict. The application of risky driving behavior in traffic accident risk detection is limited by the constraints of previous data acquisition technologies. To more accurately identify the risk of road traffic crashes, this study introduced risky driving behavior and traffic operating status and other big data, and extracted sharp acceleration, deceleration, turns, merge into other lane, traffic volume, average speed, and congestion index as variables. And traffic accident identification models were constructed based on accident data. The traffic accident identification model was evaluated based on the logistic regression algorithm. On the one hand, the contribution of risky driving behavior in traffic accident identification was quantified; on the other hand, the trend of traffic accident occurrence probability before and after the accident was analyzed. The results show that the sensitivity and AUC values of the traffic accident identification model considering both traffic operation state and risky driving behavior are increased by 5.00% and 0.03, respectively. The false alarm rate and missing report rate are decreased by 1.78% and 5.00%, respectively, which shows better fitting effect of the model. In addition, before and after the occurrence of traffic accidents, the risk probability of traffic crashes shows an obvious trend of rise, which is the key period of traffic accident prevention and control. The measures should be taken in corresponding sections in time to curb the rising trend of traffic crash risk and avoid the occurrence of traffic crashes. This study can provide intuitive basis for traffic accident prevention, and active prevention and control. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Graph Neural Network for Fault Diagnosis with Multi-Scale Time-Spatial Information Fusion Mechanism ZHAO Rongchao, WU Baili, CHEN Zhuyun, et al Journal of South China University of Technology(Natural Science Edition)    2023, 51 (12): 42-52.   DOI: 10.12141/j.issn.1000-565X.220593 Abstract （1503）   HTML （5）    PDF（pc） （4157KB）（1141）       Knowledge map    Save Due to the long-term operation of planetary gearboxes in strong noise environments and changing working conditions, the collected vibration signals exhibit weak fault characteristics and variable signal patterns, making them difficult to identify. Intelligent fault diagnosis of planetary gearboxes under these conditions remains a challenging task. In order to achieve high diagnostic accuracy and strong model generalization performance, a fault diagnosis method using a graph neural network with a multi-scale time-spatial information fusion mechanism is proposed. The method first uses convolution kernels of different scales to extract features from the original vibration signal, reducing the masking effect of strong noise signals on valuable information and enhancing its feature expression ability. A channel attention mechanism is then constructed to adaptively assign different weights among different channels to features of different scales, enhancing features in segments of information containing crucial fault characteristics. Finally, the multi-scale features of the convolution module output are used to construct graph data with spatial structure information for graph convolution learning. This approach allows for the full utilization and deep fusion of multi-dimensional time domain information and spatial correlation information, effectively improving the accuracy of diagnosis and the generalization performance of the model. The proposed method was verified using a fault dataset of wind power equipment with planetary gearbox structure. The average diagnosis accuracy of the proposed method was found to reach 98.85% and 91.29% under cross-load and cross-speed conditions, respectively. These results are superior to other intelligent diagnosis methods, including deep convolutional neural networks with wide first-layer kernels (WDCNN), long short-term memory network (LSTM), residual network (ResNet), and multi-scale convolution neural network (MSCNN). Therefore, the strong generalization performance and superiority of the proposed method were confirmed. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Study on Measuring Method of Vehicle Carbon Emission in Expressway Network LIN Xukun, ZHANG Yang, LUO Zhiqing, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 22-28.   DOI: 10.12141/j.issn.1000-565X.220019 Abstract （5471）   HTML （27）    PDF（pc） （1685KB）（1139）       Knowledge map    Save Under the background of dual-carbon policy, it is imperative to maintain ecological balance and reduce carbon emissions. Nowadays, it is very important to accurately measure the carbon emission index of vehicles on a wide range of road networks. Therefore, this study proposed a measuring method of vehicle carbon emission in expressway network based on multi-source data fusion. Firstly, a basic data cleaning method for carbon emission statistics was proposed to clean the basic data required for subsequent carbon emission calculation. Secondly, the highway carbon emission calculation model was established, and then the related calculation process was designed. Finally, taking the whole highway network of Guangdong province as an example, this paper calculated the vehicle carbon emission from September 2020 to June 2021, and compared the calculation results with China’s carbon accounting database.Through this method, the proposed method was proved to be scientific and reliable. The research shows that the average carbon emission of mini buses in Guangdong province is small, but the total carbon emission accounts for the largest proportion of all types of vehicles, up to 52.1%; the total carbon emission of gasoline vehicles accounts for 49.8%, which is higher than that of diesel vehicles (45.4%) and of other energy vehicles (4.8%). Vigorously promoting new energy vehicles can effectively reduce the carbon emission of expressways. In addition, the study finds that there are significant differences in the travel patterns of different vehicles under COVID-19, but the overall impact on the transportation economy is limited. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Robot Grasping Policy Based on Viewpoint Selection Experience Enhancement Algorithm WANG Gao, CHEN Xiaohong, LIU Ning, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 126-137.   DOI: 10.12141/j.issn.1000-565X.210769 Abstract （10013）   HTML （20）    PDF（pc） （3882KB）（1097）       Knowledge map    Save To solve the problem of the low success rate of robot vision grasping using fixed environment camera in the scene of cluttered and stacked objects, an eye-hand follow-up camera viewpoint selection policy based on deep reinforcement learning is proposed to improve the accuracy and speed of vision-based grasping. Firstly, a Markov decision process model is constructed for robot active vision-based grasping task, then the problem of viewpoint selection is transformed into a problem of solving the viewpoint value function. A deconvolution network with encoder-decoder structure is used to approximate the viewpoint action value function, and the reinforcement learning is carried out based on the deep Q-network framework. Then, to resolve the problem of sparse reward existing in reinforcement learning, a novel viewpoint experience enhancement algorithm is proposed. The different enhancement methods between the successful and failed grasping process are designed respectively. And the reward region can be expanded from a single point to a circular region for improving the convergence speed of the approximation network. The preliminary experiment is deployed on the simulation platform, and the robot model and the grasping environment are simultaneously built in the simulation platform to implement the offline reinforcement learning. In the process, the proposed viewpoint experience enhancement algorithm can effectively improve the sample utilization rate and speed up the convergence of training. Based on the proposed viewpoint experience enhancement algorithm, the viewpoint action value function approximation network can converge within 2 h. To obtain the results from the verification with application, the proposed viewpoint selection policy is applied to the real-world scenes with robot for grasping experiments. The result shows that the viewpoint optimization based on this policy can effectively promote the accuracy and speed of robot grasping. Compared with the general grasping methods, the proposed viewpoint selection policy needs only one viewpoint selection in real-world robot grasping to find the focus region with high grasping success rate. And the method can also promote the processing efficiency of the best viewpoint selection. The grasping success rate in cluttered scenes is increased by 22.8% against the single-view method, and the mean picks per hour can reach 294 units. As whole, it shows that the proposed policy has the capacity of industrial application. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Dynamic Reservation and Allocation Optimization Model of Shared Parking Slots in Multiple Parking Lots WANG Yuanqing, LIN Siyu, XIE Minghui, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 12-21.   DOI: 10.12141/j.issn.1000-565X.210780 Abstract （2196）   HTML （12）    PDF（pc） （2237KB）（1077）       Knowledge map    Save In order to alleviate the parking difficulty, make more balanced use of parking resources and realize the dynamic response to parking demands, this study established an integer programming model for dynamic reservation and allocation of shared parking slots in multiple parking lots by taking several adjacent off-street parking lots as the research object. Aiming at making full use of parking resources and saving users’ parking costs, the model adopts linear weighting to combine the goals and adaptively selects dynamic weight coefficients according to the real-time number of parking requests. The allocation results were optimized iteratively by adjusting the parking requests from the car that does not arrive. In addition, dynamic pricing mechanism was introduced to balance the utilization of each parking lot. The model was evaluated by four indicators: parking space utilization rate, parking request acceptance rate, average walking distance and equilibrium degree of parking area. the model was verified by simulation experiments. The results show that, compared with the traditional unadjusted model, the proposed model can increase the utilization and acceptance rates by 10.70% and 20.08%, respectively, on average by iteratively optimizing the unreached parking requests. The improvement degree of utilization increases first and then decreases with the number of parking requests. The average walking distance of users increases by about 10m, but it still meets the travel needs of users. Compared with the static weight model, the utilization rate and acceptance rate of the embedded dynamic weight model are increased by 2.2% and 10.88%, respectively. The dynamic weight model can better adapt to the dynamic changes of parking demand, so that parking resources can be fully utilized during peak hours. Compared with the static pricing model, the dynamic pricing mechanism was introduced to evenly distribute vehicles to each parking lot, and the equilibrium degree of parking area is reduced by 0.074 on average, so as to realize the balanced utilization of parking resources. The model can provide theoretical reference for parking allocation and management decision-making of shared parking platform and alleviate the problem of urban parking. Reference | Related Articles | Metrics | Comments（0）

Select

Evolution of Interface Performance of Longitudinal Ballastless Track Under Temperature Load After Embedded Steel Bars LU Hongyao, XU Yude Journal of South China University of Technology(Natural Science Edition)    2023, 51 (8): 21-31.   DOI: 10.12141/j.issn.1000-565X.220735 Abstract （452）   HTML （14）    PDF（pc） （5162KB）（1030）       Knowledge map    Save In order to clarify the performance evolution of the interlayer interface of the longitudinal slab ballastless track under the temperature load, this study carried out the mechanical and fatigue performance tests of the interface after embedded steel bars of the composite specimen, and the load spectrum was generated by combining the temperature field monitoring data of the track slab on site.The spatial refined finite element model of ballastless track considering the whole process of interface damage was established and the stress state and damage characteristics of the interface between the lower layers under adverse temperature load were analyzed. The concept of initial temperature load of interface damage was introduced.The change in temperature load at the onset of damage at the interlayer interface after embedded steel bars was calculated and the evolution of debonding risk time after structural performance degradation was clarified. The results show that bearing capacity of the interlayer interface embedded with steel bar is significantly improved.The critical debonding failure displacement and the maximum load are increased by 76.38% and 153.41% respectively, and the fatigue performance is better, indicating that it is feasible to reduce the risk of interfacial debonding of ballastless track through embedding steel bars. The anchoring of embedded steel bars can not fundamentally limit the transmission of temperature force in the ballastless track and the damage suppression effect at the boundary of the slab is limited. It is easy to cause hidden damage near the reinforcement planting hole and the maximum damage value can reach 0.944. With the increase of service life,the initial temperature load that causes the initial damage of the interlayer interface decreases continuously. The safe temperature change range of good bonding state of the interface is reduced from 30.3 ℃ to 16.3 ℃.The number of days with possible interface damage risk is increased by 64.29% and the interlayer interface may have been damaged before extreme weather occurs.The railway department needs to adjust the temperature range of the concerned board based on the actual development of line diseases, and dynamically adjust the setting standards for maintenance thresholds. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A Force-Sensorless Dragging Teaching Method Based on Disturbance Kalman Filter for Robot ZHANG Tie, XU Jinsheng, ZOU Yanbiao Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 116-125.   DOI: 10.12141/j.issn.1000-565X.210781 Abstract （2165）   HTML （18）    PDF（pc） （3056KB）（992）       Knowledge map    Save The dragging teaching method is easy to operate and has high teaching efficiency, which is more in line with modern flexible production. To realize the dragging teaching of industrial robots, it is necessary to accurately measure the external force and control the motion caused by the external force. In order to measure the external force exerted by the operator without torque sensor, an external force observer based on disturbance Kalman filter was designed. The observer takes the external joint torque as the disturbance term, and introduces generalized momentum to establish the state space equation of the robot system, and then uses the Kalman filter algorithm to obtain the optimal observed value of the external torque. Among them, in order to improve the estimation accuracy, the robot dynamic model was established by combining the rigid-body dynamic model and a deep neural network, which not only avoids modeling the complex friction torque but also compensates for the unmodeled factors through the deep neural network. Besides, in order to realize the leading control of the robot in the process of dragging teaching, the dynamic response relationship between the teaching motion and the external torque is equivalent to a mass damping system. An admittance control method with adaptive damping was proposed to convert the observed external torque into the desired joint angle of the teaching motion, and adaptively adjust the system damping parameters according to the change trend of the external torque to improve the teaching effect of the robot. The experiment results show that the proposed dynamic model has a lower mean square root error in the prediction torque, which can reduce the error by no less than 20%. The proposed control scheme can realize the dragging teaching without torque sensors on the six-degree-of-freedom industrial robot, and the adaptive damping method can reduce the torque required to rotate the joint by about 19%, which is more conducive to the start and stop of the teaching motion. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

LiDAR-Binocular Camera Calibration by Minimizing LiDAR Isotropic Error CHEN Zhong, LIU Zichen, ZHANG Xianmin Journal of South China University of Technology(Natural Science Edition)    2023, 51 (2): 1-9.   DOI: 10.12141/j.issn.1000-565X.220178 Abstract （1649）   HTML （1580）    PDF（pc） （2491KB）（923）       Knowledge map    Save Multi-modal data fusion of LiDAR (Laser Imaging, Detection, and Ranging) and binocular camera is important in the research on 3D reconstruction. The two sensors have their own advantages and disadvantages, and they can complement each other through data fusion to obtain better reconstruction results. In order to achieve data fusion, firstly it is necessary to unify the two data into the same coordinate system. The calibration results of the external parameters between the LiDAR and the camera are very important to 3D reconstruction. Due to sparse LiDAR point cloud and its positioning error, it is a challenge to extract feature points accurately for constructing accurate point correspondences when calibrating extrinsic parameters between LiDAR and stereo camera. In addition, most calibration methods ignore that LiDAR works on spherical coordinate system and directly use the Cartesian coordinate measurement results for calibration, which introduces anisotropic coordinates error and reduces the calibration accuracy. This paper proposed a calibration method by minimizing isotropic spherical coordinate error. Firstly, a novel calibration object using centroid feature points was proposed to improve the extraction accuracy of feature points. Secondly, the anisotropic LiDAR Cartesian coordinate error were convert into the isotropic spherical coordinate error, and the extrinsic parameters were solved through directly minimizing the spherical coordinate error. The experiments show that the proposed method has advantages over the anisotropic weighting method. The method ensures that the solution is globally optimal and the number of calibration samples required is greatly reduced on the premise of sacrificing some accuracy. With the optimal calibration error of 2.75 mm, the amount of calibration data can be reduced by about 54.5% by sacrificing 3.6% accuracy using the proposed method. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Intelligent Pushing Method and Experiment of Feeding Assistant Robot ZHANG Qin, HU Jiahui, REN Hailin Journal of South China University of Technology(Natural Science Edition)    2022, 50 (6): 111-120.   DOI: 10.12141/j.issn.1000-565X.210621 Abstract （2173）      PDF（pc） （11308KB）（879）       Knowledge map    Save Regular feed pushing is an important link in the feeding process of dairy cows, and the intelligent feeding assistance of robot instead of human is becoming the development direction in the future. The feeding robot can complete multiple feeding throughout the day, which is widely used in the feeding of dairy cows in large and medium-sized pastures. However, the existing feeding robot has a single function, which can only complete the uniform feeding function, and can not meet the personalized feeding needs of cattle. To solve this problem, this paper proposes an intelligent pushing method of feeding assistant robot. The QR code label is introduced as the positioning label of cow neck rail, and the detection frame area of QR code label and cow head is obtained based on YOLOv4 deep learning model. The detection frame area of QR code label is recognized and tracked in real time through preprocessing and prediction algorithm, and the QR code label and cow head are matched to determine the position of feeding neck rail; According to the position matching information of cow-code and the residual forage distribution information, the robot push plate was controlled to change the pushing angle to realize personalized pushing and meet the individual feeding needs of dairy cows. Research and test results show that the proposed intelligent push method has a recognition rate of 96% for the QR code; In the case of losing 60 consecutive frames, the tracking and prediction accuracy of the QR code is less than ± 2.85%; The processing time of each frame in GPU is 34.4 ms; The accuracy of intelligent feeding is 100%, which can meet the real-time requirements of intelligent pushing in complex environment. Related Articles | Metrics | Comments（0）

Select

Experimental Study on Friction and Wear and Efficiency of Water Hydraulic Axial Piston Pump with Biomimetic Non-smooth Surface Slipper Pair LIANG Yingna, GAO Jianxin, GAO Dianrong Journal of South China University of Technology(Natural Science Edition)    2022, 50 (6): 145-154.   DOI: 10.12141/j.issn.1000-565X.210484 Abstract （2351）      PDF（pc） （52434KB）（855）       Knowledge map    Save In this paper, a certain type water hydraulic axial piston pump was taken as a prototype, and the original smooth surface swash plate was replaced with a biomimetic non-smooth surface one. The flow-pressure, volumetric efficiency-pressure and mechanical efficiency-pressure of the test pump at three different pressures of 7 MPa, 10 MPa, and 12 MPa were tested, and the worn surface of the swash plate was observed using laser confocal microscope and scanning electron microscope. The results show that the slipper pair with non-smooth surface can produce hydrodynamic lubrication effect and have chip holding capacity due to pits. Self-lubrication can be realized during the friction process, achieving the effect of reducing drag and wear. With the increase of working pressure, friction marks in the half-circle high pressure area of the non-smooth surface swash plate are gradually obvious, grooves on the worn surface become wider and deeper, and adhesion wear and oxidation wear are aggravated. That is the friction and wear are aggravated. The volumetric efficiency, mechanical efficiency and total efficiency of the non-smooth surface slipper pair test pump are increased by 0.2%-0.6%, 0.1%-1.7% and 0.1%-2.3% respectively, compared with those of the smooth surface slipper pair test pump. Related Articles | Metrics | Comments（0）

Select

Online Joint Estimation of Main States of Lithium-Ion Battery Based on DAEKF Algorithm LUO Yutao, WU Zhiqiang Journal of South China University of Technology(Natural Science Edition)    2023, 51 (1): 84-94.   DOI: 10.12141/j.issn.1000-565X.220050 Abstract （1444）   HTML （19）    PDF（pc） （3301KB）（681）       Knowledge map    Save In order to realize the online joint estimation of three major states of ternary lithium-ion battery, namely SOC (State of charge), SOH (State of Health) and SOE (State of Energy), and to deal with the open-loop cumulative error caused by various noises in the actual use of electric vehicles, and, furthermore, to improve the stability of online estimation of lithium-ion battery, this paper proposed an online joint estimation method of the three major states of ternary lithium-ion battery in multiple time scales based on double adaptive extended Kalman filter (DAEKF). In the investigation, the state space equation of DAEKF algorithm is derived based on the second-order RC model, and the parameters are identified online by the recursive least square method with forgetting factor (FFRLS). The SOC and SOE of lithium-ion battery are estimated online in the micro time scale, and the SOH of lithium-ion battery is estimated online in the macro time scale. Thus, the online joint estimation of the three major states of lithium-ion battery can be realized. Finally, the proposed method was verified by experiments under different operating conditions of NVR18650B ternary lithium-ion battery. The experimental results show that the proposed method can rapidly converge the model parameters under the two verification conditions; that the estimation errors of SOC and SOE in the micro time scale are kept within 1%, and the estimation errors of SOH in the macro time scale are kept within 1.6%; and that, as compared with the EKF algorithm, the proposed method has a higher estimation accuracy and better estimation convergence and stability. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Research on Spatiotemporal Characteristic and Risk of Lane-Changing Behaviors of Large Vehicles in Expressway Merging Area WEN Huiying, LI Qiuling, ZHAO Sheng Journal of South China University of Technology(Natural Science Edition)    2022, 50 (5): 11-21.   DOI: 10.12141/j.issn.1000-565X.210489 Abstract （2278）      PDF（pc） （1593KB）（667）       Knowledge map    Save In order to study the characteristics and risks of lane-changing behaviors of large vehicles，trajectory data of large vehicles in the expressway merging area was collected based on drone shooting and image recognition technology，and lane-changing characteristics and spatiotemporal risks of large vehicles were analyzed.The results indicate that the average value of the lane change duration of large vehicles is 5.28s，the average value of the first half time is 2.60s，the average value of the last half time is 2.68s，and the average value of longitudinal lane change travel distance is 78.12 meters.They all obey Weibull Distribution，and are significantly related to lane-changing speed.The lane change duration and the first half time are significantly related to the distance between the large vehicle and the vehicle in front in the original lane and the distance between the large vehicle and the vehicle in front in the target lane.The first half time is also significantly related to the distance along the lane line.75.40% of large vehicles start to change lanes within 100 meters before the bottleneck section of the merging area，and the occurrence of lane-changing behavior spreads from the outer lane to the inner lane in turn.The ave-rage distance and relative speed between the large vehicle and the vehicle in front in the original lane are the smallest，which are 22.91 meters and -0.90m/s，respectively.If the lane change gap is small，the driver will be more inclined to change lane when the lane change gap shrinks slowly or continuously expands.The large vehicle has the highest risk of collision with the vehicle in front in the original lane，and approximately 15.32% of large vehicles change lanes when they are in an unsafe state with the vehicles in front. Related Articles | Metrics | Comments（0）

Select

Multi-objective Energy Management Strategy of HEV Based on Improved Dynamic Programming Method ZHAO Kegang, HE Kunyang, LI Jie, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (9): 138-148.   DOI: 10.12141/j.issn.1000-565X.210771 Abstract （1704）   HTML （11）    PDF（pc） （2355KB）（654）       Knowledge map    Save Hybrid electric vehicle Energy Management Strategy (EMS) optimization is a multi-objective and multi-stage decision-making problem that needs to comprehensively optimize several performance indicators of hybrid electric vehicles. The traditional multi-objective optimization algorithm faces challenges such as low efficiency and difficult to guarantee convergence when dealing with these problems. Combined with the idea of non-dominated sorting algorithm, this paper extended the traditional Dynamic Programming (DP) to the field of multi-objective optimization, and proposed Non-dominated Sorting Dynamic Programming (NSDP). When using this algorithm, the driving condition was divided into several stages firstly. In each stage, the cumulative target value vector generated by the hybrid electric vehicle in different control strategies was obtained, and the current non dominated solution set and the corresponding control strategy were obtained through the non dominated sorting algorithm. Then, the non dominated solution set of each stage was used for reverse iteration in turn, until the leading edge of the non dominated solution set and the corresponding energy management control strategy of the whole driving cycle were obtained. In the simulation experiment, Weighting Dynamic Programming (WDP) and Non-dominated Sorting Dynamic Programming were applied to solve the optimization problem of multi-objective energy management strategy for power split hybrid electric vehicles and series parallel hybrid electric vehicles under constant acceleration conditions. The results show that NSDP not only can effectively complete the solution and ensure convergence, but also has significant advantages in homogeneity of solution set and solving efficiency. Furthermore, NSDP was used to solve the energy management optimization problem of series parallel hybrid electric vehicles running in Worldwide Harmonized Light Duty Vehicle Test Cycle (WLTC). The non dominated solution set can be used to analyze the working characteristics of vehicles and provides a reliable reference for the formulation of actual energy management strategy. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

A cross-modal face retrieval method based on metric learning WO Yan, LIANG Jiyun, HAN Guoqiang Journal of South China University of Technology(Natural Science Edition)    2022, 50 (6): 1-9.   DOI: 10.12141/j.issn.1000-565X.210709 Abstract （2767）      PDF（pc） （2022KB）（649）       Knowledge map    Save Metric learning is an important technique to reduce modal differences. Existing cross-modal retrieval methods based on metric learning for cross-modal face retrieval tasks lack attention to pose differences and domain differences, and there are two problems in the process of metric learning: lack of learning of global information and the existence of a large number of redundant triplets. In this paper, a cross-modal common representation generation algorithm based on metric learning is proposed. Our study uses the yaw angle equivariant module to compensate for yaw angle differences so that we can obtain the image features with robustness, uses the multi-layer attention mechanism to obtain video features with differentiability; combines global triplets and local triplets to jointly train the cross-modal common representation generation network, then accelerates the convergence of the loss function through the screening of semi-hard triplets; combines domain calibration and transfer learning to improve the generalization of common representations. Finally, the results of comparison experiments on three face video datasets: PB, YTC and UMD Faces, demonstrate that our algorithm can improve the accuracy of cross-modal face retrieval, and the results of fine-tuning the cross-modal common representation generation network using different numbers of samples demonstrate that our algorithm can improve the accuracy of cross-modal retrieval of target domain images. Related Articles | Metrics | Comments（0）

Select

Beamspace Channel Estimation Algorithm Based on Deep Compressed Sensing ZHENG Juanyi, MU Jinyu, XING Lirong, et al Journal of South China University of Technology(Natural Science Edition)    2022, 50 (12): 101-108.   DOI: 10.12141/j.issn.1000-565X.220017 Abstract （1997）   HTML （25）    PDF（pc） （1825KB）（533）       Knowledge map    Save In the millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) system with lens antenna array, because the radio frequency (RF) link is much less than the number of antennas, it is necessary to recover the high-dimensional channel from the low-dimensional effective measurement signal by channel estimation. The current channel estimation methods basically make use of the sparsity of the beamspace channel, transforming the channel estimation into compressed sensing problem and then estimating with different methods. Aiming at the limitation that approximate message passing (AMP) algorithm needs channel prior information in channel estimation, this paper proposed an improved channel estimation algorithm. Firstly, a new noise term was derived based on the AMP algorithm and fitted with a convolutional neural network (CNN). Then the iterative denoising process was expanded into a deep network to solve the linear inverse transformation of the measurement signal to the cha-nnel. Finally, the initially estimated channel was further optimized by a residual noise removal network. In addition, the controllable parameters were introduced to increase the flexibility of the channel estimation process, and the sen-sing matrix was jointly trained with other network parameters to improve the channel estimation accuracy. This paper verified the proposed algorithm from two aspects of channel estimation accuracy and system transmission quality, and carried out the theoretical formula derivation and system simulation analysis on the Saleh-Valenzuela channel model. Simulation results show that the proposed algorithm has less model parameters and computation than the traditional algorithm, and can improve the accuracy of channel estimation and the transmission quality of the communication system. Table and Figures | Reference | Related Articles | Metrics | Comments（0）

Select

Axial Compression Behavior of Rectangular Concrete-Filled Steel Tube Columns Reinforced by Built-In Profiled Stirrup KANG Lan, CHEN Xuan, HONG Shutao Journal of South China University of Technology(Natural Science Edition)    2024, 52 (5): 101-113.   DOI: 10.12141/j.issn.1000-565X.230116 Abstract （189）   HTML （3）    PDF（pc） （4333KB）（511）       Knowledge map    Save Concrete-filled steel tube (CFST), as a kind of structure with broad development prospect, has good bearing capacity and plastic deformation ability. As a common form, rectangular concrete-filled steel tube column is widely used in engineering practice. Based on the two problems of inconsistent constraints on long and short sides and insufficient constraints on core concrete existing in practical application of rectangular concrete-filled steel tube, this study explored a new type of rectangular concrete-filled steel tube member, namely rectangular concrete-filled steel tube column reinforced by built-in profiled stirrup. Therefore, this study carried out the axial compression tests on 11 rectangular concrete-filled steel tube columns reinforced by built-in profiled stirrup, 2 rectangular concrete-filled steel tube columns with built-in racetrack stirrup, and 2 ordinary rectangular concrete-filled steel tube columns. It analyzed the influences of the coupling distance, steel tube thickness, concrete strength grade, stirrup spacing, stirrup diameter, built-in steel quantity on the axial compression bearing capacity and ductility of rectangular concrete-filled steel tube columns reinforced by built-in profiled stirrup. The findings reveal that reducing the thickness of the rectangular steel tube and embedding the resulting steel into the core concrete as profiled stirrup can effectively improve the axial compressive bearing capacity and ductility of the specimen, while maintaining the total amount of steel used. Additionally, the axial compression behavior of rectangular concrete-filled steel tube columns reinforced by built-in profiled stirrup can be divided into four stages: elastic stage, elastoplastic stage, plastic strengthening stage, and descending stage. Compared to ordinary rectangular concrete-filled steel tube columns, those reinforced by built-in profiled stirrup exhibit a more complete plastic strengthening stage. Based on the experimental results and parametric analysis, this study derived a calculation formula for the axial bearing capacity of rectangular concrete-filled steel tube columns reinforced by built-in profiled stirrup using an existing confined concrete constitutive model. This study can provide scientific basis and data reference for practical engineering applications. Table and Figures | Reference | Related Articles | Metrics | Comments（0）