As one of the major high-speed railway ballastless track structures in China,CRTSIII slab ballastless track has been laid for more than 6500 km.However,there are no detailed studies on its track irregularity deteriora...As one of the major high-speed railway ballastless track structures in China,CRTSIII slab ballastless track has been laid for more than 6500 km.However,there are no detailed studies on its track irregularity deterioration throughout extended service periods,which may threaten the safety and stability of high-speed vehicles(HSV).In this study,a long-term tracking detection of CRTSIII slab ballastless track irregularities has been conducted,revealing its annual evolution law.An HSV-track coupled dynamics model was established to investigate the HSV dynamic responses under annual evolution of track irregularities.Considering the potential deterioration of track irregularities to extremely bad condition,the recommended classified limits for irregularity are proposed by analyzing the limit-exceeding probability of the safety and stability indexes of HSV.The results show that:taking 10 m wavelength as a demarcation,longer-wavelength irregularities exhibit larger amplitudes,faster evolution rates and a linear increasing trend,primarily affecting the stability of HSV.Conversely,shorter-wavelength irregularities exhibit smaller amplitudes and an insignificant evolution trend,predominantly affecting the safety of HSV.Furthermore,the periodic irregularity induced by the arching of 32 m simply-supported beam bridge should be paid closer attention to,as their evolution rate significantly surpasses that of irregularities at other wavelengths.展开更多
The unpowered high-speed vehicle experiences a significant coupling between the disciplines of aerodynamics and control due to its characteristics of high flight speed and extensive maneuverability within large airspa...The unpowered high-speed vehicle experiences a significant coupling between the disciplines of aerodynamics and control due to its characteristics of high flight speed and extensive maneuverability within large airspace.The conventional aircraft conceptual design process follows a sequential design approach,and there is an artificial separation between the disciplines of aerodynamics and control,neglecting the coupling effects arising from their interaction.As a result,this design process often requires extensive iterations over long periods when applied to high-speed vehicles,and may not be able to effectively achieve the desired design objectives.To enhance the overall performance and design efficiency of high-speed vehicles,this study integrates the concept of Active Control Technology(ACT)from modern aircraft into the philosophy of aerodynamic/control integrated optimization.Two integrated optimization strategies,with differences in coupling granularity,have been developed.Subsequently,these strategies are put into action on a biconical vehicle that operates at Mach 5.The results reveal that the comprehensive performance of the synthesis optimal model derived from the aerodynamic/control integrated optimization strategy is improved by 31.76%and 28.29%respectively compared to the base model under high-speed conditions,demonstrating the feasibility and effectiveness of the method and optimization strategies employed.Moreover,in comparison to the single-stage strategy,the multi-stage strategy takes into deeper consideration the impact of control capacity.As a result,the control performance of the synthesis opti-mal model derived from the multi-stage strategy improves by 13.99%,whereas the single-stage strategy only achieves a 5.79%improvement.This method enables a fruitful interaction between aerodynamic configuration design and control system design,leading to enhanced overall performance and design efficiency.Furthermore,it improves the controllability of high-speed vehicles,mitigating the risk of mission failure resulting from an ineffective control system.展开更多
The wheel-rail contact problems, such as the number, location and the track of contact patches, are very important for optimizing the spatial structure of the rails and lowering the vehicle-turnout system dynamics. Ho...The wheel-rail contact problems, such as the number, location and the track of contact patches, are very important for optimizing the spatial structure of the rails and lowering the vehicle-turnout system dynamics. However, the above problems are not well solved currently because of having the difficulties in how to determine the multi-contact, to preciously present the changeable profiles of the rails and to establish an accurate spatial turnout system dynamics model. Based on a high-speed vehicle-turnout coupled model in which the track is modeled as flexible with rails and sleepers represented by beams, the line tracing extreme point method is introduced to investigate the wheel-rail multiple contact conditions and the key sections of the blade rail, longer nose rail, shorter rail in the switch and nose rail area are discretized to represent the varying profiles of rails in the turnout. The dynamic interaction between the vehicle and turnout is simulated for cases of the vehicle divergently passing the turnout and the multi-point contact is obtained. The tracks of the contact patches on the top of the rails are presented and the wheel-rail impact forces are offered in comparison with the contact patches transference on the rails. The numerical simulation results indicate that the length of two-point contact occurrence of a worn wheel profile and rails is longer than that of the new wheel profile and rails; The two-point contact definitely occurs in the switch and crossing area. Generally, three-point contact doesn’t occur for the new rail profile, which is testified by the wheel-rails interpolation distance and the first order derivative function of the tracing line extreme points. The presented research is not only helpful to optimize the structure of the turnout, but also useful to lower the dynamics of the high speed vehicle-turnout system.展开更多
In order to reduce the wheel profile wear of highspeed trains and extend the service life of wheels, a dynamic model for a high-speed vehicle was set up, in which the wheelset was regarded as flexible body, and the ac...In order to reduce the wheel profile wear of highspeed trains and extend the service life of wheels, a dynamic model for a high-speed vehicle was set up, in which the wheelset was regarded as flexible body, and the actual measured track irregularities and line conditions were considered. The wear depth of the wheel profile was calculated by the well-known Archard wear law. Through this model, the influence of the wheel profile, primary suspension stiffness, track gage, and rail cant on the wear of wheel profile were studied through multiple iterafive calculations. Numerical simulation results show that the type XP55 wheel profile has the smallest cumulative wear depth, and the type LM wheel profile has the largest wear depth. To reduce the wear of the wheel profile, the equivalent conicity of the wheel should not be too large or too small. On the other hand, a small primary vertical stiffness, a track gage around 1,435-1,438 mm, and a rail cant around 1：35-1：40 are beneficial for dynamic performance improvement and wheel wear alleviation.展开更多
To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the conc...To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the concept of particle sight distance,an improved algorithm,called SD-IPSO,is proposed for the real-time autonomous navigation of USVs in marine environments.The algorithm refines the individual behavior pattern of particles in the population,effectively improving both local and global search capabilities while avoiding premature convergence.The effectiveness of the algorithm is validated using standard test functions from CEC-2017 function library,assessing it from multiple dimensions.Sensitivity analysis is conducted on key parameters in the algorithm,including particle sight distance and population size.Results indicate that compared with PSO,SD-IPSO demonstrates significant advantages in optimization accuracy and convergence speed.The application of SD-IPSO in path planning is further investigated through a 14-point traveling salesman problem(TSP)example and navigation autonomous tests of USVs in marine environments.Findings demonstrate that the proposed algorithm exhibits superior optimization capabilities and can effectively address the path planning challenges of USVs.展开更多
Ammonia(NH3)has been widely recognized as a key precursor of atmospheric secondary aerosol formation.Vehicle emission is a major source of urban atmospheric NH3.With the tightening of emission standards and the growin...Ammonia(NH3)has been widely recognized as a key precursor of atmospheric secondary aerosol formation.Vehicle emission is a major source of urban atmospheric NH3.With the tightening of emission standards and the growing trend of vehicle fleet electrification,it is imperative to update the emission factors for NH3 from real-world on-road fleets.In this study,a tunnel measurement was conducted in the urban area of Tianjin,China.The fleet-average NH3 emission factor(EF)was 11.2 mg/(km·veh),significantly lower than those in previous studies,showing the benefit of emission standard updating.Through a multiple linear regression analysis,the EFs of light-duty gasoline vehicles,light-duty diesel vehicles,and heavy-duty diesel vehicles(HDDVs)were estimated to be 5.7±0.6 mg/(km·veh),40.8±5.1 mg/(km·veh),and 160.2±16.6 mg/(km·veh),respectively.Based on the results from this study,we found that HDDVs,which comprise<3%of the total vehicles may contribute approximately 22%of total NH3 emissions in Tianjin.Our results highlight NH3 emissions from HDDVs,a previously potentially overlooked source of NH3 emissions in urban areas.The actual on-road NH3 emissions from HDDVs may exceed current expectations,posing a growing concern for the future.展开更多
As the main component of the aircraft leading edge,the radome is often the first to be hit by raindrops and cause structural damage when passing through a rain field.Rain resistant coating is usually applied to ensure...As the main component of the aircraft leading edge,the radome is often the first to be hit by raindrops and cause structural damage when passing through a rain field.Rain resistant coating is usually applied to ensure the performance protection requirements.In order to clarify the rain erosion damage mechanism of radome coating and explore the influencing factors and mechanisms of coating material damage under different jet impact conditions,impact tests were conducted on three types of skin coating samples,and the damage mode was observed through electron microscopy characterization.The experimental results show that the typical morphology of rain erosion damage is annular surface peeling damage.The damage area and volume of the three coating samples increase with the continuous increase of raindrop impact velocity.The threshold velocity for initial damage to the coating is about 360 m/s;under the influence of the velocity component,the reduction in impact angle leads to a gradual reduction in the degree of damage to the sample.ABAQUS finite element simulation software was used to establish a constitutive model for coating rain erosion simulation and obtain the propagation law of stress waves during the impact process.The simulation results show that at the 75°impact angle,the jet impacts the surface of the specimen at different velocities,and as the impact velocity increases,the Mises equivalent stress on the surface shows an increasing trend,which is one of the main factors causing damage with increasing velocity.The effectiveness,rain erosion damage mode,and influencing mechanism of the model were verified based on the test results;the dynamic failure mechanism of the sample was further studied,and the stress propagation process at different impact angles was compared,revealing the influence mechanism and damage law of the impact angle on the high-speed raindrop impact of the material.展开更多
This paper studies the structural response of high-speed train wipers under the combined action of complex flow fields and scraping actions.The stress concentration areas are determined through simulation analysis,and...This paper studies the structural response of high-speed train wipers under the combined action of complex flow fields and scraping actions.The stress concentration areas are determined through simulation analysis,and the stress and aerodynamic load measurement points are reasonably arranged accordingly.The actual measurement is carried out in combination with the operating conditions of the existing lines.The stress variations and spectral characteristics of the train under different speed levels(80,160,180,200 km/h),tunnel entry and exit,and scraper action conditions were compared and analyzed.The stress amplification factors under tunnel intersection and scraper action were obtained,providing boundary conditions for the design of wipers for highspeed s.The research results show that the maximum stress of the wiper structure obtained through simulation calculation is concentrated at the connection of the wiper arm.Structural stress increases with the rise of speed grade.The stress increases by 1.11 times when the tunnel meets.When the scraper operates,the stress on the scraper arm increases by 4.1–7.6 times.Due to the broadband excitation effect of the aerodynamic load,the spectral energy of the structure is relatively high at the natural frequency,which excites the natural mode of the wiper.展开更多
The Internet of Vehicles(IoV)is an emerging technology that aims to connect vehicles,infrastructure,and other devices to enable intelligent transportation systems.One of the key challenges in IoV is to ensure safe and...The Internet of Vehicles(IoV)is an emerging technology that aims to connect vehicles,infrastructure,and other devices to enable intelligent transportation systems.One of the key challenges in IoV is to ensure safe and efficient communication among vehicles of different types and capabilities.This paper proposes a data-driven vehicular heterogeneity-based intelligent collision avoidance system for IoV.The system leverages Vehicle-to-Vehicle(V2V)and Vehicle-to-Infrastructure(V2I)communication to collect real-time data about the environment and the vehicles.The data is collected to acknowledge the heterogeneity of vehicles and human behavior.The data is analyzed using machine learning algorithms to identify potential collision risks and recommend appropriate actions to avoid collisions.The system takes into account the heterogeneity of vehicles,such as their size,speed,and maneuverability,to optimize collision avoidance strategies.The proposed system is experimented with real-time datasets and compared with existing collision avoidance systems.The results are shown using the evaluation metrics that show the proposed system can significantly reduce the number of collisions and improve the overall safety and efficiency of IoV with an accuracy of 96.5%using the SVM algorithm.The trial outcomes demonstrated that the new system,incorporating vehicular,weather,and human behavior factors,outperformed previous systems that only considered vehicular and weather aspects.This innovative approach is poised to lead transportation efforts,reducing accident rates and improving the quality of transportation systems in smart cities.By offering predictive capabilities,the proposed model not only helps control accident rates but also prevents them in advance,ensuring road safety.展开更多
Research on high-speed railways is a relatively new yet highly significant field in Vietnam.Among its key components,train control signaling plays a critical role,as it directly affects various interconnected systems,...Research on high-speed railways is a relatively new yet highly significant field in Vietnam.Among its key components,train control signaling plays a critical role,as it directly affects various interconnected systems,including infrastructure,traction power supply,operational planning,and overall railway safety.This article focuses on evaluating the capacity of the line based on the types of signals suitable for high-speed railways that have been effectively implemented in several European countries and successfully adapted in China.The research and simulation are conducted using MATLAB software,a reliable and widely adopted tool in the scientific community.The findings demonstrate that under normal conditions,the European Railway Traffic Management System/European Train Control System(ERTMS/ETCS)Level 2 signaling can support up to 23.7485 trains/hour/direction.Meanwhile,ERTMS/ETCS Level 3 with full moving block can accommodate up to 30.8735 trains/hour/direction,and ERTMS/ETCS Level 3 with fixed virtual blocks up to 29.4694 trains/hour/direction.In emergency scenarios,ERTMS/ETCS Level 3 with full moving block reduces headway by 33.27%compared to CTCS Level 3,while ERTMS/ETCS Level 3 with fixed virtual blocks achieves a 28.78%reduction.Overall,the ERTMS/ETCS Level 3 emerges as a state-of-the-art signaling technology offering high capacity and operational efficiency,and is recommended as a forward-looking solution for future implementation in Vietnam.展开更多
Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obsta...Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obstacle detection and self-localization.展开更多
The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EIS...The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EISA)framework for 6G unmanned aerial vehicle(UAV)-assisted Internet of vehicles(IoV)networks that integrates task-driven semantic communication,deep reinforcement learning(DRL)-based edge intelligence,and blockchain-based semantic validation across 6G terahertz(THz)links.UAVs in the proposed architecture serve as adaptive edge nodes that receive semantically vital information about the vehicle at any given stage,optimize aggregation and transmission parameters dynamically,and guarantee data integrity through a structured,lightweight consortium blockchain that signs semantically detailed representations rather than raw packets.Simulation results from a hybrid NS-3,MATLAB,and Python environment indicate that the proposed framework can achieve up to 45%reduction in end-to-end latency,an approximately 70%increase in throughput,and semantic efficiency with blockchain verification delays of less than 20 ms(more than 98%).These findings support the effectiveness of the proposed co-design for achieving context-aware,energy-efficient,and reliable communication under heavy-traffic conditions.The proposed framework provides a flexible and scalable foundation for next-generation 6G-enabled automotive networks,with subsequent growth toward federated learning-based collaborative intelligence,digital-twinassisted traffic modeling,and quantum-safe blockchain mechanisms to enhance scalability,intelligence,and long-term security.展开更多
Dear Editor,This letter addresses the formation control problem for unmanned surface vehicles(USVs)under GPS-denied environments.A novel visual servo formation control scheme,utilizing a monocular camera on the follow...Dear Editor,This letter addresses the formation control problem for unmanned surface vehicles(USVs)under GPS-denied environments.A novel visual servo formation control scheme,utilizing a monocular camera on the follower to obtain the leader’s global position,is developed,which is also capable of guaranteeing collision avoidance and visibility maintenance(CA&VM)raised by the requirement of actual formation navigation.展开更多
Autonomous vehicles operate without direct human intervention,which introduces safety risks that differ from those of conventional vehicles.Although many studies have examined safety issues related to autonomous drivi...Autonomous vehicles operate without direct human intervention,which introduces safety risks that differ from those of conventional vehicles.Although many studies have examined safety issues related to autonomous driving,high-risk situations have often been defined using single indicators,making it difficult to capture the complex and evolving nature of accident risk.To address this limitation,this study proposes a structured framework for defining and analyzing high-risk situations throughout the traffic accident process.High-risk situations are described using three complementary indicators:accident likelihood,accident severity,and accident duration.These indicators explain how risk emerges,increases,and persists over time.Based on this concept,a framework for traffic accident visualization analysis is developed to support phase-specific risk assessment and visualization.The framework combines accident-phase information with factor-level risk contributions,allowing systematic identification of key factors and their interactions across different accident stages.Using combinations of the three indicators,high-risk situations are classified into twenty-seven distinct types,providing a clear typology for complex accident scenarios involving autonomous vehicles.The applicability of the proposed framework is demonstrated through two representative accident scenarioswith different risk characteristics.The results showthat the framework effectively captures interactions among multiple risk factors,explains how risk levels change from pre-crash to post-crash phases,and identifies contributing factors that are difficult to detect using conventional traffic accident investigation methods.Overall,the proposed framework offers a practical basis for autonomous vehicle accident analysis,safety evaluation,and policy-related decision-making.展开更多
Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited e...Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited expert demonstrations.However,pure imitation learning inherently suffers from poor exploration and limited generalization,typically necessitating extensive datasets to train competent student policies.We utilize a cross-modal variational autoencoder(CM-VAE)to extract compact features from raw visual inputs and UAV states,which then feed into a policy network.We evaluated our approach in a simulated environment featuring a challenging circular trajectory with eight gate obstacles.The results demonstrate that the policy trained with pure behavior cloning consistently failed.In stark contrast,our DAgger-augmented behavior cloning method successfully traversed all gates without collision.Our findings confirm that DAgger effectively mitigates the shortcomings of behavior cloning,enabling the creation of reliable and sample-efficient navigation policies for UAVs.展开更多
With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyz...With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyze the charging load characteristics of six battery electric vehicle categories in Hebei Province,leveraging multi-source probabilistic distribution data under typical operational scenarios.The findings reveal that electric vehicle charging loads are primarily concentrated during midday and nighttime periods,with significant load fluctuations exerting substantial pressure on the grid.In response,this paper proposes strategic interventions including optimized charging infrastructure planning,time-of-use electricity pricing mechanisms,and smart charging technologies to balance grid loads.The results provide a theoretical foundation for electric vehicle load forecasting,smart grid dispatching,and vehicle-grid integration,thereby enhancing grid operational efficiency and sustainability.展开更多
Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based...Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.展开更多
Blockchain offers a promising solution to the security challenges faced by the Internet of Vehicles(IoV).However,due to the dynamic connectivity of IoV,blockchain based on a single-chain structure or Directed Acyclic ...Blockchain offers a promising solution to the security challenges faced by the Internet of Vehicles(IoV).However,due to the dynamic connectivity of IoV,blockchain based on a single-chain structure or Directed Acyclic Graph(DAG)structure often suffer from performance limitations.The DAG lattice structure is a novel blockchain model in which each node maintains its own account chain,and only the node itself is allowed to update it.This feature makes the DAG lattice structure particularly suitable for addressing the challenges in dynamically connected IoV environment.In this paper,we propose a blockchain architecture based on the DAG lattice structure,specifically designed for dynamically connected IoV.In the proposed system,nodes must obtain authorization from a trusted authority before joining,forming a permissioned blockchain.Each node is assigned an individual account chain,allowing vehicles with limited storage capacity to participate in the blockchain by storing transactions only from nearby vehicles’account chains.Every transmitted message is treated as a transaction and added to the blockchain,enablingmore efficient data transmission in a dynamic network environment.Areputation-based incentivemechanism is introduced to encourage nodes to behave normally.Experimental results demonstrate that the proposed architecture achieves better performance compared with traditional single-chain and DAG-based approaches in terms of average transmission delay and storage cost.展开更多
The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR ...The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR bridges.Drive-by monitoring of bridge uneven settlement demonstrates significant potential due to its practicality,cost-effectiveness,and efficiency.However,existing drive-by methods for detecting bridge offset have limitations such as reliance on a single data source,low detection accuracy,and the inability to identify lateral deformations of bridges.This paper proposes a novel drive-by inspection method for spatial offset of HSR bridge based on multi-source data fusion of comprehensive inspection train.Firstly,dung beetle optimizer-variational mode decomposition was employed to achieve adaptive decomposition of non-stationary dynamic signals,and explore the hidden temporal relationships in the data.Subsequently,a long short-term memory neural network was developed to achieve feature fusion of multi-source signal and accurate prediction of spatial settlement of HSR bridge.A dataset of track irregularities and CRH380A high-speed train responses was generated using a 3D train-track-bridge interaction model,and the accuracy and effectiveness of the proposed hybrid deep learning model were numerically validated.Finally,the reliability of the proposed drive-by inspection method was further validated by analyzing the actual measurement data obtained from comprehensive inspection train.The research findings indicate that the proposed approach enables rapid and accurate detection of spatial offset in HSR bridge,ensuring the long-term operational safety of HSR bridges.展开更多
Vehicle re-identification(ReID)is a challenging task in intelligent transportation,and urban surveillance systems due to its complications in camera viewpoints,vehicle scales,and environmental conditions.Recent transf...Vehicle re-identification(ReID)is a challenging task in intelligent transportation,and urban surveillance systems due to its complications in camera viewpoints,vehicle scales,and environmental conditions.Recent transformer-based approaches have shown impressive performance by utilizing global dependencies,these models struggle with aspect ratio distortions and may overlook fine-grained local attributes crucial for distinguishing visually similar vehicles.We introduce a framework based on Swin Transformers that addresses these challenges by implementing three components.First,to improve feature robustness and maintain vehicle proportions,our Aspect Ratio-Aware Swin Transformer(AR-Swin)preserve the native ratio via letterbox,uses a non-square(16×8)patch-embedding stem,and keeps fixed 7×7 token windows.Second,we introduce a Dynamic Feature Fusion Network(DFFNet)that adaptively integrates global Swin features with local attribute embeddings;such as color and vehicle type enablingmore discriminative representations.Third,our Regional Attention Blocks incorporate regionalmasks into the transformer’s windowed attentionmechanism,effectively highlighting critical details like manufacturer logos or lights.On VeRi-776,we obtain 82.55 mAP,97.26 Rank-1 and 99.23 Rank-5,and on VehicleID we obtain 91.8 Rank-1 and 97.75 Rank-5.The design is drop-in for Swin backbones and emphasizes robustness without increasing architectural complexity.Code:https://github.com/sft110/Swinvreid.展开更多
基金Project(2022YFB2602900)supported by the National Key Research and Development Program of ChinaProject(K2022T002)supported by the Scientific Research Plan of China Railway。
文摘As one of the major high-speed railway ballastless track structures in China,CRTSIII slab ballastless track has been laid for more than 6500 km.However,there are no detailed studies on its track irregularity deterioration throughout extended service periods,which may threaten the safety and stability of high-speed vehicles(HSV).In this study,a long-term tracking detection of CRTSIII slab ballastless track irregularities has been conducted,revealing its annual evolution law.An HSV-track coupled dynamics model was established to investigate the HSV dynamic responses under annual evolution of track irregularities.Considering the potential deterioration of track irregularities to extremely bad condition,the recommended classified limits for irregularity are proposed by analyzing the limit-exceeding probability of the safety and stability indexes of HSV.The results show that:taking 10 m wavelength as a demarcation,longer-wavelength irregularities exhibit larger amplitudes,faster evolution rates and a linear increasing trend,primarily affecting the stability of HSV.Conversely,shorter-wavelength irregularities exhibit smaller amplitudes and an insignificant evolution trend,predominantly affecting the safety of HSV.Furthermore,the periodic irregularity induced by the arching of 32 m simply-supported beam bridge should be paid closer attention to,as their evolution rate significantly surpasses that of irregularities at other wavelengths.
基金supported by the National Natural Science Foundation of China(Nos.92371201,52192633)the Natural Science Foundation of Shaanxi Province(No.2022JC-03)Chinese Aeronautical Foundation(No.ASFC-20220019070002)。
文摘The unpowered high-speed vehicle experiences a significant coupling between the disciplines of aerodynamics and control due to its characteristics of high flight speed and extensive maneuverability within large airspace.The conventional aircraft conceptual design process follows a sequential design approach,and there is an artificial separation between the disciplines of aerodynamics and control,neglecting the coupling effects arising from their interaction.As a result,this design process often requires extensive iterations over long periods when applied to high-speed vehicles,and may not be able to effectively achieve the desired design objectives.To enhance the overall performance and design efficiency of high-speed vehicles,this study integrates the concept of Active Control Technology(ACT)from modern aircraft into the philosophy of aerodynamic/control integrated optimization.Two integrated optimization strategies,with differences in coupling granularity,have been developed.Subsequently,these strategies are put into action on a biconical vehicle that operates at Mach 5.The results reveal that the comprehensive performance of the synthesis optimal model derived from the aerodynamic/control integrated optimization strategy is improved by 31.76%and 28.29%respectively compared to the base model under high-speed conditions,demonstrating the feasibility and effectiveness of the method and optimization strategies employed.Moreover,in comparison to the single-stage strategy,the multi-stage strategy takes into deeper consideration the impact of control capacity.As a result,the control performance of the synthesis opti-mal model derived from the multi-stage strategy improves by 13.99%,whereas the single-stage strategy only achieves a 5.79%improvement.This method enables a fruitful interaction between aerodynamic configuration design and control system design,leading to enhanced overall performance and design efficiency.Furthermore,it improves the controllability of high-speed vehicles,mitigating the risk of mission failure resulting from an ineffective control system.
基金supported by National Natural Science Foundation of China (Grant Nos. 51175032, U1134201)National Basic Research Program of China (973 Program, Grant No. 2011CD711104)
文摘The wheel-rail contact problems, such as the number, location and the track of contact patches, are very important for optimizing the spatial structure of the rails and lowering the vehicle-turnout system dynamics. However, the above problems are not well solved currently because of having the difficulties in how to determine the multi-contact, to preciously present the changeable profiles of the rails and to establish an accurate spatial turnout system dynamics model. Based on a high-speed vehicle-turnout coupled model in which the track is modeled as flexible with rails and sleepers represented by beams, the line tracing extreme point method is introduced to investigate the wheel-rail multiple contact conditions and the key sections of the blade rail, longer nose rail, shorter rail in the switch and nose rail area are discretized to represent the varying profiles of rails in the turnout. The dynamic interaction between the vehicle and turnout is simulated for cases of the vehicle divergently passing the turnout and the multi-point contact is obtained. The tracks of the contact patches on the top of the rails are presented and the wheel-rail impact forces are offered in comparison with the contact patches transference on the rails. The numerical simulation results indicate that the length of two-point contact occurrence of a worn wheel profile and rails is longer than that of the new wheel profile and rails; The two-point contact definitely occurs in the switch and crossing area. Generally, three-point contact doesn’t occur for the new rail profile, which is testified by the wheel-rails interpolation distance and the first order derivative function of the tracing line extreme points. The presented research is not only helpful to optimize the structure of the turnout, but also useful to lower the dynamics of the high speed vehicle-turnout system.
基金the support of the National Natural Science Foundation of China (No. 51005189)the National Key Technology R&D Program of China (2009BAG12A01)
文摘In order to reduce the wheel profile wear of highspeed trains and extend the service life of wheels, a dynamic model for a high-speed vehicle was set up, in which the wheelset was regarded as flexible body, and the actual measured track irregularities and line conditions were considered. The wear depth of the wheel profile was calculated by the well-known Archard wear law. Through this model, the influence of the wheel profile, primary suspension stiffness, track gage, and rail cant on the wear of wheel profile were studied through multiple iterafive calculations. Numerical simulation results show that the type XP55 wheel profile has the smallest cumulative wear depth, and the type LM wheel profile has the largest wear depth. To reduce the wear of the wheel profile, the equivalent conicity of the wheel should not be too large or too small. On the other hand, a small primary vertical stiffness, a track gage around 1,435-1,438 mm, and a rail cant around 1：35-1：40 are beneficial for dynamic performance improvement and wheel wear alleviation.
文摘To enhance the accuracy of path planning of unmanned surface vehicles(USVs),the particle swarm optimization algorithm(PSO)is improved based on species migration strategies observed in ecology.By incorporating the concept of particle sight distance,an improved algorithm,called SD-IPSO,is proposed for the real-time autonomous navigation of USVs in marine environments.The algorithm refines the individual behavior pattern of particles in the population,effectively improving both local and global search capabilities while avoiding premature convergence.The effectiveness of the algorithm is validated using standard test functions from CEC-2017 function library,assessing it from multiple dimensions.Sensitivity analysis is conducted on key parameters in the algorithm,including particle sight distance and population size.Results indicate that compared with PSO,SD-IPSO demonstrates significant advantages in optimization accuracy and convergence speed.The application of SD-IPSO in path planning is further investigated through a 14-point traveling salesman problem(TSP)example and navigation autonomous tests of USVs in marine environments.Findings demonstrate that the proposed algorithm exhibits superior optimization capabilities and can effectively address the path planning challenges of USVs.
基金supported by the National key research and development program of China(No.2022YFE0135000)the National Natural Science Foundation of China(No.42175123)the Natural Science Foundation of Tianjin(No.23JCJQJC00170).
文摘Ammonia(NH3)has been widely recognized as a key precursor of atmospheric secondary aerosol formation.Vehicle emission is a major source of urban atmospheric NH3.With the tightening of emission standards and the growing trend of vehicle fleet electrification,it is imperative to update the emission factors for NH3 from real-world on-road fleets.In this study,a tunnel measurement was conducted in the urban area of Tianjin,China.The fleet-average NH3 emission factor(EF)was 11.2 mg/(km·veh),significantly lower than those in previous studies,showing the benefit of emission standard updating.Through a multiple linear regression analysis,the EFs of light-duty gasoline vehicles,light-duty diesel vehicles,and heavy-duty diesel vehicles(HDDVs)were estimated to be 5.7±0.6 mg/(km·veh),40.8±5.1 mg/(km·veh),and 160.2±16.6 mg/(km·veh),respectively.Based on the results from this study,we found that HDDVs,which comprise<3%of the total vehicles may contribute approximately 22%of total NH3 emissions in Tianjin.Our results highlight NH3 emissions from HDDVs,a previously potentially overlooked source of NH3 emissions in urban areas.The actual on-road NH3 emissions from HDDVs may exceed current expectations,posing a growing concern for the future.
基金supported by the National Natural Science Foundation of China(Nos.12261131505,U2241274)the Russian Science Fund(No.23-49-00133)+3 种基金the Aeronautical Science Foundation of China(No.20240002053002)the Natural Science Basic Research Program of Shaanxi,China(No.2025JC-YBMS-005)the Key Research and Development Program of Shaanxi,China(No.2024GX-YBXM-037)the Basic Research Programs of Taicang,China(No.TC2024JC10)。
文摘As the main component of the aircraft leading edge,the radome is often the first to be hit by raindrops and cause structural damage when passing through a rain field.Rain resistant coating is usually applied to ensure the performance protection requirements.In order to clarify the rain erosion damage mechanism of radome coating and explore the influencing factors and mechanisms of coating material damage under different jet impact conditions,impact tests were conducted on three types of skin coating samples,and the damage mode was observed through electron microscopy characterization.The experimental results show that the typical morphology of rain erosion damage is annular surface peeling damage.The damage area and volume of the three coating samples increase with the continuous increase of raindrop impact velocity.The threshold velocity for initial damage to the coating is about 360 m/s;under the influence of the velocity component,the reduction in impact angle leads to a gradual reduction in the degree of damage to the sample.ABAQUS finite element simulation software was used to establish a constitutive model for coating rain erosion simulation and obtain the propagation law of stress waves during the impact process.The simulation results show that at the 75°impact angle,the jet impacts the surface of the specimen at different velocities,and as the impact velocity increases,the Mises equivalent stress on the surface shows an increasing trend,which is one of the main factors causing damage with increasing velocity.The effectiveness,rain erosion damage mode,and influencing mechanism of the model were verified based on the test results;the dynamic failure mechanism of the sample was further studied,and the stress propagation process at different impact angles was compared,revealing the influence mechanism and damage law of the impact angle on the high-speed raindrop impact of the material.
文摘This paper studies the structural response of high-speed train wipers under the combined action of complex flow fields and scraping actions.The stress concentration areas are determined through simulation analysis,and the stress and aerodynamic load measurement points are reasonably arranged accordingly.The actual measurement is carried out in combination with the operating conditions of the existing lines.The stress variations and spectral characteristics of the train under different speed levels(80,160,180,200 km/h),tunnel entry and exit,and scraper action conditions were compared and analyzed.The stress amplification factors under tunnel intersection and scraper action were obtained,providing boundary conditions for the design of wipers for highspeed s.The research results show that the maximum stress of the wiper structure obtained through simulation calculation is concentrated at the connection of the wiper arm.Structural stress increases with the rise of speed grade.The stress increases by 1.11 times when the tunnel meets.When the scraper operates,the stress on the scraper arm increases by 4.1–7.6 times.Due to the broadband excitation effect of the aerodynamic load,the spectral energy of the structure is relatively high at the natural frequency,which excites the natural mode of the wiper.
文摘The Internet of Vehicles(IoV)is an emerging technology that aims to connect vehicles,infrastructure,and other devices to enable intelligent transportation systems.One of the key challenges in IoV is to ensure safe and efficient communication among vehicles of different types and capabilities.This paper proposes a data-driven vehicular heterogeneity-based intelligent collision avoidance system for IoV.The system leverages Vehicle-to-Vehicle(V2V)and Vehicle-to-Infrastructure(V2I)communication to collect real-time data about the environment and the vehicles.The data is collected to acknowledge the heterogeneity of vehicles and human behavior.The data is analyzed using machine learning algorithms to identify potential collision risks and recommend appropriate actions to avoid collisions.The system takes into account the heterogeneity of vehicles,such as their size,speed,and maneuverability,to optimize collision avoidance strategies.The proposed system is experimented with real-time datasets and compared with existing collision avoidance systems.The results are shown using the evaluation metrics that show the proposed system can significantly reduce the number of collisions and improve the overall safety and efficiency of IoV with an accuracy of 96.5%using the SVM algorithm.The trial outcomes demonstrated that the new system,incorporating vehicular,weather,and human behavior factors,outperformed previous systems that only considered vehicular and weather aspects.This innovative approach is poised to lead transportation efforts,reducing accident rates and improving the quality of transportation systems in smart cities.By offering predictive capabilities,the proposed model not only helps control accident rates but also prevents them in advance,ensuring road safety.
文摘Research on high-speed railways is a relatively new yet highly significant field in Vietnam.Among its key components,train control signaling plays a critical role,as it directly affects various interconnected systems,including infrastructure,traction power supply,operational planning,and overall railway safety.This article focuses on evaluating the capacity of the line based on the types of signals suitable for high-speed railways that have been effectively implemented in several European countries and successfully adapted in China.The research and simulation are conducted using MATLAB software,a reliable and widely adopted tool in the scientific community.The findings demonstrate that under normal conditions,the European Railway Traffic Management System/European Train Control System(ERTMS/ETCS)Level 2 signaling can support up to 23.7485 trains/hour/direction.Meanwhile,ERTMS/ETCS Level 3 with full moving block can accommodate up to 30.8735 trains/hour/direction,and ERTMS/ETCS Level 3 with fixed virtual blocks up to 29.4694 trains/hour/direction.In emergency scenarios,ERTMS/ETCS Level 3 with full moving block reduces headway by 33.27%compared to CTCS Level 3,while ERTMS/ETCS Level 3 with fixed virtual blocks achieves a 28.78%reduction.Overall,the ERTMS/ETCS Level 3 emerges as a state-of-the-art signaling technology offering high capacity and operational efficiency,and is recommended as a forward-looking solution for future implementation in Vietnam.
基金supported in part by the National Natural Science Foundation of China(U25A20473,62222314)the YanZhao Young Scientist Project of Hebei Province(F2024203047)+2 种基金the Natural Science Foundation of Hebei Province(F2022203001,F2024203072)the State Key Laboratory of Submarine Geoscience(sglkt2025-7)the Education Department Foundation of Hebei Province(JCZX2025027)。
文摘Dear Editor,This letter studies the motion planning issue for an autonomous underwater vehicle(AUV)in obstacle environment.We propose a novel integrated detection-communication waveform that enables simultaneous obstacle detection and self-localization.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)-Information Technology Research Center(ITRC)under Grant No.IITP-2025-RS-2023-00259004the Basic Science Research Program through the National Research Foundation of Korea(NRF)under Grant No.RS-2025-25434261.
文摘The intelligent transportation systems require secure,low-latency,and reliable communication architectures to enable the real-time vehicular application.This paper proposes an edge-intelligent semantic aggregation(EISA)framework for 6G unmanned aerial vehicle(UAV)-assisted Internet of vehicles(IoV)networks that integrates task-driven semantic communication,deep reinforcement learning(DRL)-based edge intelligence,and blockchain-based semantic validation across 6G terahertz(THz)links.UAVs in the proposed architecture serve as adaptive edge nodes that receive semantically vital information about the vehicle at any given stage,optimize aggregation and transmission parameters dynamically,and guarantee data integrity through a structured,lightweight consortium blockchain that signs semantically detailed representations rather than raw packets.Simulation results from a hybrid NS-3,MATLAB,and Python environment indicate that the proposed framework can achieve up to 45%reduction in end-to-end latency,an approximately 70%increase in throughput,and semantic efficiency with blockchain verification delays of less than 20 ms(more than 98%).These findings support the effectiveness of the proposed co-design for achieving context-aware,energy-efficient,and reliable communication under heavy-traffic conditions.The proposed framework provides a flexible and scalable foundation for next-generation 6G-enabled automotive networks,with subsequent growth toward federated learning-based collaborative intelligence,digital-twinassisted traffic modeling,and quantum-safe blockchain mechanisms to enhance scalability,intelligence,and long-term security.
基金supported by the National Natural Science Foundation of China(62421004,U24A20279,62473243,62533004)。
文摘Dear Editor,This letter addresses the formation control problem for unmanned surface vehicles(USVs)under GPS-denied environments.A novel visual servo formation control scheme,utilizing a monocular camera on the follower to obtain the leader’s global position,is developed,which is also capable of guaranteeing collision avoidance and visibility maintenance(CA&VM)raised by the requirement of actual formation navigation.
基金supported by the Korea Institute of Police Technology(No.:RS-2024-00405603).
文摘Autonomous vehicles operate without direct human intervention,which introduces safety risks that differ from those of conventional vehicles.Although many studies have examined safety issues related to autonomous driving,high-risk situations have often been defined using single indicators,making it difficult to capture the complex and evolving nature of accident risk.To address this limitation,this study proposes a structured framework for defining and analyzing high-risk situations throughout the traffic accident process.High-risk situations are described using three complementary indicators:accident likelihood,accident severity,and accident duration.These indicators explain how risk emerges,increases,and persists over time.Based on this concept,a framework for traffic accident visualization analysis is developed to support phase-specific risk assessment and visualization.The framework combines accident-phase information with factor-level risk contributions,allowing systematic identification of key factors and their interactions across different accident stages.Using combinations of the three indicators,high-risk situations are classified into twenty-seven distinct types,providing a clear typology for complex accident scenarios involving autonomous vehicles.The applicability of the proposed framework is demonstrated through two representative accident scenarioswith different risk characteristics.The results showthat the framework effectively captures interactions among multiple risk factors,explains how risk levels change from pre-crash to post-crash phases,and identifies contributing factors that are difficult to detect using conventional traffic accident investigation methods.Overall,the proposed framework offers a practical basis for autonomous vehicle accident analysis,safety evaluation,and policy-related decision-making.
基金supported by the National Natural Science Foundation of China(No.62576349)。
文摘Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited expert demonstrations.However,pure imitation learning inherently suffers from poor exploration and limited generalization,typically necessitating extensive datasets to train competent student policies.We utilize a cross-modal variational autoencoder(CM-VAE)to extract compact features from raw visual inputs and UAV states,which then feed into a policy network.We evaluated our approach in a simulated environment featuring a challenging circular trajectory with eight gate obstacles.The results demonstrate that the policy trained with pure behavior cloning consistently failed.In stark contrast,our DAgger-augmented behavior cloning method successfully traversed all gates without collision.Our findings confirm that DAgger effectively mitigates the shortcomings of behavior cloning,enabling the creation of reliable and sample-efficient navigation policies for UAVs.
基金funded by Humanities and Social Sciences of Ministry of Education Planning Fund of China,grant number 21YJA790009National Natural Science Foundation of China,grant number 72140001.
文摘With the rapid proliferation of electric vehicles,their charging loads pose new challenges to power grid stability and operational efficiency.To address this,this study employs a Monte Carlo simulation model to analyze the charging load characteristics of six battery electric vehicle categories in Hebei Province,leveraging multi-source probabilistic distribution data under typical operational scenarios.The findings reveal that electric vehicle charging loads are primarily concentrated during midday and nighttime periods,with significant load fluctuations exerting substantial pressure on the grid.In response,this paper proposes strategic interventions including optimized charging infrastructure planning,time-of-use electricity pricing mechanisms,and smart charging technologies to balance grid loads.The results provide a theoretical foundation for electric vehicle load forecasting,smart grid dispatching,and vehicle-grid integration,thereby enhancing grid operational efficiency and sustainability.
基金the Hebei Province Science and Technology Plan Project(19221909D)rincess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R308),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.
基金funded in part by the Supported by Natural Science Foundation of Inner Mongolia Autonomous Region of China under Grants 2024QN06022 and 2023QN06008in part by the First-Class Discipline Research Special Project under Grant YLXKZX-NGD-015in part by the Inner Mongolia University of Technology Scientific Research Start-Up Project under Grant BS2024067.
文摘Blockchain offers a promising solution to the security challenges faced by the Internet of Vehicles(IoV).However,due to the dynamic connectivity of IoV,blockchain based on a single-chain structure or Directed Acyclic Graph(DAG)structure often suffer from performance limitations.The DAG lattice structure is a novel blockchain model in which each node maintains its own account chain,and only the node itself is allowed to update it.This feature makes the DAG lattice structure particularly suitable for addressing the challenges in dynamically connected IoV environment.In this paper,we propose a blockchain architecture based on the DAG lattice structure,specifically designed for dynamically connected IoV.In the proposed system,nodes must obtain authorization from a trusted authority before joining,forming a permissioned blockchain.Each node is assigned an individual account chain,allowing vehicles with limited storage capacity to participate in the blockchain by storing transactions only from nearby vehicles’account chains.Every transmitted message is treated as a transaction and added to the blockchain,enablingmore efficient data transmission in a dynamic network environment.Areputation-based incentivemechanism is introduced to encourage nodes to behave normally.Experimental results demonstrate that the proposed architecture achieves better performance compared with traditional single-chain and DAG-based approaches in terms of average transmission delay and storage cost.
基金sponsored by the National Natural Science Foundation of China(Grant No.52178100).
文摘The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR bridges.Drive-by monitoring of bridge uneven settlement demonstrates significant potential due to its practicality,cost-effectiveness,and efficiency.However,existing drive-by methods for detecting bridge offset have limitations such as reliance on a single data source,low detection accuracy,and the inability to identify lateral deformations of bridges.This paper proposes a novel drive-by inspection method for spatial offset of HSR bridge based on multi-source data fusion of comprehensive inspection train.Firstly,dung beetle optimizer-variational mode decomposition was employed to achieve adaptive decomposition of non-stationary dynamic signals,and explore the hidden temporal relationships in the data.Subsequently,a long short-term memory neural network was developed to achieve feature fusion of multi-source signal and accurate prediction of spatial settlement of HSR bridge.A dataset of track irregularities and CRH380A high-speed train responses was generated using a 3D train-track-bridge interaction model,and the accuracy and effectiveness of the proposed hybrid deep learning model were numerically validated.Finally,the reliability of the proposed drive-by inspection method was further validated by analyzing the actual measurement data obtained from comprehensive inspection train.The research findings indicate that the proposed approach enables rapid and accurate detection of spatial offset in HSR bridge,ensuring the long-term operational safety of HSR bridges.
基金supported by SDAIA-KFUPM Joint Research Center of Artificial Intelligence,Deanship of Research,King Fahd University of Petroleum and Minerals,under Grant#CAI02562(JRC-AI-RFP-17).
文摘Vehicle re-identification(ReID)is a challenging task in intelligent transportation,and urban surveillance systems due to its complications in camera viewpoints,vehicle scales,and environmental conditions.Recent transformer-based approaches have shown impressive performance by utilizing global dependencies,these models struggle with aspect ratio distortions and may overlook fine-grained local attributes crucial for distinguishing visually similar vehicles.We introduce a framework based on Swin Transformers that addresses these challenges by implementing three components.First,to improve feature robustness and maintain vehicle proportions,our Aspect Ratio-Aware Swin Transformer(AR-Swin)preserve the native ratio via letterbox,uses a non-square(16×8)patch-embedding stem,and keeps fixed 7×7 token windows.Second,we introduce a Dynamic Feature Fusion Network(DFFNet)that adaptively integrates global Swin features with local attribute embeddings;such as color and vehicle type enablingmore discriminative representations.Third,our Regional Attention Blocks incorporate regionalmasks into the transformer’s windowed attentionmechanism,effectively highlighting critical details like manufacturer logos or lights.On VeRi-776,we obtain 82.55 mAP,97.26 Rank-1 and 99.23 Rank-5,and on VehicleID we obtain 91.8 Rank-1 and 97.75 Rank-5.The design is drop-in for Swin backbones and emphasizes robustness without increasing architectural complexity.Code:https://github.com/sft110/Swinvreid.
