The interaction between the airflow and train influences the aerodynamic characteristics and dynamic performance of high-speed trains.This study focused on the fluid-solid coupling effect of airflow and HST,and propos...The interaction between the airflow and train influences the aerodynamic characteristics and dynamic performance of high-speed trains.This study focused on the fluid-solid coupling effect of airflow and HST,and proposed a co-simulation(CS)approach between computational fluid dynamics and multi-body dynamics.Firstly,the aerodynamic model was developed by employing overset mesh technology and the finite volume method,and the detailed train-track coupled dynamic model was established.Then the User Data Protocol was adopted to build data communication channels.Moreover,the proposed CS method was validated by comparison with a reported field test result.Finally,a case study of the HST exiting a tunnel subjected to crosswind was conducted to compare differences between CS and offline simulation(OS)methods.In terms of the presented case,the changing trends of aerodynamic forces and car-body displacements calculated by the two methods were similar.Differences mainly lie in aerodynamic moments and transient wheel-rail impacts.Maximum pitching and yawing moments on the head vehicle in the two methods differ by 21.1 kN∙m and 29.6 kN∙m,respectively.And wheel-rail impacts caused by sudden changes in aerodynamic loads are significantly severer in CS.Wheel-rail safety indices obtained by CS are slightly greater than those by OS.This research proposes a CS method for aerodynamic characteristics and dynamic performance of the HST in complex scenarios,which has superiority in computational efficiency and stability.展开更多
This paper investigates the traffic offloading optimization challenge in Space-Air-Ground Integrated Networks(SAGIN)through a novel Recursive Multi-Agent Proximal Policy Optimization(RMAPPO)algorithm.The exponential g...This paper investigates the traffic offloading optimization challenge in Space-Air-Ground Integrated Networks(SAGIN)through a novel Recursive Multi-Agent Proximal Policy Optimization(RMAPPO)algorithm.The exponential growth of mobile devices and data traffic has substantially increased network congestion,particularly in urban areas and regions with limited terrestrial infrastructure.Our approach jointly optimizes unmanned aerial vehicle(UAV)trajectories and satellite-assisted offloading strategies to simultaneously maximize data throughput,minimize energy consumption,and maintain equitable resource distribution.The proposed RMAPPO framework incorporates recurrent neural networks(RNNs)to model temporal dependencies in UAV mobility patterns and utilizes a decentralized multi-agent reinforcement learning architecture to reduce communication overhead while improving system robustness.The proposed RMAPPO algorithm was evaluated through simulation experiments,with the results indicating that it significantly enhances the cumulative traffic offloading rate of nodes and reduces the energy consumption of UAVs.展开更多
Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakt...Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating In...Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.展开更多
A kind of construction truck model is built in Adams based on multi-body dynamic theory. The rigid and elastic wheels of tire-soil contact models are proposed based on the Bekker pressure model and the Jonasi shear so...A kind of construction truck model is built in Adams based on multi-body dynamic theory. The rigid and elastic wheels of tire-soil contact models are proposed based on the Bekker pressure model and the Jonasi shear soil model, and they are described in the form of S-function to enhance the calculation efficiency and simulation accuracy. Finally, the interaction of truck and soil is simulated by Adams-Maflab co-simulation to study the influence of soft terrain on the ride comfort of vehicles. The co-simulation results reveal that the terrain properties have a great influence on the ride comfort of vehicles as well as driving speed, road roughness and cargo weight. This co-simulation model is convenient for adding the factor of terrain deformation to the analysis of vehicle ride comfort. It can also be used to optimize suspension system parameters especially for off-road vehicles.展开更多
In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural...In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural network proportion-integration-differentiation （PID） control parameters on-line adjustment is utilized to improve system accuracy, celerity and stability. Simulation results indicate that with the control system proposed in this paper, the system deviation is reduced, therefore accuracy is improved; response speed for step signal and sinusoidal signal gets faster, thus acceleration is rapidly improved; and the system can be restored to the control value in case of interfering, so stability is improved.展开更多
Under high-level earthquakes,bridge piers and bearings are prone to be damaged and the elastoplastic state of bridge structural components is easily accessible in the train-track-bridge interaction(TTBI)system.Conside...Under high-level earthquakes,bridge piers and bearings are prone to be damaged and the elastoplastic state of bridge structural components is easily accessible in the train-track-bridge interaction(TTBI)system.Considering the complexity and structural non-linearity of the TTBI system under earthquakes,a single software is not adequate for the coupling analysis.Therefore,in this paper,an interactive method for the TTBI system is proposed by combining the multi-body dynamics software Simpack and the seismic simulation software OpenSees based on the Client-Server architecture,which takes full advantages of the powerful wheel-track contact analysis capabilities of Simpack and the sophisticated nonlinear analysis capabilities of OpenSees.Based on the proposed Simpack and OpenSees co-simulating train-track-bridge(SOTTB)method,a single-span bridge analysis under the earthquake was conducted and the accuracy of co-simulation method was verified by comparing it with results of the finite element model.Finally,the TTBI model is built utilizing the SOTTB method to further discuss the running safety of HST on multi-span simply supported bridges under earthquakes.The results show that the SOTTB method has the advantages of usability,high versatility and accuracy which can be further used to study the running safety of HST under earthquakes with high intensities.展开更多
In order to observe the change and fluctuation in flow and pressure of a hydraulic quadruped robot＇s hydraulic system when the robot walks on trot gait,a co-simulation method based on ADAMS and AMESim is proposed. Fi...In order to observe the change and fluctuation in flow and pressure of a hydraulic quadruped robot＇s hydraulic system when the robot walks on trot gait,a co-simulation method based on ADAMS and AMESim is proposed. Firstly,the change rule in each swing angle of the hydraulic quadruped robot＇s four legs is analyzed and converted to the displacement change of the hydraulic cylinder by calculating their geometric relationship.Secondly,the robot＇s dynamic model is built in ADAMS and its hydraulic and control system models are built in AMESim. The displacement change of the hydraulic cylinder in the hydraulic system is used as the driving function of the dynamics model in ADAMS,and the driving force of the dynamics model is used as the loads of the hydraulic system in AMESim. By introducing the PID closed-loop control in the control system,the co-simulation between hydraulic system and mechanical system is implemented. Finally,the curve of hydraulic cylinders＇ loads,flow and pressure are analyzed and the results show that they fluctuate highly in accordance with the real situation. The study provides data support for the development of a hydraulic quadruped robot＇s physical prototype.展开更多
To study the durability of a passenger car, this work investigates numerical simulation techniques. The investigations are based on an explicit implicit approach in which substructure techniques are used to reduce the...To study the durability of a passenger car, this work investigates numerical simulation techniques. The investigations are based on an explicit implicit approach in which substructure techniques are used to reduce the simulation time, allowing full vehicle dynamic analyses to be performed on a timescale that is dif cult or impossible with the conventional nite element model (FEM). The model used here includes all necessary nonlinearities in order to maintain accuracy. All key components of the car structure are modeled with deformable materials. Tire road interactions are modeled in the explicit package with contact-impact interfaces with arbitrary frictional and geometric properties. Key parameters of the responses of the car driven on six different kinds of test road surfaces are examined and compared with experimental values. It can be concluded that the explicit implicit co-simulation techniques used here are ef cient and accurate enough for engineering purposes. This paper also discusses the limitations of the proposed method and outlines possible improvements for future work.展开更多
Various distributed cooperative control schemes have been widely utilized for cyber-physical power system(CPPS),which only require local communications among geographic neighbors to fulfill certain goals.However,the p...Various distributed cooperative control schemes have been widely utilized for cyber-physical power system(CPPS),which only require local communications among geographic neighbors to fulfill certain goals.However,the process of evaluating the performance of an algorithm for a CPPS can be affected by the physical target characteristics and real communication conditions.To address this potential problem,a testbed with controller hardware-in-the-loop(CHIL)is proposed in this paper.On the basis of a power grid simulation conducted using the real-time simulator RT-LAB developed by the company OPAL-RT,along with a communication network simulation developed with OPNET,multiple distributed controllers were developed with hardware devices to directly collect the real-time operating data of the power system model in RT-LAB and provide local control.Furthermore,the communication between neighboring controllers was realized using the cyber system modelin OPNET with an Ethernet interface.The hardware controllers produced a real-world control behavior instead of a digital simulation,and precisely simulated the dynamic features of a CPPS with high speed.A classic cooperative control case for active power output was studied to explain the integrated simulation process and validate the effectiveness of the co-simulation testbed.展开更多
Based on the characteristics of integrated virtual prototype technology, the mechanical system sub-model, the hydraulic system sub-model and the control system sub-model of a forging manipula- tor system have been bui...Based on the characteristics of integrated virtual prototype technology, the mechanical system sub-model, the hydraulic system sub-model and the control system sub-model of a forging manipula- tor system have been built using a variety of software, and a forging manipulator mtrltidisciplinary co- simulation model has been also built using a method of simulation models interface. Then the simu- lation and experiment are finished, and the result of the experiment is in good agreement with the re- sult of the simulation. It shows that the co-simulation model established can simulate accurately pa- rameter changes in real time during the moving of the forging manipulator such as displacement, ve- locity and pressure flow, which is of important significance for the optimized design of the forging manipulator system to establish the models.展开更多
The virtual prototyping models of the mechanical, hydraulic and control system of the ITER tractor were built with CATIA, ADAMS and MATLAB/Simulink respectively according to its heavy load and high precision character...The virtual prototyping models of the mechanical, hydraulic and control system of the ITER tractor were built with CATIA, ADAMS and MATLAB/Simulink respectively according to its heavy load and high precision characteristics, and the data transfer between the different models was accomplished by the integration interface between different software. Consequently the virtual experimental platform for the multi-disciplinary co-simulation was established. A co-simulation study of the mechanical-hydraulic-control coupling system of the ITER tractor was carried out. The synchronization servo control of parallel hydraulic cylinders was implemented, and the tracking control of the preconcerted trajectory of the hydraulic cylinders was realized on the established experimental platform. This paper presents the optimization design and technology rebuilding for the complicated coupling system with its theoretic foundation and co-simulation virtual experimental platform.展开更多
The 3D model of flapping wing mechanism and veins is constructed in 3D computer aided design (CAD) software UG.Then the co-simulation model is established by using multibody dynamics software ADAMS and MATLAB.The vali...The 3D model of flapping wing mechanism and veins is constructed in 3D computer aided design (CAD) software UG.Then the co-simulation model is established by using multibody dynamics software ADAMS and MATLAB.The validation of this co-simulation model is verified by comparing the simulation results with final experiments.The simulation results and experiments reveal that the relation between flapping frequency and driving voltage of motor is approximately linear under various wingspans.The variance of flapping frequency among different wingspans augments gradually with increasing voltage.Furthermore,the simulation results suggest that flapping frequency is sensitive to wingspan and decreases with increasing wingspan of veins,and the relation between flapping frequency and moment of inertia of veins is also approximately linear for various voltages.展开更多
We reversely analyzed the energy management strategy （EMS） for a single-shaft parallel hybrid electric vehicle （HEV）, and build a forward co-simulation platform based on Cruise and Matlab. The vehicle dynamics mod...We reversely analyzed the energy management strategy （EMS） for a single-shaft parallel hybrid electric vehicle （HEV）, and build a forward co-simulation platform based on Cruise and Matlab. The vehicle dynamics model is built with Cruise, and control model is set up with Matlab/Simulink environment. The data between the two models are transferred by the Matlab API interface in Cruise. After mechanical and signal connections are completed, we establish the computing tasks and take the simulations of vehicle＇ s power performance, economy, and emission performance. The simulation results match the actual measurement results, which show that the co-simulation platform is correct and feasible. The platform can be used not only for a basic simulation platform to optimize further EMS, but also for the development of actual control system.展开更多
A virtual thermal test system was built through the co-simulation using Simulink and Comsol to realize the complete virtualization of the thermal test.Using the co-simulation technology,comprehensive simulation analys...A virtual thermal test system was built through the co-simulation using Simulink and Comsol to realize the complete virtualization of the thermal test.Using the co-simulation technology,comprehensive simulation analysis of the control system,electric field and thermal field was realized.The data state of each observation point could be directly observed at one time,including the output state information of the power amplifier,the output state information of the heater,and the thermal state information of the test unit.The virtual thermal test system has a predictive and guiding role for engineering thermal tests,and can realize thermal environment simulation beyond the existing thermal environment ground simulation capabilities,providing a basis for the development of future models.展开更多
A method, which compares the angular acceleration and vibration spectrums of shafts and gears with physical characteristics of gearbox as tooth numbers and speed ratios, is proposed to find the source of gear rattle v...A method, which compares the angular acceleration and vibration spectrums of shafts and gears with physical characteristics of gearbox as tooth numbers and speed ratios, is proposed to find the source of gear rattle vibration. A mathematical and multi-body dynamics co-simulation model is built to reproduce the gear rattle phenomenon of one typical type of manual transmission. In the model, multi-body dynamics part is used for rotational motion and engagement simulation of gearbox shafts and gears, while mathematical part for control and data processing. The simulation results show that the sound source of the gear rattle from the first gear to the third gear is similar to the experimental results;different parameters like rotating damping, contact stiffness,contact damping, inertia moment and torque fluctuation making effects on gear rattle vibration strength are researched and simulated. The comparison of the simulation and experimental results shows that this method can provide recommendations for solving practical gear rattle problems.展开更多
A hardware-software co-simulation method for system on chip (SOC) design is discussed. It is based on an instruction set simulator (ISS) and an event-driven hardware simulator, and a bus interface model that is descri...A hardware-software co-simulation method for system on chip (SOC) design is discussed. It is based on an instruction set simulator (ISS) and an event-driven hardware simulator, and a bus interface model that is described in C language provides the interface between the two. The bus interface model and the ISS are linked into a singleton program--the software simulator, which communicate with the hardware simulator through Windows sockets. The implementation of the bus interface model and the synchronization between hardware and software simulator are discussed in detail. Co-simulation control of the hardware simulator is also discussed.展开更多
Research on a servo tracking system mounted with a small arm for robot fighting platform based on multi-body system dynamics and intelligent control theory is presented.A multi-body dynamic model which can accurately ...Research on a servo tracking system mounted with a small arm for robot fighting platform based on multi-body system dynamics and intelligent control theory is presented.A multi-body dynamic model which can accurately express dynamic performances of the system is built in ADAMS.In addition,an intelligent PID control model is built with MATLAB/Simulink,and the two models are integrated and co-simulated by the interface of ADAMS/Controls.Simulation experiments indicate that co-simulation technique used for design of the servo tracking system mounted with a small arm can effectively improve its design efficiency,and can also provide theoretical bases for the motion control and performance improvement of the servo tracking system mounted with a small arm.展开更多
In order to analyze the energy consumption of wheel loader during working process, a three-dimensional（3D） model of wheel loader is established by Pro/E software, and it is imported into the software SimulationX tob...In order to analyze the energy consumption of wheel loader during working process, a three-dimensional（3D） model of wheel loader is established by Pro/E software, and it is imported into the software SimulationX tobuild the kinetic model of the whole wheel loader. Meanwhile, the simulation model of hydraulic system is builtby the same software. By integrating the simulation model of hydraulic system with the kinetic model, the co-sim-ulation model of wheel loader could be achieved. The precision of co-simulation model of the working device isverified through the comparison between simulation results and test results. The testing results show that, undernegative loading condition, the energy loss in multi-way valve accounts for about 52%. The important energy lossin loader＇s working hydraulic system using constant displacement pump is the large throttling loss of multi-wayvalves. This study provides a reference for designing of a more energy-efficient hydaulic system of wheel loader.展开更多
基金Supported by the Sichuan Science and Technology Program(Grant No.2023ZDZX0008)the National Natural Science Foundation of China(Grant No.52388102)the New Cornerstone Science Foundation through the XPLORER PRIZE.
文摘The interaction between the airflow and train influences the aerodynamic characteristics and dynamic performance of high-speed trains.This study focused on the fluid-solid coupling effect of airflow and HST,and proposed a co-simulation(CS)approach between computational fluid dynamics and multi-body dynamics.Firstly,the aerodynamic model was developed by employing overset mesh technology and the finite volume method,and the detailed train-track coupled dynamic model was established.Then the User Data Protocol was adopted to build data communication channels.Moreover,the proposed CS method was validated by comparison with a reported field test result.Finally,a case study of the HST exiting a tunnel subjected to crosswind was conducted to compare differences between CS and offline simulation(OS)methods.In terms of the presented case,the changing trends of aerodynamic forces and car-body displacements calculated by the two methods were similar.Differences mainly lie in aerodynamic moments and transient wheel-rail impacts.Maximum pitching and yawing moments on the head vehicle in the two methods differ by 21.1 kN∙m and 29.6 kN∙m,respectively.And wheel-rail impacts caused by sudden changes in aerodynamic loads are significantly severer in CS.Wheel-rail safety indices obtained by CS are slightly greater than those by OS.This research proposes a CS method for aerodynamic characteristics and dynamic performance of the HST in complex scenarios,which has superiority in computational efficiency and stability.
文摘This paper investigates the traffic offloading optimization challenge in Space-Air-Ground Integrated Networks(SAGIN)through a novel Recursive Multi-Agent Proximal Policy Optimization(RMAPPO)algorithm.The exponential growth of mobile devices and data traffic has substantially increased network congestion,particularly in urban areas and regions with limited terrestrial infrastructure.Our approach jointly optimizes unmanned aerial vehicle(UAV)trajectories and satellite-assisted offloading strategies to simultaneously maximize data throughput,minimize energy consumption,and maintain equitable resource distribution.The proposed RMAPPO framework incorporates recurrent neural networks(RNNs)to model temporal dependencies in UAV mobility patterns and utilizes a decentralized multi-agent reinforcement learning architecture to reduce communication overhead while improving system robustness.The proposed RMAPPO algorithm was evaluated through simulation experiments,with the results indicating that it significantly enhances the cumulative traffic offloading rate of nodes and reduces the energy consumption of UAVs.
基金funded by Key research and development Program of Henan Province(No.251111211200)National Natural Science Foundation of China(Grant No.U2004163).
文摘Traffic sign detection is an important part of autonomous driving,and its recognition accuracy and speed are directly related to road traffic safety.Although convolutional neural networks(CNNs)have made certain breakthroughs in this field,in the face of complex scenes,such as image blur and target occlusion,the traffic sign detection continues to exhibit limited accuracy,accompanied by false positives and missed detections.To address the above problems,a traffic sign detection algorithm,You Only Look Once-based Skip Dynamic Way(YOLO-SDW)based on You Only Look Once version 8 small(YOLOv8s),is proposed.Firstly,a Skip Connection Reconstruction(SCR)module is introduced to efficiently integrate fine-grained feature information and enhance the detection accuracy of the algorithm in complex scenes.Secondly,a C2f module based on Dynamic Snake Convolution(C2f-DySnake)is proposed to dynamically adjust the receptive field information,improve the algorithm’s feature extraction ability for blurred or occluded targets,and reduce the occurrence of false detections and missed detections.Finally,the Wise Powerful IoU v2(WPIoUv2)loss function is proposed to further improve the detection accuracy of the algorithm.Experimental results show that the average precision mAP@0.5 of YOLO-SDW on the TT100K dataset is 89.2%,and mAP@0.5:0.95 is 68.5%,which is 4%and 3.3%higher than the YOLOv8s baseline,respectively.YOLO-SDW ensures real-time performance while having higher accuracy.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
文摘Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
基金The National Natural Science Foundation of China(No.50575040)the Natural Science Foundation of Jiangsu Province(No.BK2007112)
文摘A kind of construction truck model is built in Adams based on multi-body dynamic theory. The rigid and elastic wheels of tire-soil contact models are proposed based on the Bekker pressure model and the Jonasi shear soil model, and they are described in the form of S-function to enhance the calculation efficiency and simulation accuracy. Finally, the interaction of truck and soil is simulated by Adams-Maflab co-simulation to study the influence of soft terrain on the ride comfort of vehicles. The co-simulation results reveal that the terrain properties have a great influence on the ride comfort of vehicles as well as driving speed, road roughness and cargo weight. This co-simulation model is convenient for adding the factor of terrain deformation to the analysis of vehicle ride comfort. It can also be used to optimize suspension system parameters especially for off-road vehicles.
文摘In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural network proportion-integration-differentiation （PID） control parameters on-line adjustment is utilized to improve system accuracy, celerity and stability. Simulation results indicate that with the control system proposed in this paper, the system deviation is reduced, therefore accuracy is improved; response speed for step signal and sinusoidal signal gets faster, thus acceleration is rapidly improved; and the system can be restored to the control value in case of interfering, so stability is improved.
基金Project(2020EEEVL0403)supported by the China Earthquake AdministrationProjects(51878674,52022113)supported by the National Natural Science Foundation of ChinaProject(2022ZZTS0670)supported by the Fundamental Research Funds for the Central Universities,China。
文摘Under high-level earthquakes,bridge piers and bearings are prone to be damaged and the elastoplastic state of bridge structural components is easily accessible in the train-track-bridge interaction(TTBI)system.Considering the complexity and structural non-linearity of the TTBI system under earthquakes,a single software is not adequate for the coupling analysis.Therefore,in this paper,an interactive method for the TTBI system is proposed by combining the multi-body dynamics software Simpack and the seismic simulation software OpenSees based on the Client-Server architecture,which takes full advantages of the powerful wheel-track contact analysis capabilities of Simpack and the sophisticated nonlinear analysis capabilities of OpenSees.Based on the proposed Simpack and OpenSees co-simulating train-track-bridge(SOTTB)method,a single-span bridge analysis under the earthquake was conducted and the accuracy of co-simulation method was verified by comparing it with results of the finite element model.Finally,the TTBI model is built utilizing the SOTTB method to further discuss the running safety of HST on multi-span simply supported bridges under earthquakes.The results show that the SOTTB method has the advantages of usability,high versatility and accuracy which can be further used to study the running safety of HST under earthquakes with high intensities.
文摘In order to observe the change and fluctuation in flow and pressure of a hydraulic quadruped robot＇s hydraulic system when the robot walks on trot gait,a co-simulation method based on ADAMS and AMESim is proposed. Firstly,the change rule in each swing angle of the hydraulic quadruped robot＇s four legs is analyzed and converted to the displacement change of the hydraulic cylinder by calculating their geometric relationship.Secondly,the robot＇s dynamic model is built in ADAMS and its hydraulic and control system models are built in AMESim. The displacement change of the hydraulic cylinder in the hydraulic system is used as the driving function of the dynamics model in ADAMS,and the driving force of the dynamics model is used as the loads of the hydraulic system in AMESim. By introducing the PID closed-loop control in the control system,the co-simulation between hydraulic system and mechanical system is implemented. Finally,the curve of hydraulic cylinders＇ loads,flow and pressure are analyzed and the results show that they fluctuate highly in accordance with the real situation. The study provides data support for the development of a hydraulic quadruped robot＇s physical prototype.
文摘To study the durability of a passenger car, this work investigates numerical simulation techniques. The investigations are based on an explicit implicit approach in which substructure techniques are used to reduce the simulation time, allowing full vehicle dynamic analyses to be performed on a timescale that is dif cult or impossible with the conventional nite element model (FEM). The model used here includes all necessary nonlinearities in order to maintain accuracy. All key components of the car structure are modeled with deformable materials. Tire road interactions are modeled in the explicit package with contact-impact interfaces with arbitrary frictional and geometric properties. Key parameters of the responses of the car driven on six different kinds of test road surfaces are examined and compared with experimental values. It can be concluded that the explicit implicit co-simulation techniques used here are ef cient and accurate enough for engineering purposes. This paper also discusses the limitations of the proposed method and outlines possible improvements for future work.
基金the National Key Research and Development Program of China(Basic Research Class)(No.2017YFB0903000)the National Natural Science Foundation of China(No.U1909201).
文摘Various distributed cooperative control schemes have been widely utilized for cyber-physical power system(CPPS),which only require local communications among geographic neighbors to fulfill certain goals.However,the process of evaluating the performance of an algorithm for a CPPS can be affected by the physical target characteristics and real communication conditions.To address this potential problem,a testbed with controller hardware-in-the-loop(CHIL)is proposed in this paper.On the basis of a power grid simulation conducted using the real-time simulator RT-LAB developed by the company OPAL-RT,along with a communication network simulation developed with OPNET,multiple distributed controllers were developed with hardware devices to directly collect the real-time operating data of the power system model in RT-LAB and provide local control.Furthermore,the communication between neighboring controllers was realized using the cyber system modelin OPNET with an Ethernet interface.The hardware controllers produced a real-world control behavior instead of a digital simulation,and precisely simulated the dynamic features of a CPPS with high speed.A classic cooperative control case for active power output was studied to explain the integrated simulation process and validate the effectiveness of the co-simulation testbed.
基金Supported by the National Natural Science Foundation of China(No.51575471)Collaborative Innovation Program Topics of Heavy Machinery of Yanshan University(2011 Program,No.ZX01-20140400-01)
文摘Based on the characteristics of integrated virtual prototype technology, the mechanical system sub-model, the hydraulic system sub-model and the control system sub-model of a forging manipula- tor system have been built using a variety of software, and a forging manipulator mtrltidisciplinary co- simulation model has been also built using a method of simulation models interface. Then the simu- lation and experiment are finished, and the result of the experiment is in good agreement with the re- sult of the simulation. It shows that the co-simulation model established can simulate accurately pa- rameter changes in real time during the moving of the forging manipulator such as displacement, ve- locity and pressure flow, which is of important significance for the optimized design of the forging manipulator system to establish the models.
基金supported by design of the ITER transfer casks system (ITER International Team) ITA 23-01-CNthe Key Laboratory of Biomimetic Sensing and Advanced Robot Technology,Anhui Province,China
文摘The virtual prototyping models of the mechanical, hydraulic and control system of the ITER tractor were built with CATIA, ADAMS and MATLAB/Simulink respectively according to its heavy load and high precision characteristics, and the data transfer between the different models was accomplished by the integration interface between different software. Consequently the virtual experimental platform for the multi-disciplinary co-simulation was established. A co-simulation study of the mechanical-hydraulic-control coupling system of the ITER tractor was carried out. The synchronization servo control of parallel hydraulic cylinders was implemented, and the tracking control of the preconcerted trajectory of the hydraulic cylinders was realized on the established experimental platform. This paper presents the optimization design and technology rebuilding for the complicated coupling system with its theoretic foundation and co-simulation virtual experimental platform.
基金the National Natural Science Foundationof China(No.60375033)
文摘The 3D model of flapping wing mechanism and veins is constructed in 3D computer aided design (CAD) software UG.Then the co-simulation model is established by using multibody dynamics software ADAMS and MATLAB.The validation of this co-simulation model is verified by comparing the simulation results with final experiments.The simulation results and experiments reveal that the relation between flapping frequency and driving voltage of motor is approximately linear under various wingspans.The variance of flapping frequency among different wingspans augments gradually with increasing voltage.Furthermore,the simulation results suggest that flapping frequency is sensitive to wingspan and decreases with increasing wingspan of veins,and the relation between flapping frequency and moment of inertia of veins is also approximately linear for various voltages.
基金Supported by the National High Technology Research and Development Program of China("863"Program),(2011AAllA252)
文摘We reversely analyzed the energy management strategy （EMS） for a single-shaft parallel hybrid electric vehicle （HEV）, and build a forward co-simulation platform based on Cruise and Matlab. The vehicle dynamics model is built with Cruise, and control model is set up with Matlab/Simulink environment. The data between the two models are transferred by the Matlab API interface in Cruise. After mechanical and signal connections are completed, we establish the computing tasks and take the simulations of vehicle＇ s power performance, economy, and emission performance. The simulation results match the actual measurement results, which show that the co-simulation platform is correct and feasible. The platform can be used not only for a basic simulation platform to optimize further EMS, but also for the development of actual control system.
文摘A virtual thermal test system was built through the co-simulation using Simulink and Comsol to realize the complete virtualization of the thermal test.Using the co-simulation technology,comprehensive simulation analysis of the control system,electric field and thermal field was realized.The data state of each observation point could be directly observed at one time,including the output state information of the power amplifier,the output state information of the heater,and the thermal state information of the test unit.The virtual thermal test system has a predictive and guiding role for engineering thermal tests,and can realize thermal environment simulation beyond the existing thermal environment ground simulation capabilities,providing a basis for the development of future models.
文摘A method, which compares the angular acceleration and vibration spectrums of shafts and gears with physical characteristics of gearbox as tooth numbers and speed ratios, is proposed to find the source of gear rattle vibration. A mathematical and multi-body dynamics co-simulation model is built to reproduce the gear rattle phenomenon of one typical type of manual transmission. In the model, multi-body dynamics part is used for rotational motion and engagement simulation of gearbox shafts and gears, while mathematical part for control and data processing. The simulation results show that the sound source of the gear rattle from the first gear to the third gear is similar to the experimental results;different parameters like rotating damping, contact stiffness,contact damping, inertia moment and torque fluctuation making effects on gear rattle vibration strength are researched and simulated. The comparison of the simulation and experimental results shows that this method can provide recommendations for solving practical gear rattle problems.
文摘A hardware-software co-simulation method for system on chip (SOC) design is discussed. It is based on an instruction set simulator (ISS) and an event-driven hardware simulator, and a bus interface model that is described in C language provides the interface between the two. The bus interface model and the ISS are linked into a singleton program--the software simulator, which communicate with the hardware simulator through Windows sockets. The implementation of the bus interface model and the synchronization between hardware and software simulator are discussed in detail. Co-simulation control of the hardware simulator is also discussed.
基金Sponsored by the Independent Research Foundation of State Key Laboratory(ZDKT08-05)the Ministerial Level Research Foundation(06104040)
文摘Research on a servo tracking system mounted with a small arm for robot fighting platform based on multi-body system dynamics and intelligent control theory is presented.A multi-body dynamic model which can accurately express dynamic performances of the system is built in ADAMS.In addition,an intelligent PID control model is built with MATLAB/Simulink,and the two models are integrated and co-simulated by the interface of ADAMS/Controls.Simulation experiments indicate that co-simulation technique used for design of the servo tracking system mounted with a small arm can effectively improve its design efficiency,and can also provide theoretical bases for the motion control and performance improvement of the servo tracking system mounted with a small arm.
文摘In order to analyze the energy consumption of wheel loader during working process, a three-dimensional（3D） model of wheel loader is established by Pro/E software, and it is imported into the software SimulationX tobuild the kinetic model of the whole wheel loader. Meanwhile, the simulation model of hydraulic system is builtby the same software. By integrating the simulation model of hydraulic system with the kinetic model, the co-sim-ulation model of wheel loader could be achieved. The precision of co-simulation model of the working device isverified through the comparison between simulation results and test results. The testing results show that, undernegative loading condition, the energy loss in multi-way valve accounts for about 52%. The important energy lossin loader＇s working hydraulic system using constant displacement pump is the large throttling loss of multi-wayvalves. This study provides a reference for designing of a more energy-efficient hydaulic system of wheel loader.
