Low visibility at airports can significantly impact airside capacity, leading to ground delays and runway/taxiway incursions. Digital tower technology, enabled by live camera feeds, leverages computer vision to enhance airside surveillance and operational efficiency. However, technical challenges in digital camera systems can introduce low-fidelity transmission effects such as blurring, pixelation, or JPEG compression. Additionally, adverse weather conditions like rain and fog can further reduce visibility for tower controllers, whether from digital video or out-of-tower views. This paper proposes a computer vision framework and deep learning algorithms to detect and track aircraft in low-visibility (due to bad weather) and low-fidelity (due to technical issues) environments to enhance visibility using digital video input. The framework employs a convolutional neural network for aircraft detection and Kalman filters for tracking, especially in low-visibility conditions. Performance enhancements come from pre- and postprocessing algorithms like object filtering, corrupted image detection, and image enhancement. It proves effective on an airport video dataset from Houston Airport, enhancing visibility under adverse weather conditions.
{"title":"Airside Surveillance by Computer Vision in Low-Visibility and Low-Fidelity Environment","authors":"P. Thai, Sameer Alam, Nimrod Lilith","doi":"10.2514/1.d0410","DOIUrl":"https://doi.org/10.2514/1.d0410","url":null,"abstract":"Low visibility at airports can significantly impact airside capacity, leading to ground delays and runway/taxiway incursions. Digital tower technology, enabled by live camera feeds, leverages computer vision to enhance airside surveillance and operational efficiency. However, technical challenges in digital camera systems can introduce low-fidelity transmission effects such as blurring, pixelation, or JPEG compression. Additionally, adverse weather conditions like rain and fog can further reduce visibility for tower controllers, whether from digital video or out-of-tower views. This paper proposes a computer vision framework and deep learning algorithms to detect and track aircraft in low-visibility (due to bad weather) and low-fidelity (due to technical issues) environments to enhance visibility using digital video input. The framework employs a convolutional neural network for aircraft detection and Kalman filters for tracking, especially in low-visibility conditions. Performance enhancements come from pre- and postprocessing algorithms like object filtering, corrupted image detection, and image enhancement. It proves effective on an airport video dataset from Houston Airport, enhancing visibility under adverse weather conditions.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"89 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141647201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christopher R. Chin, A. Saravanan, H. Balakrishnan
The rapid deployment of fleets of small, uncrewed aircraft (drones) in the immediate aftermath of a natural disaster to search impacted regions for people in need of rescue is one of the most vital applications of advanced air mobility. Effective drone-based search operations require that the drone fleets operate out of bases that are appropriately located in advance of the disaster. Using a case study based in the Iwate prefecture of Japan, we develop optimization formulations to strategically locate drone bases. It is important to be capable of responding quickly to the locations most likely to require a search, while covering as large an area as possible. We evaluate the disparities in the level of access afforded to different areas. We extend our optimization formulation to account for the probability of the base locations themselves being impacted by the disaster and the possibility of base relocation. Finally, we illustrate how a vehicle routing component can be used to address the tactical portion of drone-based search operations.
{"title":"Strategic Planning of Aerial Assets for Disaster Response","authors":"Christopher R. Chin, A. Saravanan, H. Balakrishnan","doi":"10.2514/1.d0423","DOIUrl":"https://doi.org/10.2514/1.d0423","url":null,"abstract":"The rapid deployment of fleets of small, uncrewed aircraft (drones) in the immediate aftermath of a natural disaster to search impacted regions for people in need of rescue is one of the most vital applications of advanced air mobility. Effective drone-based search operations require that the drone fleets operate out of bases that are appropriately located in advance of the disaster. Using a case study based in the Iwate prefecture of Japan, we develop optimization formulations to strategically locate drone bases. It is important to be capable of responding quickly to the locations most likely to require a search, while covering as large an area as possible. We evaluate the disparities in the level of access afforded to different areas. We extend our optimization formulation to account for the probability of the base locations themselves being impacted by the disaster and the possibility of base relocation. Finally, we illustrate how a vehicle routing component can be used to address the tactical portion of drone-based search operations.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"45 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141650108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Thousands of aircraft flight plans are affected by space launch and reentry operations each year, increasing the distances flown, causing flight delays, and increasing air traffic controllers workload. Due to regulations and procedures, predefined Aircraft Hazard Areas (AHAs) are used to protect aircraft from the risks of space launch and reentry debris, thus constraining the available airspace for other airspace users. While disruptive, there is no less impactful approach at present that adequately protects the flying public. In this paper, we explore the application of trajectory-based operations to evaluate the impact of an AHA on commercial aircraft, with the aim of reducing the number of flights that must be rerouted or rescheduled. This approach relies on precise trajectory predictions to the AHA boundary to determine which flights are expected to clear the AHA before its activation or remain clear of the AHA until after its deactivation. This paper derives the required predicted trajectory accuracy for air traffic automation systems to effectively predict flights impacted by an AHA. The required accuracy is derived based on a model for managing flights relative to the AHA using speed changes alone (as opposed to reroutes or holding) in the context of operational uncertainties like departure time delays and flight characteristics. Additionally, we derived a model to relate scheduling buffers to the AHA activation time, delivery accuracy at the AHA boundary, and AHA violation probability.
每年有数以千计的飞机飞行计划受到航天发射和重返大气层作业的影响，从而增加了飞行距离，导致航班延误，并增加了空中交通管制员的工作量。根据相关规定和程序，预先确定的飞机危险区（AHA）用于保护飞机免受太空发射和重返碎片的风险，从而限制了其他空域用户的可用空域。虽然具有破坏性，但目前没有影响较小的方法可以充分保护飞行公众。在本文中，我们探讨了如何应用基于轨迹的操作来评估 AHA 对商用飞机的影响，目的是减少必须改变航线或重新安排时间的航班数量。这种方法依赖于对 AHA 边界的精确轨迹预测，以确定哪些航班有望在 AHA 启用前避开 AHA，或在 AHA 停用前一直避开 AHA。本文得出了空中交通自动化系统有效预测受 AHA 影响的航班所需的预测轨迹精度。所需的精确度是在离港时间延迟和航班特性等运行不确定性的背景下，根据仅使用速度变化（而非改道或保持）来管理相对于 AHA 的航班的模型得出的。此外，我们还推导出一个模型，用于将调度缓冲区与 AHA 激活时间、AHA 边界的交付准确性以及 AHA 违反概率联系起来。
{"title":"Predicted Trajectory Accuracy Requirements to Reduce Aviation Impact of Space Launch Operations","authors":"L. A. Weitz, Timothy J. Gruber, Nicholas E. Rozen","doi":"10.2514/1.d0426","DOIUrl":"https://doi.org/10.2514/1.d0426","url":null,"abstract":"Thousands of aircraft flight plans are affected by space launch and reentry operations each year, increasing the distances flown, causing flight delays, and increasing air traffic controllers workload. Due to regulations and procedures, predefined Aircraft Hazard Areas (AHAs) are used to protect aircraft from the risks of space launch and reentry debris, thus constraining the available airspace for other airspace users. While disruptive, there is no less impactful approach at present that adequately protects the flying public. In this paper, we explore the application of trajectory-based operations to evaluate the impact of an AHA on commercial aircraft, with the aim of reducing the number of flights that must be rerouted or rescheduled. This approach relies on precise trajectory predictions to the AHA boundary to determine which flights are expected to clear the AHA before its activation or remain clear of the AHA until after its deactivation. This paper derives the required predicted trajectory accuracy for air traffic automation systems to effectively predict flights impacted by an AHA. The required accuracy is derived based on a model for managing flights relative to the AHA using speed changes alone (as opposed to reroutes or holding) in the context of operational uncertainties like departure time delays and flight characteristics. Additionally, we derived a model to relate scheduling buffers to the AHA activation time, delivery accuracy at the AHA boundary, and AHA violation probability.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"111 32","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141665713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aircraft weight estimation is a common problem facing researchers working with aircraft surveillance data. Although knowledge of an aircraft’s weight and thrust is required for many types of analyses, such as those evaluating aircraft acoustic noise, fuel burn, and emissions, these parameters are typically not available from surveillance sources. Instead, researchers generally only have access to basic aircraft states: lateral position, groundspeed, and altitude. Therefore, methods for estimating the weight of aircraft from these basic states become necessary in cases where aircraft performance is a key component of the analysis. This paper introduces two weight estimation models: one for the estimation of aircraft takeoff weight from departure data, and another for the estimation of aircraft landing weight from arrival data. The models are mathematically simple but grounded in knowledge of aircraft certification, airline operations, and aircraft flight management system logic. The landing weight estimation model proposed is shown to have a mean absolute error equivalent to 2.66% of maximum takeoff weight and a standard deviation of 3.35% of maximum takeoff weight when validated using onboard data recordings from 240 Airbus A320 flights. Similarly, the proposed takeoff weight estimation model is shown to have a mean absolute error of 2.83% of the maximum takeoff weight and a standard deviation of 3.55% of the maximum takeoff weight when applied to the same validation dataset.
{"title":"Aircraft Takeoff and Landing Weight Estimation from Surveillance Data","authors":"Sandro Salgueiro, R. Hansman, Jacqueline Huynh","doi":"10.2514/1.d0370","DOIUrl":"https://doi.org/10.2514/1.d0370","url":null,"abstract":"Aircraft weight estimation is a common problem facing researchers working with aircraft surveillance data. Although knowledge of an aircraft’s weight and thrust is required for many types of analyses, such as those evaluating aircraft acoustic noise, fuel burn, and emissions, these parameters are typically not available from surveillance sources. Instead, researchers generally only have access to basic aircraft states: lateral position, groundspeed, and altitude. Therefore, methods for estimating the weight of aircraft from these basic states become necessary in cases where aircraft performance is a key component of the analysis. This paper introduces two weight estimation models: one for the estimation of aircraft takeoff weight from departure data, and another for the estimation of aircraft landing weight from arrival data. The models are mathematically simple but grounded in knowledge of aircraft certification, airline operations, and aircraft flight management system logic. The landing weight estimation model proposed is shown to have a mean absolute error equivalent to 2.66% of maximum takeoff weight and a standard deviation of 3.35% of maximum takeoff weight when validated using onboard data recordings from 240 Airbus A320 flights. Similarly, the proposed takeoff weight estimation model is shown to have a mean absolute error of 2.83% of the maximum takeoff weight and a standard deviation of 3.55% of the maximum takeoff weight when applied to the same validation dataset.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":" 39","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141678946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xuan Jiang, Yuhan Tang, Junzhe Cao, Vishwanath Bulusu, H. Yang, Xin Peng, Yunhan Zheng, Jinhua Zhao, Raja Sengupta
{"title":"Simulating Integration of Urban Air Mobility into Existing Transportation Systems: Survey","authors":"Xuan Jiang, Yuhan Tang, Junzhe Cao, Vishwanath Bulusu, H. Yang, Xin Peng, Yunhan Zheng, Jinhua Zhao, Raja Sengupta","doi":"10.2514/1.d0431","DOIUrl":"https://doi.org/10.2514/1.d0431","url":null,"abstract":"","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"26 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141684412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elaheh Sabziyan Varnousfaderani, S. Shihab, E. F. Dulia
Near-future air taxi operations with electric vertical takeoff and landing aircraft will be constrained by the need for frequent recharging and limited takeoff and landing pads in vertiports and will be subject to time-varying demand and electricity prices, making the dispatch problem unique and particularly challenging to solve. Previously, the authors have developed optimization models to address this problem. Such optimization models, however, suffer from prohibitively high computational run times when the scale of the problem increases, making them less practical for real-world implementation. To overcome this issue, the authors have developed two deep reinforcement learning-based dispatch algorithms, namely, single-agent and multi-agent double dueling deep Q-network dispatch algorithms, where the objective is to maximize operating profit. A passenger transportation simulation environment was built to assess the performance of these algorithms across 36 numerical cases with varying numbers of vehicles and vertiports and amounts of demand. The results indicate that the multi-agent dispatch algorithm can closely approximate the optimal dispatch policy with significantly less computational expenses compared to the benchmark optimization model. The multi-agent algorithm was found to outperform the single-agent counterpart with respect to both profits generated and training time. Additionally, we implemented a heuristic-based algorithm, faster but less effective in generating profits compared to our two deep reinforcement learning-based algorithms.
{"title":"DeepDispatch: Deep Reinforcement Learning-Based Vehicle Dispatch Algorithm for Advanced Air Mobility","authors":"Elaheh Sabziyan Varnousfaderani, S. Shihab, E. F. Dulia","doi":"10.2514/1.d0416","DOIUrl":"https://doi.org/10.2514/1.d0416","url":null,"abstract":"Near-future air taxi operations with electric vertical takeoff and landing aircraft will be constrained by the need for frequent recharging and limited takeoff and landing pads in vertiports and will be subject to time-varying demand and electricity prices, making the dispatch problem unique and particularly challenging to solve. Previously, the authors have developed optimization models to address this problem. Such optimization models, however, suffer from prohibitively high computational run times when the scale of the problem increases, making them less practical for real-world implementation. To overcome this issue, the authors have developed two deep reinforcement learning-based dispatch algorithms, namely, single-agent and multi-agent double dueling deep Q-network dispatch algorithms, where the objective is to maximize operating profit. A passenger transportation simulation environment was built to assess the performance of these algorithms across 36 numerical cases with varying numbers of vehicles and vertiports and amounts of demand. The results indicate that the multi-agent dispatch algorithm can closely approximate the optimal dispatch policy with significantly less computational expenses compared to the benchmark optimization model. The multi-agent algorithm was found to outperform the single-agent counterpart with respect to both profits generated and training time. Additionally, we implemented a heuristic-based algorithm, faster but less effective in generating profits compared to our two deep reinforcement learning-based algorithms.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"115 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141363036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Helmke, Matthias Kleinert, Oliver Ohneiser, Nils Ahrenhold, Lucas Klamert, Petr Motlicek
Air traffic controllers (ATCos) quantified the benefits of automatic speech recognition and understanding (ASRU) on workload and flight safety. As a baseline procedure, ATCos manually enter all verbal clearances into the aircraft radar labels by mouse. In our proposed solution, ATCos are supported by ASRU, which is capable of delivering the required radar label updates automatically. ATCos need to visually review the ASRU-based label updates and only have to make corrections in case of misinterpretations. Overall, the amount of time required for manually inserting clearances, i.e., by selecting the correct input in the radar labels, was reduced from 12,700 s during 14 hours of simulation time down to 405 s when ATCos were supported by ASRU. Considering the additional time of mental workload for verifying ASRU output, there is still a saving of more than one-third of the time for radar label updates. This paper also considers safety aspects, i.e., how often incorrect inputs into aircraft radar labels occur with ASRU. The number of wrong or missing inputs is less than without ASRU support. This paper advances the use case that ASRU could potentially improve safety and efficiency for ATCo operations for arrivals.
{"title":"Safety and Workload Benefits of Automatic Speech Understanding for Radar Label Updates","authors":"H. Helmke, Matthias Kleinert, Oliver Ohneiser, Nils Ahrenhold, Lucas Klamert, Petr Motlicek","doi":"10.2514/1.d0419","DOIUrl":"https://doi.org/10.2514/1.d0419","url":null,"abstract":"Air traffic controllers (ATCos) quantified the benefits of automatic speech recognition and understanding (ASRU) on workload and flight safety. As a baseline procedure, ATCos manually enter all verbal clearances into the aircraft radar labels by mouse. In our proposed solution, ATCos are supported by ASRU, which is capable of delivering the required radar label updates automatically. ATCos need to visually review the ASRU-based label updates and only have to make corrections in case of misinterpretations. Overall, the amount of time required for manually inserting clearances, i.e., by selecting the correct input in the radar labels, was reduced from 12,700 s during 14 hours of simulation time down to 405 s when ATCos were supported by ASRU. Considering the additional time of mental workload for verifying ASRU output, there is still a saving of more than one-third of the time for radar label updates. This paper also considers safety aspects, i.e., how often incorrect inputs into aircraft radar labels occur with ASRU. The number of wrong or missing inputs is less than without ASRU support. This paper advances the use case that ASRU could potentially improve safety and efficiency for ATCo operations for arrivals.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":" 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141369048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Proposed concepts of operations for advanced air mobility rely on private service providers being responsible for providing air traffic management services to uncrewed aircraft such as drones and autonomous air taxis. While such proposals are unprecedented in the aviation context, one can draw parallels to the Internet and the role played by Internet service providers in managing web traffic. A study of the evolution of the Internet illustrates that, without clear rules for cooperation around a nascent market, private profit motives incentivize against service provider cooperation, especially for traffic flows that traverse multiple regions managed by different service providers. To address this problem, we propose a profit-sharing mechanism based on the Shapley value that incentivizes service providers to cooperate. We show that this mechanism i) ensures that service providers route flights along globally optimal routes, and ii) encourages service providers to work together in providing more efficient routes. We study the allocation of sectors to service providers and show that different allocations can cause large differences in profit earned. Finally, we discuss some of the remaining challenges with having a federated network of private service providers supporting traffic management for advanced air mobility operations.
{"title":"Market Structures for Service Providers in Advanced Air Mobility","authors":"Victor L. Qin, Geoffrey Ding, H. Balakrishnan","doi":"10.2514/1.d0415","DOIUrl":"https://doi.org/10.2514/1.d0415","url":null,"abstract":"Proposed concepts of operations for advanced air mobility rely on private service providers being responsible for providing air traffic management services to uncrewed aircraft such as drones and autonomous air taxis. While such proposals are unprecedented in the aviation context, one can draw parallels to the Internet and the role played by Internet service providers in managing web traffic. A study of the evolution of the Internet illustrates that, without clear rules for cooperation around a nascent market, private profit motives incentivize against service provider cooperation, especially for traffic flows that traverse multiple regions managed by different service providers. To address this problem, we propose a profit-sharing mechanism based on the Shapley value that incentivizes service providers to cooperate. We show that this mechanism i) ensures that service providers route flights along globally optimal routes, and ii) encourages service providers to work together in providing more efficient routes. We study the allocation of sectors to service providers and show that different allocations can cause large differences in profit earned. Finally, we discuss some of the remaining challenges with having a federated network of private service providers supporting traffic management for advanced air mobility operations.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":" 37","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141368406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The establishment of aircraft categories is a classification technique employed in a variety of aviation disciplines, including design and development, certification, ongoing airworthiness, air traffic management, surveillance, and safety analysis. Traditional approaches rely on manual feature engineering, which can be labor-intensive and ineffective for capturing complex patterns. In this paper, an approach to aircraft categorization using unsupervised machine learning clustering is proposed. The aim of the proposed approach is to be simple in order to be useful and understandable across disciplinary domains; to be scalable to large volumes of air traffic data; and to be adaptable to changes to account for the evolving technological and operational nature of the airspace environment. The application is based on an adapted version of the [Formula: see text]-means algorithm that can group aircraft into clusters based on 3D position over time. The approach is validated using real-world, publicly available ADS-B air traffic data, and the results are compared to traditional categorization methods from the field of aircraft certification. The results showed that the model could be used to 1) identify and group aircraft sharing the same flight phase, 2) categorize aircraft with a similar general heading or direction, and 3) distinguish between local regional aircraft operations and longer flight operations. It was also shown that, depending on the use case, the model could be extended to identify more granular behaviors by increasing the [Formula: see text] value used to create the model. Overall, the findings demonstrate that leveraging machine learning techniques for aircraft categorization provides an effective, automated, and scalable solution applicable to a wide range of current applications.
{"title":"Aircraft Categorization Approach Using Machine Learning to Analyze Aircraft Behavior","authors":"Nicolas Vincent-Boulay, Catharine Marsden","doi":"10.2514/1.d0398","DOIUrl":"https://doi.org/10.2514/1.d0398","url":null,"abstract":"The establishment of aircraft categories is a classification technique employed in a variety of aviation disciplines, including design and development, certification, ongoing airworthiness, air traffic management, surveillance, and safety analysis. Traditional approaches rely on manual feature engineering, which can be labor-intensive and ineffective for capturing complex patterns. In this paper, an approach to aircraft categorization using unsupervised machine learning clustering is proposed. The aim of the proposed approach is to be simple in order to be useful and understandable across disciplinary domains; to be scalable to large volumes of air traffic data; and to be adaptable to changes to account for the evolving technological and operational nature of the airspace environment. The application is based on an adapted version of the [Formula: see text]-means algorithm that can group aircraft into clusters based on 3D position over time. The approach is validated using real-world, publicly available ADS-B air traffic data, and the results are compared to traditional categorization methods from the field of aircraft certification. The results showed that the model could be used to 1) identify and group aircraft sharing the same flight phase, 2) categorize aircraft with a similar general heading or direction, and 3) distinguish between local regional aircraft operations and longer flight operations. It was also shown that, depending on the use case, the model could be extended to identify more granular behaviors by increasing the [Formula: see text] value used to create the model. Overall, the findings demonstrate that leveraging machine learning techniques for aircraft categorization provides an effective, automated, and scalable solution applicable to a wide range of current applications.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"10 Sup2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141382580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrea Garbo, Mark T. Kotwicz Herniczek, Brian J. German
Designs for electric vertical takeoff and landing (VTOL) aircraft deviate from traditional aircraft designs and include a wide variety of different configurations. Significant uncertainty also exists regarding the status of future battery technology, including energy density and charge rates. This paper presents a simple analytic model to estimate the profitability of an urban air mobility electric VTOL aircraft for a variety of vehicle configurations, battery technology parameters, and economic factors. Five main elements are considered by the framework: aircraft performance, battery technology, mission profile, mission economics, and electrical grid parameters. A sensitivity analysis is provided, comparing the operational performance and profitability of three electric VTOL concepts (lift plus cruise, quadcopter, and side by side), with respect to electrical grid and battery technology factors. The takeoff weight to maximize the number of completed routes or the overall profitability is also examined. Interestingly, results show that these two values do not coincide across the entire design space due to the nonlinearity of the battery life cycle with respect to the depth of discharge, which strongly affects battery replacement cost.
{"title":"Urban Air Mobility Profitability and Operational Sensitivity to Battery and Charging Technology","authors":"Andrea Garbo, Mark T. Kotwicz Herniczek, Brian J. German","doi":"10.2514/1.d0328","DOIUrl":"https://doi.org/10.2514/1.d0328","url":null,"abstract":"Designs for electric vertical takeoff and landing (VTOL) aircraft deviate from traditional aircraft designs and include a wide variety of different configurations. Significant uncertainty also exists regarding the status of future battery technology, including energy density and charge rates. This paper presents a simple analytic model to estimate the profitability of an urban air mobility electric VTOL aircraft for a variety of vehicle configurations, battery technology parameters, and economic factors. Five main elements are considered by the framework: aircraft performance, battery technology, mission profile, mission economics, and electrical grid parameters. A sensitivity analysis is provided, comparing the operational performance and profitability of three electric VTOL concepts (lift plus cruise, quadcopter, and side by side), with respect to electrical grid and battery technology factors. The takeoff weight to maximize the number of completed routes or the overall profitability is also examined. Interestingly, results show that these two values do not coincide across the entire design space due to the nonlinearity of the battery life cycle with respect to the depth of discharge, which strongly affects battery replacement cost.","PeriodicalId":36984,"journal":{"name":"Journal of Air Transportation","volume":"57 36","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140965603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：