E. Dunkel, Jason Swope, Alberto Candela, Lauren West, Steve Ankuo Chien, Zaid Towfic, Léonie Buckley, Juan Romero-Cañas, José Luis Espinosa-Aranda, Elena Hervas-Martin, Mark Fernandez
Future space missions can benefit from processing imagery on board to detect science events, create insights, and respond autonomously. One of the challenges to this mission concept is that traditional space flight computing has limited capabilities because it is derived from much older computing to ensure reliable performance in the extreme environments of space: particularly radiation. Modern commercial-off-the-shelf processors, such as the Movidius Myriad X and the Qualcomm Snapdragon, provide significant improvements in small size, weight, and power packaging; and they offer direct hardware acceleration for deep neural networks, although these processors are not radiation hardened. We deploy neural network models on these processors hosted by Hewlett Packard Enterprise’s Spaceborne Computer-2 on board the International Space Station (ISS). We find that the Myriad and Snapdragon digital signal processors (DSP)/artificial intelligence processors (AIP) provide speed improvement over the Snapdragon CPU in all cases except single-pixel networks (typically greater than 10 times for DSP/AIP). In addition, the discrepancy introduced through quantization and porting of our Jet Propulsion Laboratory models was usually quite low (less than 5%). Models were run multiple times, and memory checkers were deployed to test for radiation effects. To date, we have found no difference in output between ground and ISS runs, and no memory checker errors.
{"title":"Benchmarking Deep Learning Models on Myriad and Snapdragon Processors for Space Applications","authors":"E. Dunkel, Jason Swope, Alberto Candela, Lauren West, Steve Ankuo Chien, Zaid Towfic, Léonie Buckley, Juan Romero-Cañas, José Luis Espinosa-Aranda, Elena Hervas-Martin, Mark Fernandez","doi":"10.2514/1.i011216","DOIUrl":"https://doi.org/10.2514/1.i011216","url":null,"abstract":"Future space missions can benefit from processing imagery on board to detect science events, create insights, and respond autonomously. One of the challenges to this mission concept is that traditional space flight computing has limited capabilities because it is derived from much older computing to ensure reliable performance in the extreme environments of space: particularly radiation. Modern commercial-off-the-shelf processors, such as the Movidius Myriad X and the Qualcomm Snapdragon, provide significant improvements in small size, weight, and power packaging; and they offer direct hardware acceleration for deep neural networks, although these processors are not radiation hardened. We deploy neural network models on these processors hosted by Hewlett Packard Enterprise’s Spaceborne Computer-2 on board the International Space Station (ISS). We find that the Myriad and Snapdragon digital signal processors (DSP)/artificial intelligence processors (AIP) provide speed improvement over the Snapdragon CPU in all cases except single-pixel networks (typically greater than 10 times for DSP/AIP). In addition, the discrepancy introduced through quantization and porting of our Jet Propulsion Laboratory models was usually quite low (less than 5%). Models were run multiple times, and memory checkers were deployed to test for radiation effects. To date, we have found no difference in output between ground and ISS runs, and no memory checker errors.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"29 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89538197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anomalous behavior during the aircraft landing phase can significantly increase the probability of adverse events. Automated anomaly detection during the landing phase can help aviation safety-related organizations to efficiently detect anomalous behavior and consider mitigation strategies. This paper develops a Bayesian autoencoder neural network model to identify anomalous behavior in landing trajectories by reconstructing the flight data because the reconstruction error is larger for anomalous flights. Different loss functions, such as Huber loss, mean squared error loss, and least trimmed squares are investigated to construct the Bayesian autoencoder model; and their performances are compared using different measures: the mean of the reconstruction error, the standard deviation of the reconstruction error, and both the mean and standard deviation of the reconstruction error. Different loss function-based models show differences in performance, depending on which measure is used for anomaly detection; among all the options considered, one of the Huber loss options appears to give the best performance, as indicated by the F1 score. Furthermore, the mean and standard deviation of the reconstruction error for a single flight are used to identify the time of occurrence and the flight parameters related to anomalous behavior.
{"title":"Identifying Anomalous Behavior in Aircraft Landing Trajectory Using a Bayesian Autoencoder","authors":"Yingxiao Kong, S. Mahadevan","doi":"10.2514/1.i011178","DOIUrl":"https://doi.org/10.2514/1.i011178","url":null,"abstract":"Anomalous behavior during the aircraft landing phase can significantly increase the probability of adverse events. Automated anomaly detection during the landing phase can help aviation safety-related organizations to efficiently detect anomalous behavior and consider mitigation strategies. This paper develops a Bayesian autoencoder neural network model to identify anomalous behavior in landing trajectories by reconstructing the flight data because the reconstruction error is larger for anomalous flights. Different loss functions, such as Huber loss, mean squared error loss, and least trimmed squares are investigated to construct the Bayesian autoencoder model; and their performances are compared using different measures: the mean of the reconstruction error, the standard deviation of the reconstruction error, and both the mean and standard deviation of the reconstruction error. Different loss function-based models show differences in performance, depending on which measure is used for anomaly detection; among all the options considered, one of the Huber loss options appears to give the best performance, as indicated by the F1 score. Furthermore, the mean and standard deviation of the reconstruction error for a single flight are used to identify the time of occurrence and the flight parameters related to anomalous behavior.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"10 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78888061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shanelle G. Clarke, Sounghwan Hwang, Omanshu Thapliyal, Inseok Hwang
Urban air mobility (UAM) systems are characterized by the heterogeneity of participating aerial vehicles (AVs). Participating AVs are expected to cooperate with each other while maintaining flexibility in individual missions and reacting to the possibility of cyberattacks and security threats. In this paper, we focus on the vulnerabilities of the UAM cyberphysical system against distributed denial-of-service (DDOS) cyberattacks. We develop a resilient control strategy for the AVs navigating through the UAM airspace to mitigate the effect of DDOS cyberattacks. A graph-theoretic vulnerability metric is proposed. Each AV can compute its vulnerability against DDOS cyberattacks in a fully distributed manner using this metric. Based on this computed metric, the AVs self-organize to minimize collision risk in the operating airspace after assessing self-vulnerability. This reconfiguration is also carried out in a fully distributed manner. The proposed resilient control is proven to reduce vulnerability in a probabilistic manner. This reduced vulnerability holds against DDOS cyberattacks with a known attack budget.
{"title":"Distributed Denial-of-Service Resilient Control for Urban Air Mobility Applications","authors":"Shanelle G. Clarke, Sounghwan Hwang, Omanshu Thapliyal, Inseok Hwang","doi":"10.2514/1.i011222","DOIUrl":"https://doi.org/10.2514/1.i011222","url":null,"abstract":"Urban air mobility (UAM) systems are characterized by the heterogeneity of participating aerial vehicles (AVs). Participating AVs are expected to cooperate with each other while maintaining flexibility in individual missions and reacting to the possibility of cyberattacks and security threats. In this paper, we focus on the vulnerabilities of the UAM cyberphysical system against distributed denial-of-service (DDOS) cyberattacks. We develop a resilient control strategy for the AVs navigating through the UAM airspace to mitigate the effect of DDOS cyberattacks. A graph-theoretic vulnerability metric is proposed. Each AV can compute its vulnerability against DDOS cyberattacks in a fully distributed manner using this metric. Based on this computed metric, the AVs self-organize to minimize collision risk in the operating airspace after assessing self-vulnerability. This reconfiguration is also carried out in a fully distributed manner. The proposed resilient control is proven to reduce vulnerability in a probabilistic manner. This reduced vulnerability holds against DDOS cyberattacks with a known attack budget.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"19 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85333453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Moamen Ibrahim Mohamed, Khaled Mahmoud Badran, Ahmed Esmat Hussien
Agile low-Earth-orbit (LEO) observation satellites need a robust attitude control and determination system. It is a critical satellite subsystem, which stabilizes the satellite to different desired orientations during its mission using different actuators. The detection of satellite misorientation is a highly challenging problem because it requires continuous monitoring of data from hundreds of satellite sensors to guarantee healthy operability. In this paper, the authors propose a data-driven deep-learning framework for detecting satellite misorientation by analyzing attitude control subsystem telemetry data. The proposed approach combines a hybrid predictive deep-learning model that consists of long short-term memory and convolutional neural networks in two parallel paths to predict telemetry data and a robust isolation forest classifier for anomaly detection purposes that can classify output residuals as normal or anomalous. The hybrid model was optimized by the particle swarm optimization algorithm to ensure faster fitness function convergence with optimal model hyperparameters. The suggested data-driven model was validated using real telemetry datasets, including real anomalous case studies. The experimental results proved the suggested approach’s superiority for identifying satellite misorientation as well as helping satellite operators monitor the system’s health and deduce the causes of anomalies to aid in decision-making.
{"title":"Anomaly Detection for Agile Satellite Attitude Control System Using Hybrid Deep-Learning Technique","authors":"Moamen Ibrahim Mohamed, Khaled Mahmoud Badran, Ahmed Esmat Hussien","doi":"10.2514/1.i011280","DOIUrl":"https://doi.org/10.2514/1.i011280","url":null,"abstract":"Agile low-Earth-orbit (LEO) observation satellites need a robust attitude control and determination system. It is a critical satellite subsystem, which stabilizes the satellite to different desired orientations during its mission using different actuators. The detection of satellite misorientation is a highly challenging problem because it requires continuous monitoring of data from hundreds of satellite sensors to guarantee healthy operability. In this paper, the authors propose a data-driven deep-learning framework for detecting satellite misorientation by analyzing attitude control subsystem telemetry data. The proposed approach combines a hybrid predictive deep-learning model that consists of long short-term memory and convolutional neural networks in two parallel paths to predict telemetry data and a robust isolation forest classifier for anomaly detection purposes that can classify output residuals as normal or anomalous. The hybrid model was optimized by the particle swarm optimization algorithm to ensure faster fitness function convergence with optimal model hyperparameters. The suggested data-driven model was validated using real telemetry datasets, including real anomalous case studies. The experimental results proved the suggested approach’s superiority for identifying satellite misorientation as well as helping satellite operators monitor the system’s health and deduce the causes of anomalies to aid in decision-making.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"15 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77162192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiaxin Xu, Junfeng Zhang, Zihan Peng, J. Bao, Bin Wang
Temporal–spatial resource optimization within the terminal maneuvering area has become an important research direction to meet the growing demand for air traffic. Accurate departure flight time prediction from taking off to the metering fixes is critical for departure management, connecting the surface operations, and overhead stream insertion. This paper employs ensemble learning methods (including bagging, boosting, and stacking) to predict departure flight times via different metering fixes based on four feature categories: initial states, operating situation, traffic demand, and wind velocity. The stacking method employs a linear regressor, a support vector regressor, and a tree-based ensemble regressor as base learners. The Guangzhou Baiyun International Airport case study shows that the stacking method proposed in this work outperforms other methods and could achieve satisfactory performance in departure flight time prediction, with a high prediction accuracy of up to 89% within a 1 min absolute error and 98% within a 2 min absolute error. Besides, the affecting factors analysis indicates that the operation direction, flight distance, and traffic demand in different areas significantly improve prediction accuracy.
{"title":"Data-Driven Departure Flight Time Prediction Based on Feature Construction and Ensemble Learning","authors":"Jiaxin Xu, Junfeng Zhang, Zihan Peng, J. Bao, Bin Wang","doi":"10.2514/1.i011227","DOIUrl":"https://doi.org/10.2514/1.i011227","url":null,"abstract":"Temporal–spatial resource optimization within the terminal maneuvering area has become an important research direction to meet the growing demand for air traffic. Accurate departure flight time prediction from taking off to the metering fixes is critical for departure management, connecting the surface operations, and overhead stream insertion. This paper employs ensemble learning methods (including bagging, boosting, and stacking) to predict departure flight times via different metering fixes based on four feature categories: initial states, operating situation, traffic demand, and wind velocity. The stacking method employs a linear regressor, a support vector regressor, and a tree-based ensemble regressor as base learners. The Guangzhou Baiyun International Airport case study shows that the stacking method proposed in this work outperforms other methods and could achieve satisfactory performance in departure flight time prediction, with a high prediction accuracy of up to 89% within a 1 min absolute error and 98% within a 2 min absolute error. Besides, the affecting factors analysis indicates that the operation direction, flight distance, and traffic demand in different areas significantly improve prediction accuracy.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"1 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83255459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ross Horne, S. Mauw, Andrzej Mizera, André Stemper, J. Thoemel
We explore the feasibility of onboard anomaly detection using artificial neural networks for CubeSat systems and related spacecraft where computing resources are limited. We gather data for training and evaluation using a CubeSat in a laboratory for a scenario where a malfunctioning component affects temperature fluctuations across the control system. This data, published in an open repository, guide the selection of suitable features, neural network architecture, and metrics comprising our anomaly detection algorithm. The precision and recall of the algorithm demonstrate improvements as compared to out-of-limit methods, whereas our open-source implementation for a typical microcontroller exhibits small memory overhead, and hence may coexist with existing control software without introducing new hardware. These features make our solution feasible to deploy on board a CubeSat, and thus on other, more advanced types of satellites.
{"title":"Anomaly Detection Using Deep Learning Respecting the Resources on Board a CubeSat","authors":"Ross Horne, S. Mauw, Andrzej Mizera, André Stemper, J. Thoemel","doi":"10.2514/1.i011232","DOIUrl":"https://doi.org/10.2514/1.i011232","url":null,"abstract":"We explore the feasibility of onboard anomaly detection using artificial neural networks for CubeSat systems and related spacecraft where computing resources are limited. We gather data for training and evaluation using a CubeSat in a laboratory for a scenario where a malfunctioning component affects temperature fluctuations across the control system. This data, published in an open repository, guide the selection of suitable features, neural network architecture, and metrics comprising our anomaly detection algorithm. The precision and recall of the algorithm demonstrate improvements as compared to out-of-limit methods, whereas our open-source implementation for a typical microcontroller exhibits small memory overhead, and hence may coexist with existing control software without introducing new hardware. These features make our solution feasible to deploy on board a CubeSat, and thus on other, more advanced types of satellites.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"80 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80966652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. L. Verstraete, L. R. Ceballos, C. Hente, B. Roccia, C. Gebhardt
Reliable aerodynamic and aeroelastic simulations of advanced aeronautical/mechanical systems require us to predict flow-induced forces as accurately as possible. Nowadays, computational fluid dynamic techniques are quite popular, but at an overwhelming computational cost. Consequently, methods like the unsteady vortex-lattice method (UVLM) became the workhorses for many simulation environments. Then, numerous UVLM-based codes using diverse numerical schemes, enhanced by several add-ons and implemented following different programming paradigms, were available in the literature. However, there is no set of benchmark cases intended for the systematic verification of those codes relying on the UVLM. Therefore, we provide six fully reproducible benchmark cases that can be used for such an end. We also describe two in-house UVLM-based codes that are well suited for aerodynamic simulations and for being encapsulated as an aerodynamic engine within partitioned aeroelastic simulation schemes. Because both codes follow radically different implementation philosophies, these represent excellent candidates to undergo the series of benchmark cases proposed. The work is completed by providing a valuable dataset and comparison criteria to measure to what extent two or more codes are in agreement. Along this path, for very first time, we use a comparison strategy to contrast free-wake methods based on the Hausdorff distance.
{"title":"Code-to-Code Benchmark for Simulation Tools Based on the Unsteady Vortex-Lattice Method","authors":"M. L. Verstraete, L. R. Ceballos, C. Hente, B. Roccia, C. Gebhardt","doi":"10.2514/1.i011184","DOIUrl":"https://doi.org/10.2514/1.i011184","url":null,"abstract":"Reliable aerodynamic and aeroelastic simulations of advanced aeronautical/mechanical systems require us to predict flow-induced forces as accurately as possible. Nowadays, computational fluid dynamic techniques are quite popular, but at an overwhelming computational cost. Consequently, methods like the unsteady vortex-lattice method (UVLM) became the workhorses for many simulation environments. Then, numerous UVLM-based codes using diverse numerical schemes, enhanced by several add-ons and implemented following different programming paradigms, were available in the literature. However, there is no set of benchmark cases intended for the systematic verification of those codes relying on the UVLM. Therefore, we provide six fully reproducible benchmark cases that can be used for such an end. We also describe two in-house UVLM-based codes that are well suited for aerodynamic simulations and for being encapsulated as an aerodynamic engine within partitioned aeroelastic simulation schemes. Because both codes follow radically different implementation philosophies, these represent excellent candidates to undergo the series of benchmark cases proposed. The work is completed by providing a valuable dataset and comparison criteria to measure to what extent two or more codes are in agreement. Along this path, for very first time, we use a comparison strategy to contrast free-wake methods based on the Hausdorff distance.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"47 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91013911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The cyber threat to aerospace systems has been growing rapidly in recent years with several real-world and experimental cyberattacks observed. This growing threat has prompted investigation of cyberattack and defense strategies for manned and unmanned air systems, spacecraft, and other aerospace systems. The work in this paper seeks to further understand these attacks by introducing and developing a novel cyberattack for autonomous aerospace systems. The problem faced by the attacker is posed and discussed analytically using false data injection of state measurements to exploit the vehicle’s onboard controller to take control of the system. It is shown that the attacker can utilize traditional control techniques to exert control over the system and eliminate the control of the victim by intercepting and modifying the vehicle’s measurement data. The attacker is able to accomplish this objective without any prior knowledge of the system’s plant, controller, or reference signal. The attack is demonstrated on the elevator-to-pitch-attitude-angle dynamics of a Cessna T-37 aircraft model. It is shown to be successful in eliminating the victim’s control influence over the system and driving the system to its own target state.
{"title":"Control Acquisition Attack of Aerospace Systems via False Data Injection","authors":"Garrett A. Jares, J. Valasek","doi":"10.2514/1.i011199","DOIUrl":"https://doi.org/10.2514/1.i011199","url":null,"abstract":"The cyber threat to aerospace systems has been growing rapidly in recent years with several real-world and experimental cyberattacks observed. This growing threat has prompted investigation of cyberattack and defense strategies for manned and unmanned air systems, spacecraft, and other aerospace systems. The work in this paper seeks to further understand these attacks by introducing and developing a novel cyberattack for autonomous aerospace systems. The problem faced by the attacker is posed and discussed analytically using false data injection of state measurements to exploit the vehicle’s onboard controller to take control of the system. It is shown that the attacker can utilize traditional control techniques to exert control over the system and eliminate the control of the victim by intercepting and modifying the vehicle’s measurement data. The attacker is able to accomplish this objective without any prior knowledge of the system’s plant, controller, or reference signal. The attack is demonstrated on the elevator-to-pitch-attitude-angle dynamics of a Cessna T-37 aircraft model. It is shown to be successful in eliminating the victim’s control influence over the system and driving the system to its own target state.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"28 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86842381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, a two-stage multicriteria decision-making framework for aircraft conflict resolution in the air traffic management system is proposed. Aircraft conflict resolution has been commonly solved based on single-objective optimization. However, the existing approach may not provide a satisfactory solution to all stakeholders involved in the air traffic management system. Therefore, in the first stage of the proposed algorithm, a new conflict resolution strategy is presented based on multiobjective optimization in which multiple-objective functions are optimized simultaneously. Each objective function is designed to take into account the interests of various stakeholders, and the augmented epsilon-constraint method is applied to determine Pareto optimal solutions. In the second stage, the best compromise solution among the Pareto optimal solutions is determined based on the technique for order performance by similarity to the ideal solution. The numerical simulation results show that the proposed algorithm provides a better solution from the perspective of mitigating the competing interests among stakeholders than the existing approach based on single-objective optimization.
{"title":"Two-Stage Multicriteria Decision-Making Framework for Aircraft Conflict Resolution","authors":"Youkyung Hong, Youdan Kim","doi":"10.2514/1.i011152","DOIUrl":"https://doi.org/10.2514/1.i011152","url":null,"abstract":"In this study, a two-stage multicriteria decision-making framework for aircraft conflict resolution in the air traffic management system is proposed. Aircraft conflict resolution has been commonly solved based on single-objective optimization. However, the existing approach may not provide a satisfactory solution to all stakeholders involved in the air traffic management system. Therefore, in the first stage of the proposed algorithm, a new conflict resolution strategy is presented based on multiobjective optimization in which multiple-objective functions are optimized simultaneously. Each objective function is designed to take into account the interests of various stakeholders, and the augmented epsilon-constraint method is applied to determine Pareto optimal solutions. In the second stage, the best compromise solution among the Pareto optimal solutions is determined based on the technique for order performance by similarity to the ideal solution. The numerical simulation results show that the proposed algorithm provides a better solution from the perspective of mitigating the competing interests among stakeholders than the existing approach based on single-objective optimization.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"374 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76613904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate identification of phases of flight is an essential step in analyses such as airport operation counts, fuel burn estimation, and safety studies. Past research has focused primarily on using positional data with rule-based or probabilistic-based decision-making to identify the phases of flight. Many of these efforts note that the task of correctly identifying phases of flight is challenging, often requiring extreme fine-tuning of methods. In this paper, we initially study whether combinations of dimensionality reduction of flight data records from general aviation aircraft impact clustering into the correct flight phases (climb, cruise, or descent) without any preprocessing or fine-tuning. For dimensionality reduction, we considered the low variance filter, the high correlation filter, principal component analysis, and autoencoders. We found that these dimensionality reduction algorithms do not offer any benefit for the phase identification task, as compared to feature selection that simply omits engine-specific features. For the clustering task, we considered [Formula: see text]-means and Gaussian mixture models. After performing clustering on eight test flights, we conclude that both methods are adequate at identifying the phases of flight in various general aviation flights and yield similar results.
{"title":"Study on Machine Learning Methods for General Aviation Flight Phase Identification","authors":"Nicoletta Fala, G. Georgalis, Nastaran Arzamani","doi":"10.2514/1.i011246","DOIUrl":"https://doi.org/10.2514/1.i011246","url":null,"abstract":"Accurate identification of phases of flight is an essential step in analyses such as airport operation counts, fuel burn estimation, and safety studies. Past research has focused primarily on using positional data with rule-based or probabilistic-based decision-making to identify the phases of flight. Many of these efforts note that the task of correctly identifying phases of flight is challenging, often requiring extreme fine-tuning of methods. In this paper, we initially study whether combinations of dimensionality reduction of flight data records from general aviation aircraft impact clustering into the correct flight phases (climb, cruise, or descent) without any preprocessing or fine-tuning. For dimensionality reduction, we considered the low variance filter, the high correlation filter, principal component analysis, and autoencoders. We found that these dimensionality reduction algorithms do not offer any benefit for the phase identification task, as compared to feature selection that simply omits engine-specific features. For the clustering task, we considered [Formula: see text]-means and Gaussian mixture models. After performing clustering on eight test flights, we conclude that both methods are adequate at identifying the phases of flight in various general aviation flights and yield similar results.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"47 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72464600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：