In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is design...In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.展开更多
Weather is a key factor affecting the control of air traffic.Accurate recognition and classification of similar weather scenes in the terminal area is helpful for rapid decision-making in air trafficflow management.Curren...Weather is a key factor affecting the control of air traffic.Accurate recognition and classification of similar weather scenes in the terminal area is helpful for rapid decision-making in air trafficflow management.Current researches mostly use traditional machine learning methods to extract features of weather scenes,and clustering algorithms to divide similar scenes.Inspired by the excellent performance of deep learning in image recognition,this paper proposes a terminal area similar weather scene classification method based on improved deep convolution embedded clustering(IDCEC),which uses the com-bination of the encoding layer and the decoding layer to reduce the dimensionality of the weather image,retaining useful information to the greatest extent,and then uses the combination of the pre-trained encoding layer and the clustering layer to train the clustering model of the similar scenes in the terminal area.Finally,term-inal area of Guangzhou Airport is selected as the research object,the method pro-posed in this article is used to classify historical weather data in similar scenes,and the performance is compared with other state-of-the-art methods.The experi-mental results show that the proposed IDCEC method can identify similar scenes more accurately based on the spatial distribution characteristics and severity of weather;at the same time,compared with the actualflight volume in the Guangz-hou terminal area,IDCEC's recognition results of similar weather scenes are con-sistent with the recognition of experts in thefield.展开更多
Conflict resolution(CR)is a fundamental component of air traffic management,where recent progress in artificial intelligence has led to the effective application of deep reinforcement learning(DRL)techniques to enhanc...Conflict resolution(CR)is a fundamental component of air traffic management,where recent progress in artificial intelligence has led to the effective application of deep reinforcement learning(DRL)techniques to enhance CR strategies.However,existing DRL models applied to CR are often limited to simple scenarios.This approach frequently leads to the neglect of the high risks associated with multiple intersections in the high-density and multi-airport system terminal area(MAS-TMA),and suffers from poor interpretability.This paper addresses the aforementioned gap by introducing an improved multi-agent DRL model that adopted to autonomous CR(AutoCR)within MAS-TMA.Specifically,dynamic weather conditions are incorporated into the state space to enhance adaptability.In the action space,the flight intent is considered and transformed into optimal maneuvers according to overload,thus improving interpretability.On these bases,the deep Q-network(DQN)algorithm is further improved to address the AutoCR problem in MAS-TMA.Simulation experiments conducted in the“Guangdong-Hong Kong-Macao”greater bay area(GBA)MAS-TMA demonstrate the effectiveness of the proposed method,successfully resolving over eight potential conflicts and performing robustly across various air traffic densities.展开更多
Continental reconstructions in Central Asia are represented by orogenesis along some large orogenic belts in the Altaid collage （Fig. 1 ） or Central Asian Orogenic Belt （CAOB）, which separate the East European and...Continental reconstructions in Central Asia are represented by orogenesis along some large orogenic belts in the Altaid collage （Fig. 1 ） or Central Asian Orogenic Belt （CAOB）, which separate the East European and Siberian cratons to the north from the Tarim and North China cratons to the south （$eng0r et al,, 1993; Jahn et al., 2004; Windley et al., 2007; Qu et al., 2008; Xiao et al., 2010; Xiao and Santosh, 2014）. The Altaid Collage was characterized by complex long tectonic and structural evolution from at least ca. 1.0 Ga to late Paleozoic-early Mesozoic with considerable continental growth （Khain et al., 2002; Jahn et al., 2004; Xiao et al., 2009, 2014; KrOner et al., 2014）, followed by Cenozoic intracontinental evolution related to far-field effect of the collision of the In- dian Plate to the Eurasian Accompanying with these complex world-class ore deposits developed 2001; Goldfarb et al., 2003, 2014）. Plate （Cunningham, 2005）. geodynamic evolutions, many （Qin, 2000; Yakubchuk et al,2001; Goldfarb et al., 2003, 2014）.展开更多
Work-zone crashes have always drawn public attention. A number of fatalities are recorded every year nationwide within work zone areas. Most existing countermeasures have been dedicated more to the advance warning are...Work-zone crashes have always drawn public attention. A number of fatalities are recorded every year nationwide within work zone areas. Most existing countermeasures have been dedicated more to the advance warning areas, transition areas, and activity areas of work zone, than the termination areas, where drivers might play less attention to safety threats. In this study, the vehicle-to-vehicle communication based left turn warning system was applied at a work zone termination area, which is immediately followed by a T-intersection. The work-zone is located on the minor road side, while left turn vehicles will be appearing from the major street through the said T-intersection. A smart phone application was designed using Android coding system to provide several types of warning messages to drivers. Corresponding scenarios were designed in a driving simulator, and 20 subjects were recruited to participate in the simulation test followed by a questionnaire survey. The subjects received a warning message when driving to the termination area of a work zone on the coming left turn vehicles. Twenty test drivers’ driving speed, acceleration rates, and break reaction distance to the warning messages were studied in four different scenarios. Results show that the smartphone application has a great impact on driving behaviors, especially the female voice and the beep tone warning, which are recommended for possible field tests. Besides, the developed smartphone applications can be further updated for practical applications of similar needs.展开更多
In order to alleviate the flight congestion in terminal areas(TMAs),it is of great significance to develop an effective method.An arrival sequencing model based on the serial point merge systems(PMSs)is constructed to...In order to alleviate the flight congestion in terminal areas(TMAs),it is of great significance to develop an effective method.An arrival sequencing model based on the serial point merge systems(PMSs)is constructed to improve the operational benefits of arrival flights.The approach of first come first service(FCFS)combined with the method of constraint position shift(CPS)is used as the sequencing strategy.Through the simulated annealing algorithm,the results show that the arrival flights sequencing through serial PMSs has significant advantages in reducing delays and increasing runway throughput especially in the case of high traffic loads.The proposed approach is conducive in promoting the implementation and application of serial PMS.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
基金supported by the Fundamental Research Funds for the Central Universities(NOS.NS2019054,NS2020045)。
文摘In order to improve the recognition accuracy of similar weather scenarios(SWSs)in terminal area,a recognition model for SWS based on contrastive learning(SWS-CL)is proposed.Firstly,a data augmentation method is designed to improve the number and quality of weather scenarios samples according to the characteristics of convective weather images.Secondly,in the pre-trained recognition model of SWS-CL,a loss function is formulated to minimize the distance between the anchor and positive samples,and maximize the distance between the anchor and the negative samples in the latent space.Finally,the pre-trained SWS-CL model is fine-tuned with labeled samples to improve the recognition accuracy of SWS.The comparative experiments on the weather images of Guangzhou terminal area show that the proposed data augmentation method can effectively improve the quality of weather image dataset,and the proposed SWS-CL model can achieve satisfactory recognition accuracy.It is also verified that the fine-tuned SWS-CL model has obvious advantages in datasets with sparse labels.
基金supported by the Fundamental Research Funds for the CentralUniversities under Grant NS2020045. Y.L.G received the grant.
文摘Weather is a key factor affecting the control of air traffic.Accurate recognition and classification of similar weather scenes in the terminal area is helpful for rapid decision-making in air trafficflow management.Current researches mostly use traditional machine learning methods to extract features of weather scenes,and clustering algorithms to divide similar scenes.Inspired by the excellent performance of deep learning in image recognition,this paper proposes a terminal area similar weather scene classification method based on improved deep convolution embedded clustering(IDCEC),which uses the com-bination of the encoding layer and the decoding layer to reduce the dimensionality of the weather image,retaining useful information to the greatest extent,and then uses the combination of the pre-trained encoding layer and the clustering layer to train the clustering model of the similar scenes in the terminal area.Finally,term-inal area of Guangzhou Airport is selected as the research object,the method pro-posed in this article is used to classify historical weather data in similar scenes,and the performance is compared with other state-of-the-art methods.The experi-mental results show that the proposed IDCEC method can identify similar scenes more accurately based on the spatial distribution characteristics and severity of weather;at the same time,compared with the actualflight volume in the Guangz-hou terminal area,IDCEC's recognition results of similar weather scenes are con-sistent with the recognition of experts in thefield.
基金supported by the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX25_0621)the Foundation of Inter-disciplinary Innovation Fund for Doctoral Students of Nanjing University of Aeronautics and Astronautics(No.KXKCXJJ202507)。
文摘Conflict resolution(CR)is a fundamental component of air traffic management,where recent progress in artificial intelligence has led to the effective application of deep reinforcement learning(DRL)techniques to enhance CR strategies.However,existing DRL models applied to CR are often limited to simple scenarios.This approach frequently leads to the neglect of the high risks associated with multiple intersections in the high-density and multi-airport system terminal area(MAS-TMA),and suffers from poor interpretability.This paper addresses the aforementioned gap by introducing an improved multi-agent DRL model that adopted to autonomous CR(AutoCR)within MAS-TMA.Specifically,dynamic weather conditions are incorporated into the state space to enhance adaptability.In the action space,the flight intent is considered and transformed into optimal maneuvers according to overload,thus improving interpretability.On these bases,the deep Q-network(DQN)algorithm is further improved to address the AutoCR problem in MAS-TMA.Simulation experiments conducted in the“Guangdong-Hong Kong-Macao”greater bay area(GBA)MAS-TMA demonstrate the effectiveness of the proposed method,successfully resolving over eight potential conflicts and performing robustly across various air traffic densities.
基金financially supported by the Natural National Science Foundation of China(Grant Nos.41230207,41202150, 41472192,41390441 and 41190075)
文摘Continental reconstructions in Central Asia are represented by orogenesis along some large orogenic belts in the Altaid collage （Fig. 1 ） or Central Asian Orogenic Belt （CAOB）, which separate the East European and Siberian cratons to the north from the Tarim and North China cratons to the south （$eng0r et al,, 1993; Jahn et al., 2004; Windley et al., 2007; Qu et al., 2008; Xiao et al., 2010; Xiao and Santosh, 2014）. The Altaid Collage was characterized by complex long tectonic and structural evolution from at least ca. 1.0 Ga to late Paleozoic-early Mesozoic with considerable continental growth （Khain et al., 2002; Jahn et al., 2004; Xiao et al., 2009, 2014; KrOner et al., 2014）, followed by Cenozoic intracontinental evolution related to far-field effect of the collision of the In- dian Plate to the Eurasian Accompanying with these complex world-class ore deposits developed 2001; Goldfarb et al., 2003, 2014）. Plate （Cunningham, 2005）. geodynamic evolutions, many （Qin, 2000; Yakubchuk et al,2001; Goldfarb et al., 2003, 2014）.
文摘Work-zone crashes have always drawn public attention. A number of fatalities are recorded every year nationwide within work zone areas. Most existing countermeasures have been dedicated more to the advance warning areas, transition areas, and activity areas of work zone, than the termination areas, where drivers might play less attention to safety threats. In this study, the vehicle-to-vehicle communication based left turn warning system was applied at a work zone termination area, which is immediately followed by a T-intersection. The work-zone is located on the minor road side, while left turn vehicles will be appearing from the major street through the said T-intersection. A smart phone application was designed using Android coding system to provide several types of warning messages to drivers. Corresponding scenarios were designed in a driving simulator, and 20 subjects were recruited to participate in the simulation test followed by a questionnaire survey. The subjects received a warning message when driving to the termination area of a work zone on the coming left turn vehicles. Twenty test drivers’ driving speed, acceleration rates, and break reaction distance to the warning messages were studied in four different scenarios. Results show that the smartphone application has a great impact on driving behaviors, especially the female voice and the beep tone warning, which are recommended for possible field tests. Besides, the developed smartphone applications can be further updated for practical applications of similar needs.
基金supported by the National Natural Science Foundation of China(No.U1933119)the Foundation of Graduate Innovation Center in Nanjing University of Aeronautics and Astronautics(No.xcxjh20210703)
文摘In order to alleviate the flight congestion in terminal areas(TMAs),it is of great significance to develop an effective method.An arrival sequencing model based on the serial point merge systems(PMSs)is constructed to improve the operational benefits of arrival flights.The approach of first come first service(FCFS)combined with the method of constraint position shift(CPS)is used as the sequencing strategy.Through the simulated annealing algorithm,the results show that the arrival flights sequencing through serial PMSs has significant advantages in reducing delays and increasing runway throughput especially in the case of high traffic loads.The proposed approach is conducive in promoting the implementation and application of serial PMS.
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.
