Current Issue

22 December 2025, Volume 44 Issue 12 Previous Issue   
---
Modern Traffic Equipment
Traffic & Transportation + Artificial Intelligence
Intelligent Traffic Infrastructure


For Selected:

Download Citations EndNote Ris BibTeX

Toggle Thumbnails

Modern Traffic Equipment

Select

LQR Trajectory Tracking Control of Unmanned Vehicles Based on Improved Quantum Genetic Algorithm LIU Gang1, ZHANG Ze1, YANG Xu2, WANG Wenzhu1, REN Hongbin3 2025, 44(12): 1-10.  DOI: 10.3969/j.issn.1674-0696.2025.12.01 Abstract ( )   PDF (1480KB) ( )   In order to improve the trajectory tracking accuracy of unmanned vehicles, an LQR trajectory tracking control method for unmanned vehicles based on improved quantum genetic algorithm (IQGA) was proposed. Firstly, in order to solve the problems of significant steady-state error and insufficient predictability of the LQR controller, a feedforward module and a prediction module were designed. Secondly, addressing the challenge of selecting weight parameters for LQR controllers, the quantum genetic algorithm was employed to optimize and select these parameters. Then, addressing the issues in quantum genetic algorithms where the rotation angle of the quantum rotation gate was fixed, which made the algorithm easy to fall into the local optimal value and the lack of population diversity, an adaptive dynamic rotation angle adjustment strategy and a discrete coefficient determination mechanism were designed. Finally, the improved LQR control algorithm (IQGA-LQR) was tested for double lane change trajectory tracking on the Simulink-Carsim co-simulation platform. The simulation results show that compared with the traditional LQR, GA-LQR and QGA-LQR algorithm, the peak lateral errors of the IQGA-LQR algorithm are reduced by 63.1%, 50.15% and 39.44% respectively; and root mean square errors of the IQGA-LQR algorithm are reduced by 50.68%, 41.03% and 34.86%, respectively. References | Related Articles | Metrics

Select

Combustion and Emission of Linear Range Extender Considering Coupling Effects of Dynamics and Thermodynamics TANG Xinhua 2025, 44(12): 11-17.  DOI: 10.3969/j.issn.1674-0696.2025.12.02 Abstract ( )   PDF (1984KB) ( )   The linear range extender is a new type of vehicle power with free dynamic characteristics. In order to accurately reveal its special combustion and emission characteristics, a simulation method featuring coupled iteration of dynamics and thermodynamics was proposed, and a multi-dimensional combustion reaction and pollutant generation model considering dynamic coupling behavior and thermoelectric interaction was constructed. Compared with the conventional range extender, the influence of the unique motion characteristics of the linear range extender on its combustion and emission performance was studied. The results show that the linear range extender has slower effective compression and faster expansion, resulting in lagging behind the conventional range extender all in the process of fuel injection, atomization and air mixing, which makes the maximum combustion pressure and temperature not only smaller and but also the duration shorter. Therefore, the further combustion reactivity of CO is weakened, resulting in more CO pollutants remaining after combustion ends. However, the low combustion temperature also inhibits the generation of NO and Soot, bringing cleaner combustion products, and due to the overall oxygen-rich state in the cylinder, the HC emission of the linear range extender is also slightly less. References | Related Articles | Metrics

Select

Impact of Unit Cell Size on the Mechanical Performance of Ti-6Al-4V Lattice Structure REN Yi1,2，CAI Siyang1，LIU Zhuofan1, ZHAO Yucheng1, GAO Zehao1 2025, 44(12): 18-23.  DOI: 10.3969/j.issn.1674-0696.2025.12.03 Abstract ( )   PDF (5964KB) ( )   Focusing on the Ti-6Al-4V lattice structures formed by laser powder bed fusion (LPBF) technology, the impact of various unit cell sizes on the mechanical properties of additive manufacturing titanium alloy lattice structures was investigated. Initially, four types of lattice structures composed of varying sizes of body-centered cubic (BCC) and face-centered cubic (FCC) unit cells were designed and additively manufactured via LPBF. Secondly, the surface morphology, geometric characteristics and manufacturing defects of the additively manufactured Ti-6Al-4V lattice structures were characterized by use of scanning electron microscope (SEM). Thirdly, a universal mechanical testing machine was employed to conduct quasi-static uniaxial compression tests on the four types of LPBF-fabricated lattice structures, and the impact of different unit cell sizes on the mechanical properties of the lattice structures were compared. Finally, the deformation modes of lattice structures with different unit cell sizes were analyzed by combining with the fracture morphology characteristics. The results indicate that compared to lattice structures with larger unit cell sizes, the specific elastic modulus and specific compressive strength of the RBCC lattice structure have increased by 34% and 32.7% respectively, compared to BCC; while the specific elastic modulus and specific compressive strength of the RFCC lattice structure have increased by 45.6% and 32% respectively, compared to FCC. References | Related Articles | Metrics

Select

Deep Optimization Method of Energy Management Strategy for Hydrogen-Fueled Aircraft JU Fei, GU Zhizhong, XUE Feiyang, WANG Lihao, CHEN Jiale 2025, 44(12): 24-32.  DOI: 10.3969/j.issn.1674-0696.2025.12.04 Abstract ( )   PDF (2057KB) ( )   To enhance the endurance performance of hydrogen-fueled aircraft, an online energy management optimization strategy based on simulated annealing-particle swarm optimization (SA-PSO) was proposed. In the proposed strategy, the parameters of the fuzzy control membership functions were optimized and a fuzzy logic energy management model with power battery SOC and fuel cell demand power as inputs was constructed, enabling efficient energy distribution under dynamic operating conditions. The research results show that compared with the conventional thermostat strategy, the proposed strategy demonstrates superior adaptability and energy efficiency. The integrated SA-PSO algorithm is employed to deeply optimize the fuzzy control parameters, which exhibits fast convergence and strong optimization capabilities in large-scale parameter optimization. The optimized energy management strategy effectively reduces hydrogen consumption and improves energy utilization efficiency under complex dynamic conditions, providing a theoretical basis for online energy management of long-endurance hydrogen-fueled aircraft. References | Related Articles | Metrics

Traffic & Transportation + Artificial Intelligence

Select

Algorithm for Object Detection in Complex Traffic Scenes Based on Improved YOLOv8 Model ZHAO Shuen, GONG Daoyuan, TIAN Zhuoshuai 2025, 44(12): 33-41.  DOI: 10.3969/j.issn.1674-0696.2025.12.05 Abstract ( )   PDF (3787KB) ( )   The detection of road traffic participants such as pedestrians, cyclists and vehicles is regarded as one of the core tasks for achieving autonomous driving. However, in complex scenarios such as uneven lighting, occlusion, dense targets, and small distant objects, false detections and missed detections frequently occur. To address these issues, an improved YOLOv8 object detection algorithm for complex traffic scenes was proposed. Based on the lightweight GhostNet network structure, the backbone and neck networks of the YOLOv8 model were optimized. Standard convolutions (Conv) were replaced by ghost convolutions (GhostConv), while the C2f module was substituted with a combination of the ghost bottleneck (G-bneck) and the C3 module, effectively suppressing redundant detections and improving detection efficiency. A mixed local channel attention (MLCA) mechanism was employed to integrate multi-scale information, enhancing the feature extraction capability of the model. Additionally, a small-object detection layer was incorporated to preserve more detailed features, thereby improving detection performance for small distant targets. Finally, the wise intersection over union (WIoU) loss function was adopted to accelerate network convergence and enhance robustness in complex scenarios. Experimental results demonstrate that the improved YOLOv8 model achieves a mean average precision of 0.872 on the constructed RCCW-Dataset for complex traffic scenes, representing a 2.1% improvement over the original model. Meanwhile, the number and size of model parameters have been reduced by 41% and 37% respectively, enabling effective detection of target tasks in real-time complex traffic scenarios. References | Related Articles | Metrics

Select

Game Selection between Private Cars and Low-Altitude Travel under Conditions of Bounded Rationality WU Lingling，LI Xing，REN Qiliang 2025, 44(12): 42-52.  DOI: 10.3969/j.issn.1674-0696.2025.12.06 Abstract ( )   PDF (2911KB) ( )   The advent of short-haul low-altitude flights offers residents new options for long-distance travel within the city, breaking the balance of private cars as a commonly used means of transportation. Significant differences in preferences for means of transportation of traveler with varying needs greatly increase the complexity for airlines in formulating management strategies. To understand the process of residents choice of travel modes and explore airline management strategies, an evolutionary game model between travelers and airlines was constructed. The subjective psychological perception behavior of game subjects was simulated by introducing prospect theory. The decision-making evolution process of game subjects in different scenarios was analyzed according to the replication dynamic equation of evolutionary games. MATLAB was used to carry out the numerical simulation. The evolution process of the system when related parameters changed was analyzed. The dynamic performance payment model was introduced for unstable and fluctuating states of system to optimize the model, and the probability of travelers choosing low-altitude travel under stable state was 0.39, and the probability of airlines actively controlling was 0.82, and the parameter sensitivity analysis was carried out. The simulation outcomes indicate that although the sensitivity parameters in prospect theory can affect the evolutionary speed of decision-making by game subjects, they do not affect the stability of the evolutionary outcome. Travelers with varying travel needs exhibit different risk preferences in decision-making. Factor sensitivity analysis suggests that airlines should primarily focus on optimizing control measures such as reducing flight prices, optimizing flight frequencies, and decreasing passenger waiting time to enhance the attractiveness of low-altitude travel. The research findings provide a theoretical basis for airline management and control. References | Related Articles | Metrics

Select

Expressway Traffic Flow Data Repair Based on Hybrid Strategy Improved SSA-FCM HE Qingling1, 2, LIU Jing3, WANG Changfeng4, CHENG Rui2 2025, 44(12): 53-61.  DOI: 10.3969/j.issn.1674-0696.2025.12.07 Abstract ( )   PDF (1420KB) ( )   In order to address the deficiencies in accuracy and applicability of the clustering and repair results of expressway traffic flow data, an expressway traffic flow data repair model based on hybrid strategy improved SSA-FCM was constructed. Firstly, the SSA algorithm was improved by using hybrid strategies such as Logistic-Tent combination mapping, elite reverse learning and Cauchy mutation hybrid mechanism, so as to improve the diversity and quality of its population and overcome the issues of SSA algorithm being prone to local optima and premature convergence. Secondly, the ambiguity index, clustering center and number of FCM were determined by using hesitant fuzzy theory and ISSA algorithm. Finally, based on the vehicle trajectory data of expressway, the repair effect of the proposed model was compared and analyzed. The research results show that the mean value and standard deviation of the numerical simulation results of the ISSA algorithm in the eight benchmark test functions are closer to the optimal optimization values. The average absolute error (EMA), root mean square error (ERMS), and average absolute percentage error (EMAP) of the data repair results obtained by ISSA-FCM model under different random missing rate conditions are 4.1 km/h, 4.3 km/h and 7.1%, respectively. Compared to SSA-FCM, PSO-FCM, GA-FCM, LSTM, and ARIMA, the above errors are reduced by 13.9% to 58.3%, 40.3% to 68.2%, and 12.4% to 56.6%, respectively. References | Related Articles | Metrics

Select

Impact of Distracted Driving on Traffic Flow of Urban Expressways MOU Zhenhua, WANG Yongming, PAN Jiangshan, ZHENG Yuanxi 2025, 44(12): 62-71.  DOI: 10.3969/j.issn.1674-0696.2025.12.08 Abstract ( )   PDF (2456KB) ( )   To investigate the impact of drivers distracted behavior on traffic flow of urban expressways, 26 driving volunteers were recruited to conduct a driving simulation experiment. The experiment simulated the driving states under congested conditions, including normal driving, text input, voice input, and hands-free calling, and analyzed the changes in the motion state of distracted vehicles compared to those driving normally. A simulation environment was built, and the vehicle motion state characteristics were taken as vehicle motion parameters to study the impact of distracted driving behavior on urban expressway traffic flow under different distraction ratios. The research results show that with the increase of distracted vehicles, the impact on expressway traffic flow has also increased. Taking the number of overtaking instances as an example, under 5% distraction, 10% distraction, and 15% distraction scenarios, the number of overtaking instances increases by 11.7%, 23.3%, and 28.0%, respectively, compared to normal driving. In addition, traffic density has a certain influence on vehicle speed and traffic flow. Under different density conditions, the impact of distracted driving on traffic flow varies. Under low-density conditions, the overall traffic flow exhibits high stability. When distracted driving occurs at 5%, 10% and 15%, the vehicle speed decreases by 12.8%, 13.8% and 17.9%, respectively. Under high-density conditions, the impact of distracted driving is weakened, with speed fluctuations remaining within 5.0%. While, under medium-density conditions, the impact of distracted driving is the most significant, resulting in speed reductions of 12.1%, 21.5%, and 40.1%, thereby increasing the vehicle instability. References | Related Articles | Metrics

Select

Prediction Methods for Runway Configuration of Multi-runway Airport LI Nan1，LIANG Chen1，LI Xingyu2，CHAI Jiangtao3 2025, 44(12): 72-79.  DOI: 10.3969/j.issn.1674-0696.2025.12.09 Abstract ( )   PDF (934KB) ( )   To accurately predict runway operational modes at multi-runway airports and enhance collaboration efficiency between airports and air traffic control departments, a machine learning method based on an ensemble model was proposed to predict runway operation modes. Firstly, the relevant concepts of runway operation mode were systematically sorted out, and the operation mode and its usage frequency of multi-runway airports were analyzed from multiple dimensions. Subsequently, three major categories of factors affecting runway operation modes and their ten sub-features were identified, and a runway operation mode prediction model was constructed by use of Voting ensemble classifier. Finally, empirical validation was conducted by selecting actud operational data from Beijing Daxing International Airport, covering September 2023 and March 2024. Experimental results demonstrate that the proposed ensemble learning model significantly outperforms traditional prediction methods in predication accuracy, particularly achieving breakthrough performance in the recognition accuracy of high-frequency operational modes, which attains prediction accuracy of 90.63%, 87.65%, and 83.56% in 1-hour, 3-hour, and 6-hour prediction task in advance respectively. These findings provide theoretical foundations for dynamic scheduling decisions while enhancing collaborative decision-making efficiency between airports and ATC entities. References | Related Articles | Metrics

Intelligent Traffic Infrastructure

Select

Experimental Study of Turbulent Kinetic Energy Distribution Characteristics of Double-Propeller Jet in Restricted Waters ZHONG Liang1,2，LIANG Weikun1，GU Mengting1，YANG Xuanxu1 2025, 44(12): 80-88.  DOI: 10.3969/j.issn.1674-0696.2025.12.10 Abstract ( )   PDF (4309KB) ( )   The distribution characteristics of turbulent kinetic energy of double-propeller jet are directly related to the dissipation of water flow energy and have important impacts on the erosion of hydraulic structures and water environment safety in restricted waters. Based on indoor PIV water flume experiments, the turbulent kinetic energy distribution characteristics of double-propeller jet in restricted waters were studied, and the influence rules of section coefficient, propeller pitch and rotational speed on the turbulent kinetic energy distribution in the jet action zone were explored. The results show that in the restricted water area, the turbulent kinetic energy reaches its peak at approximately 0.5 times the propeller diameter (Dp) behind the propeller and then decays. The maximum turbulent kinetic energy on the outer profile of the propeller decays by 50% compared to the profile where the propeller is located, and the central profile of the hull decays by 65%. The vertical distribution shows an inverted “J” shape, and there is a significant “inflection point” where the rate drops sharply on the attenuation curve. The reduction of section coefficient will limit the vertical diffusion range of the double-propeller jet, and the attenuation rate of turbulence kinetic energy along the path will decrease. An increase in pitch expands the turbulence range of the jet, leading to a significant decrease in turbulence kinetic energy at the intersection area of the hulls central profile. An increase in propeller rotational speed will significantly enhance water turbulence and expand the diffusion range of turbulent kinetic energy. The turbulent kinetic energy of the propeller center and outer jet is most significantly affected by rotational speed. References | Related Articles | Metrics

Select

Hydrogeological Numerical Simulation and Application of Project of Zhongliangshan Double Tunnels ZHANG Yongan1, ZHENG Li2, YANG Le2, 3, WEN Tao1, 2 2025, 44(12): 89-95.  DOI: 10.3969/j.issn.1674-0696.2025.12.11 Abstract ( )   PDF (5828KB) ( )   Visual MODFLOW software was applied to numerically simulate groundwater level variations during the construction and operation of the Huayan Tunnel and Huafu Tunnel in the Zhongliangshan hydrogeological unit of Chongqing. The impact scope and self-recovery process of groundwater environment during tunnel construction and operation periods were analyzed, and the time-varying patterns of tunnel groundwater environment were revealed. The research results indicate that the greater the groundwater discharge, the longer the required remediation time. The severe impact range of groundwater environment in Huafu Tunnel is 400 meters, with a drop in precipitation funnel of 20 meters; while the severe impact range of groundwater environment in Huayan Tunnel is 900 meters, with a drop in precipitation funnel of 55 meters. The implementation of water-blocking techniques during tunnel construction results in approximately 50% water level reduction in the first year and 75% reduction in the second year. Groundwater level during tunnel construction and operation can be categorized into four stages: rapid decline period, rapid recovery period, slow recovery period, and equilibrium period. References | Related Articles | Metrics

Select

Embedded CFRP Reinforced Concrete Beam Fracture Analysis Model LI Bo1, HAN Haozhe2, ZHANG Feng2, XU Shuo2 2025, 44(12): 96-104.  DOI: 10.3969/j.issn.1674-0696.2025.12.12 Abstract ( )   PDF (1338KB) ( )   To describe the mechanical properties of the embedded CFRP (carbon fiber reinforced polymer) reinforced concrete beams, an analytical model based on crack propagation was proposed, which took into account the post-cracking tensile stress in concrete, as well as the bond-slip behavior between CFRP and concrete, accurately describing the initiation and propagation of cracks. Twelve samples were fabricated, taking into account the differences in loading ages of 7 days and 14 days, as well as the disparities between plain concrete and CFRPgrid-reinforced concrete beams. The proposed analytical model was employed to perform mechanical analyses on both plain concrete beams and CFRP grid-reinforced concrete beams. Experimental and theoretical analysis results were compared. The research results show that the load-crack mouth opening displacement curve of plain concrete beam exhibits a typical single-peak curve. After the first peak point, the plain concrete beam becomes unstable and the cracks rapidly open. The load-crack mouth opening displacement curve of CFRP grid-reinforced beam also exhibits a descending segment due to the sudden release of local fracture energy. However, due to the bond between the CFRP grid and the concrete, the grid begins to repeatedly exert its tensile strength, resulting in a second ascending segment of the curve, reaching a second peak point. References | Related Articles | Metrics

Select

Calculation Method for Cable Force of Sliding Cables in Arch Bridge Cable System ZHOU Shuixing1, BAI Bingrui1, ZHOU Lingqi1,2, ZHENG Pengpeng3 2025, 44(12): 105-110.  DOI: 10.3969/j.issn.1674-0696.2025.12.13 Abstract ( )   PDF (1550KB) ( )   Both the main cable of the bridge cable hoisting system and the stay cable passing through diverting pulleys in the arch bridge cable-stayed buckling system belong to sliding cables, and their cable force and deformation calculations are relatively complex. Firstly, a single pulley was simplified as a rigid link, and the formula for calculating the direction angle of the link of the sliding cable under the static equilibrium state was derived, proving that the link located at the angle bisector of the sliding cable was a necessary and sufficient condition for ensuring equal cable forces. A solution procedure for the sliding cable structure was proposed, and the correctness and efficiency of the proposed method were verified through two numerical examples and one engineering case study. The research results show that the maximum error between the theoretical cable force obtained by the proposed method and the actual tension force is only 3.9%, while the maximum error of the cable forces calculated by the reverse extension method and the elastic modulus reduction method is up to 12.8%. Furthermore, the inherent reasons that cause the larger errors in the latter two methods are revealed. References | Related Articles | Metrics

Select

Bridge Displacement Influence Line Recognition Based on Machine Vision and Nonlinear Frequency Modulation Signal Decomposition WANG Zuocai1,2, BAI Xiang1, DUAN Dayou3, XIN Yu1 2025, 44(12): 111-122.  DOI: 10.3969/j.issn.1674-0696.2025.12.14 Abstract ( )   PDF (4310KB) ( )   Bridge displacement influence line plays an important role in bridge condition assessment. Traditional bridge displacement influence line identification methods mostly rely on contact sensors, which have problems such as low efficiency and obstruction of traffic. In order to realize convenient and intelligent recognition of bridge displacement influence line, a bridge displacement influence line recognition method based on machine vision and nonlinear frequency modulation signal decomposition was proposed. In the proposed method, the phase-based video motion magnification (PVMM) algorithm was first used to select the phase change of the frequency sub-band of interest in the video and amplify it. The one-dimensional row-gradient domain-guided image filter (Row GDGIF) was used to finely remove the bilateral, artifacts and other noises in the amplified sub-band, and then the motion-amplified video was synthesized. Then, the sub-pixel edge detection technology was used to identify the edge of the bridge, and vibration displacement response of the bridge under moving vehicle load was obtained. Finally, considering the time-varying characteristics of the bridge vibration displacement response frequency, the nonlinear frequency modulation signal decomposition technique was introduced to separate the static and dynamic components of the bridge vibration displacement, realizing bridge displacement influence line identification at last. The applicability and robustness of bridge displacement influence line identification method based on nonlinear frequency modulation signal decomposition was verified by the combination of finite element numerical simulation. The experimental research on the identification of bridge displacement influence line was further conducted. Based on machine vision, the vibration displacement of the bridge under different vehicle speeds was extracted, and the nonlinear frequency modulation signal decomposition method was used to identify the bridge displacement influence line. The results show that the proposed method can effectively identify the bridge displacement influence line and have relatively high accuracy. References | Related Articles | Metrics