1. Background Driven by ongoing economic expansion and low-altitude aviation development, the global air transportation industry has experienced significant growth in recent decades, resulting in increasing airspace c...1. Background Driven by ongoing economic expansion and low-altitude aviation development, the global air transportation industry has experienced significant growth in recent decades, resulting in increasing airspace complexity, and considerable challenges for Air Traffic Control(ATC). As the fundamental technique of the ATC system, Flight Trajectory Prediction(FTP) forecasts future traffic dynamics to support critical applications(such as conflict detection), and also serves as a cornerstone for future Trajectory-based Operations(TBO).展开更多
With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intellig...With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intelligent SA(ISA).However,the existing AI-based SA approaches often rely on unimodal data and lack a comprehensive description and benchmark of the ISA tasks utilizing multi-modal data for real-time ATC environments.To address this gap,by analyzing the situation awareness procedure of the ATCOs,the ISA task is refined to the processing of the two primary elements,i.e.,spoken instructions and flight trajectories.Subsequently,the ISA is further formulated into Controlling Intent Understanding(CIU)and Flight Trajectory Prediction(FTP)tasks.For the CIU task,an innovative automatic speech recognition and understanding framework is designed to extract the controlling intent from unstructured and continuous ATC communications.For the FTP task,the single-and multi-horizon FTP approaches are investigated to support the high-precision prediction of the situation evolution.A total of 32 unimodal/multi-modal advanced methods with extensive evaluation metrics are introduced to conduct the benchmarks on the real-world multi-modal ATC situation dataset.Experimental results demonstrate the effectiveness of AI-based techniques in enhancing ISA for the ATC environment.展开更多
Inside the terminal maneuvering area(TMA),flight trajectories need to be determined to maintain safe and efficient arrival operations.Air traffic control officers(ATCOs)devise trajectories and provide instructions to ...Inside the terminal maneuvering area(TMA),flight trajectories need to be determined to maintain safe and efficient arrival operations.Air traffic control officers(ATCOs)devise trajectories and provide instructions to pilots.The subjectivity involved in the decision-making exposes operational efficiency to factors such as workload,experience,and TMA complexity.Suboptimal trajectory solutions can increase arrival transit times,i.e.,the time spent from entering TMA to landing,leading to congestion and flight delays.These adverse effects are particularly critical during peak hours.While existing methods provide efficient trajectory solutions,they often overlook critical embedded features that constitute trajectory solution feasibility in real operations.To address these challenges,we propose a trajectory grafting method to generate high-fidelity,feature-embedded trajectories compatible with existing air traffic management systems.Trajectory grafting utilizes historical trajectory segments as components to construct situational flight trajectories that conform to given traffic dynamics and constraints.Collectively,these trajectory segments constitute a feasible design space,thereby eliminating the need to explicitly model operational constraints,flight physics,and ATCOs’workload.Our results demonstrate the benefits of this method,which reduces the average arrival transit time by 3%during peak hours.The benefits are further amplified by its compound effect,with up to 24%reductions in accumulated arrival transit times.展开更多
The rapid development of the aviation industry urgently requires airspace traffic management,and flight trajectory prediction is a core component of airspace traffic management.Flight trajectory is a multidimensional ...The rapid development of the aviation industry urgently requires airspace traffic management,and flight trajectory prediction is a core component of airspace traffic management.Flight trajectory is a multidimensional time series with rich spatio-temporal characteristics,and existing flight trajectory prediction methods only target the trajectory point temporal relationships,but not the implicit interrelationships among the trajectory point attributes.In this paper,a graph convolutional network(AR-GCN)based on the intra-attribute relationships is proposed for solving the flight track prediction problem.First,the network extracts the temporal features of each attribute and fuses them with the original features of the attribute to obtain the enhanced attribute features,then extracts the implicit relationships between attributes as inter-attribute relationship features.Secondly,the enhanced attribute features are used as nodes and the inter-attribute relationship features are used as edges to construct the inter-attribute relationship graph.Finally,the graph convolutional network is used to aggregate the attribute features.Based on the full fusion of the above features,we achieved high accuracy prediction of the trajectory.In this paper,experiments are conducted on ADS-B historical track data.We compare our method with the classical method and the proposed method.Experimental results show that our method achieves significant improvement in prediction accuracy.展开更多
With the objective of reducing the flight cost and the amount of polluting emissions released in the atmosphere, a new optimization algorithm considering the climb, cruise and descent phases is presented for the refer...With the objective of reducing the flight cost and the amount of polluting emissions released in the atmosphere, a new optimization algorithm considering the climb, cruise and descent phases is presented for the reference vertical flight trajectory. The selection of the reference vertical navigation speeds and altitudes was solved as a discrete combinatory problem by means of a graphtree passing through nodes using the beam search optimization technique. To achieve a compromise between the execution time and the algorithm＇s ability to find the global optimal solution, a heuristic methodology introducing a parameter called ‘‘optimism coefficient was used in order to estimate the trajectory＇s flight cost at every node. The optimal trajectory cost obtained with the developed algorithm was compared with the cost of the optimal trajectory provided by a commercial flight management system（FMS）. The global optimal solution was validated against an exhaustive search algorithm（ESA）, other than the proposed algorithm. The developed algorithm takes into account weather effects, step climbs during cruise and air traffic management constraints such as constant altitude segments, constant cruise Mach, and a pre-defined reference lateral navigation route. The aircraft fuel burn was computed using a numerical performance model which was created and validated using flight test experimental data.展开更多
As actively sensing animals guided by acoustic information, echolocating bats must adapt their vocal–motor behavior to various environmentsand behavioral tasks. Here, we investigated how the temporal patterns of echo...As actively sensing animals guided by acoustic information, echolocating bats must adapt their vocal–motor behavior to various environmentsand behavioral tasks. Here, we investigated how the temporal patterns of echolocation and flight behavior were adjusted in 2 species of batswith a high duty cycle (HDC) call structure, Rhinolophus ferrumequinum and Hipposideros armiger, when they flew along a straight corridorand then passed through windows of 3 different sizes. We also tested whether divergence existed in the adaptations of the 2 species. Both H.armiger and R. ferrumequinum increased their call rates by shortening the pulse duration and inter-pulse interval for more rapid spatial samplingof the environment when flying through smaller windows. Bats produced more sonar sound groups (SSGs) while maintaining a stable proportion of calls that made up SSGs during approaches to smaller windows. The 2 species showed divergent adjustment in flight behavior across3 different window sizes. Hipposideros armiger reduced its flight speed to pass through smaller windows while R. ferrumequinum increasedits flight speed. Our results suggest that these 2 species of HDC bats adopt similar acoustic timing patterns for different tasks although theyperformed different flight behaviors.展开更多
As one of the important components of computational flight mechanics and control,numerical algorithms of trajectory optimization for flight vehicles are currently studied by many researchers in aerospace engineering t...As one of the important components of computational flight mechanics and control,numerical algorithms of trajectory optimization for flight vehicles are currently studied by many researchers in aerospace engineering to completely solve these difficult problems,but few papers on the survey of this research field have been published recently.Based on the investigation of more than one hundred literatures,considering the application perspectives of computational flight mechanics and recent developments of trajectory optimization,the numerical algorithms of trajectory optimizations for aerospace vehicles are summarized and systematically analyzed.This paper summarized the basic principle,characteristics and application for all kinds of current trajectory optimization algorithms;and introduced some new methods and theories appearing in recent years.Finally,collaborative trajectory optimization for many flight vehicles,and hypersonic vehicle trajectory optimization were mainly reviewed in this paper.In the conclusion of this paper,the future research properties are presented regarding to numerical algorithms of trajectory optimization and control for flight vehicles as follows:collaboration and antagonization for many flight vehicles and multiple targets,global,real-time online,high accuracy of 7-D trajectory,considering all kinds of unknown random disturbances in trajectory optimization,and so on.展开更多
A new Kinetic Energy Rod( KER) warhead named profiled rod warhead is proposed in this paper.Based on the design of profiled rod warhead,a model of profiled rod driven by detonation is established. The detonation proce...A new Kinetic Energy Rod( KER) warhead named profiled rod warhead is proposed in this paper.Based on the design of profiled rod warhead,a model of profiled rod driven by detonation is established. The detonation process is simulated by ANSYS / LS-DYNA,and the deployment velocity and initial flight attitude of rod are achieved. In addition,static rod deployment testing are performed to investigate the damage effect,the spatial flight attitude and deployment velocity. A satisfactory agreement is obtained by the comparison between numerical results and testing results. Meanwhile,the profiled rod studies are conducted to determine a higher penetrability compared with traditional cylindrical rods. Rigid body dynamics equations of profiled rod,which accounts for the influence of air resistance,are set up to predict the flight trajectory of long-distance. The results show that the profiled rod may provide a better penetration angle which still maintains a significant penetrability against projectiles when the rods move off long-distance range.展开更多
文摘1. Background Driven by ongoing economic expansion and low-altitude aviation development, the global air transportation industry has experienced significant growth in recent decades, resulting in increasing airspace complexity, and considerable challenges for Air Traffic Control(ATC). As the fundamental technique of the ATC system, Flight Trajectory Prediction(FTP) forecasts future traffic dynamics to support critical applications(such as conflict detection), and also serves as a cornerstone for future Trajectory-based Operations(TBO).
基金supported by the National Natural Science Foundation of China(Nos.62371323,62401380,U2433217,U2333209,and U20A20161)Natural Science Foundation of Sichuan Province,China(Nos.2025ZNSFSC1476)+2 种基金Sichuan Science and Technology Program,China(Nos.2024YFG0010 and 2024ZDZX0046)the Institutional Research Fund from Sichuan University(Nos.2024SCUQJTX030)the Open Fund of Key Laboratory of Flight Techniques and Flight Safety,CAAC(Nos.GY2024-01A).
文摘With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intelligent SA(ISA).However,the existing AI-based SA approaches often rely on unimodal data and lack a comprehensive description and benchmark of the ISA tasks utilizing multi-modal data for real-time ATC environments.To address this gap,by analyzing the situation awareness procedure of the ATCOs,the ISA task is refined to the processing of the two primary elements,i.e.,spoken instructions and flight trajectories.Subsequently,the ISA is further formulated into Controlling Intent Understanding(CIU)and Flight Trajectory Prediction(FTP)tasks.For the CIU task,an innovative automatic speech recognition and understanding framework is designed to extract the controlling intent from unstructured and continuous ATC communications.For the FTP task,the single-and multi-horizon FTP approaches are investigated to support the high-precision prediction of the situation evolution.A total of 32 unimodal/multi-modal advanced methods with extensive evaluation metrics are introduced to conduct the benchmarks on the real-world multi-modal ATC situation dataset.Experimental results demonstrate the effectiveness of AI-based techniques in enhancing ISA for the ATC environment.
基金funded by the Hong Kong Research Grants Council General Research Fund(Project No.11209717).
文摘Inside the terminal maneuvering area(TMA),flight trajectories need to be determined to maintain safe and efficient arrival operations.Air traffic control officers(ATCOs)devise trajectories and provide instructions to pilots.The subjectivity involved in the decision-making exposes operational efficiency to factors such as workload,experience,and TMA complexity.Suboptimal trajectory solutions can increase arrival transit times,i.e.,the time spent from entering TMA to landing,leading to congestion and flight delays.These adverse effects are particularly critical during peak hours.While existing methods provide efficient trajectory solutions,they often overlook critical embedded features that constitute trajectory solution feasibility in real operations.To address these challenges,we propose a trajectory grafting method to generate high-fidelity,feature-embedded trajectories compatible with existing air traffic management systems.Trajectory grafting utilizes historical trajectory segments as components to construct situational flight trajectories that conform to given traffic dynamics and constraints.Collectively,these trajectory segments constitute a feasible design space,thereby eliminating the need to explicitly model operational constraints,flight physics,and ATCOs’workload.Our results demonstrate the benefits of this method,which reduces the average arrival transit time by 3%during peak hours.The benefits are further amplified by its compound effect,with up to 24%reductions in accumulated arrival transit times.
文摘The rapid development of the aviation industry urgently requires airspace traffic management,and flight trajectory prediction is a core component of airspace traffic management.Flight trajectory is a multidimensional time series with rich spatio-temporal characteristics,and existing flight trajectory prediction methods only target the trajectory point temporal relationships,but not the implicit interrelationships among the trajectory point attributes.In this paper,a graph convolutional network(AR-GCN)based on the intra-attribute relationships is proposed for solving the flight track prediction problem.First,the network extracts the temporal features of each attribute and fuses them with the original features of the attribute to obtain the enhanced attribute features,then extracts the implicit relationships between attributes as inter-attribute relationship features.Secondly,the enhanced attribute features are used as nodes and the inter-attribute relationship features are used as edges to construct the inter-attribute relationship graph.Finally,the graph convolutional network is used to aggregate the attribute features.Based on the full fusion of the above features,we achieved high accuracy prediction of the trajectory.In this paper,experiments are conducted on ADS-B historical track data.We compare our method with the classical method and the proposed method.Experimental results show that our method achieves significant improvement in prediction accuracy.
基金the team of the Business-led Network of Centers of Excellence Green Aviation Research & Development Network (GARDN)in particular Mr. Sylvan Cofsky, for the funds received for this project (GARDNⅡ–Project: CMC-21)conducted at The Research Laboratory in Active Controls, Avionics and Aeroservoelasticity (LARCASE) in the framework of the global project ‘‘Optimized Descent and Cruise”
文摘With the objective of reducing the flight cost and the amount of polluting emissions released in the atmosphere, a new optimization algorithm considering the climb, cruise and descent phases is presented for the reference vertical flight trajectory. The selection of the reference vertical navigation speeds and altitudes was solved as a discrete combinatory problem by means of a graphtree passing through nodes using the beam search optimization technique. To achieve a compromise between the execution time and the algorithm＇s ability to find the global optimal solution, a heuristic methodology introducing a parameter called ‘‘optimism coefficient was used in order to estimate the trajectory＇s flight cost at every node. The optimal trajectory cost obtained with the developed algorithm was compared with the cost of the optimal trajectory provided by a commercial flight management system（FMS）. The global optimal solution was validated against an exhaustive search algorithm（ESA）, other than the proposed algorithm. The developed algorithm takes into account weather effects, step climbs during cruise and air traffic management constraints such as constant altitude segments, constant cruise Mach, and a pre-defined reference lateral navigation route. The aircraft fuel burn was computed using a numerical performance model which was created and validated using flight test experimental data.
基金supported by the National Natural Science Foundation of China(Grant No.31770429 and 32071492)the National Defense Basic Scientific Research Project of China(Grant No.C019220023).
文摘As actively sensing animals guided by acoustic information, echolocating bats must adapt their vocal–motor behavior to various environmentsand behavioral tasks. Here, we investigated how the temporal patterns of echolocation and flight behavior were adjusted in 2 species of batswith a high duty cycle (HDC) call structure, Rhinolophus ferrumequinum and Hipposideros armiger, when they flew along a straight corridorand then passed through windows of 3 different sizes. We also tested whether divergence existed in the adaptations of the 2 species. Both H.armiger and R. ferrumequinum increased their call rates by shortening the pulse duration and inter-pulse interval for more rapid spatial samplingof the environment when flying through smaller windows. Bats produced more sonar sound groups (SSGs) while maintaining a stable proportion of calls that made up SSGs during approaches to smaller windows. The 2 species showed divergent adjustment in flight behavior across3 different window sizes. Hipposideros armiger reduced its flight speed to pass through smaller windows while R. ferrumequinum increasedits flight speed. Our results suggest that these 2 species of HDC bats adopt similar acoustic timing patterns for different tasks although theyperformed different flight behaviors.
基金supported by the Fundatmental Research Funds for the Central Universities of China (Grant No. CXZZ11_0215)
文摘As one of the important components of computational flight mechanics and control,numerical algorithms of trajectory optimization for flight vehicles are currently studied by many researchers in aerospace engineering to completely solve these difficult problems,but few papers on the survey of this research field have been published recently.Based on the investigation of more than one hundred literatures,considering the application perspectives of computational flight mechanics and recent developments of trajectory optimization,the numerical algorithms of trajectory optimizations for aerospace vehicles are summarized and systematically analyzed.This paper summarized the basic principle,characteristics and application for all kinds of current trajectory optimization algorithms;and introduced some new methods and theories appearing in recent years.Finally,collaborative trajectory optimization for many flight vehicles,and hypersonic vehicle trajectory optimization were mainly reviewed in this paper.In the conclusion of this paper,the future research properties are presented regarding to numerical algorithms of trajectory optimization and control for flight vehicles as follows:collaboration and antagonization for many flight vehicles and multiple targets,global,real-time online,high accuracy of 7-D trajectory,considering all kinds of unknown random disturbances in trajectory optimization,and so on.
基金Sponsored by the CALT University Joint Fund(Grant No.CALT201105)
文摘A new Kinetic Energy Rod( KER) warhead named profiled rod warhead is proposed in this paper.Based on the design of profiled rod warhead,a model of profiled rod driven by detonation is established. The detonation process is simulated by ANSYS / LS-DYNA,and the deployment velocity and initial flight attitude of rod are achieved. In addition,static rod deployment testing are performed to investigate the damage effect,the spatial flight attitude and deployment velocity. A satisfactory agreement is obtained by the comparison between numerical results and testing results. Meanwhile,the profiled rod studies are conducted to determine a higher penetrability compared with traditional cylindrical rods. Rigid body dynamics equations of profiled rod,which accounts for the influence of air resistance,are set up to predict the flight trajectory of long-distance. The results show that the profiled rod may provide a better penetration angle which still maintains a significant penetrability against projectiles when the rods move off long-distance range.
