Application of Data Science to Aviation II

A special issue of Aerospace (ISSN 2226-4310). This special issue belongs to the section "Air Traffic and Transportation".

Deadline for manuscript submissions: closed (31 December 2022) | Viewed by 12122

Special Issue Editors


E-Mail Website
Guest Editor
ONERA DTIS, Université de Toulouse, CEDEX 4, 31055 Toulouse, France
Interests: machine learning; data science; decision science; air traffic management; aviation
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Institute of Flight Systems, Bundeswehr University Munich, 85577 Neubiberg, Germany
Interests: air transportation; data-driven and model-based environments; predictive analysis; integrated airspace and airport management
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Future aviation requires air traffic providers, operators, and researchers to implement new procedures and technologies for an efficient and environment-friendly air transportation network. Data analytics and machine learning (ML) techniques are well suited for aviation to extract information from the large amount of generated data, to predict future situations based on historical information, and to assist humans in taking optimal decisions. The rationale is to try to learn how to imitate the behavior of operators rather than having them explain and model an incomplete set of rules they are assumed to follow.

The air transportation system is complex, multidimensional, highly distributed, and interdependent. It interacts with global and regional economies and has reached its limits in many ways. The operational uncertainties related to weather conditions, increasing safety requirements and environmental expectations (green aviation) are challenging the robustness and efficiency of the system and open new research questions.

In order to provide input for a better situation awareness and for collaborative optimization, significant added value stems from various data sources such as flight plans, onboard flight data records, maintenance records, secondary surveillance radar information (trajectories, Mode S, and ADS-B), ground-based augmentation systems (GBASs), weather information, satellite imaging, or stakeholders’ resource planning information.

This Special Issue will focus on the use of aviation-related data (such as the data sources listed above) for artificial intelligence and data science techniques (including data analytics, machine learning, reinforcement learning, constraint optimization) in order to improve the operational aviation environment.

Dr. Xavier Olive
Dr. Michael Schultz
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Aerospace is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • aviation
  • big data
  • machine learning
  • artificial intelligence
  • air traffic management
  • air traffic operations

Related Special Issue

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

24 pages, 5875 KiB  
Article
Improving Algorithm Conflict Resolution Manoeuvres with Reinforcement Learning
by Marta Ribeiro, Joost Ellerbroek and Jacco Hoekstra
Aerospace 2022, 9(12), 847; https://doi.org/10.3390/aerospace9120847 - 19 Dec 2022
Cited by 1 | Viewed by 1834
Abstract
Future high traffic densities with drone operations are expected to exceed the number of aircraft that current air traffic control procedures can control simultaneously. Despite extensive research on geometric CR methods, at higher densities, their performance is hindered by the unpredictable emergent behaviour [...] Read more.
Future high traffic densities with drone operations are expected to exceed the number of aircraft that current air traffic control procedures can control simultaneously. Despite extensive research on geometric CR methods, at higher densities, their performance is hindered by the unpredictable emergent behaviour from surrounding aircraft. In response, research has shifted its attention to creating automated tools capable of generating conflict resolution (CR) actions adapted to the environment and not limited by man-made rules. Several works employing reinforcement learning (RL) methods for conflict resolution have been published recently. Although proving that they have potential, at their current development, the results of the practical implementation of these methods do not reach their expected theoretical performance. Consequently, RL applications cannot yet match the efficacy of geometric CR methods. Nevertheless, these applications can improve the set of rules that geometrical CR methods use to generate a CR manoeuvre. This work employs an RL method responsible for deciding the parameters that a geometric CR method uses to generate the CR manoeuvre for each conflict situation. The results show that this hybrid approach, combining the strengths of geometric CR and RL methods, reduces the total number of losses of minimum separation. Additionally, the large range of different optimal solutions found by the RL method shows that the rules of geometric CR method must be expanded, catering for different conflict geometries. Full article
(This article belongs to the Special Issue Application of Data Science to Aviation II)
Show Figures

Figure 1

19 pages, 4661 KiB  
Article
Cluster-Based Aircraft Fuel Estimation Model for Effective and Efficient Fuel Budgeting on New Routes
by Jefry Yanto and Rhea P. Liem
Aerospace 2022, 9(10), 624; https://doi.org/10.3390/aerospace9100624 - 20 Oct 2022
Cited by 3 | Viewed by 1534
Abstract
Fuel burn accounts for up to 25% of an aircraft’s total operating cost and has become one of the most important decision factors in the airline industry. Hence, prudent fuel estimation is essential for airlines to ensure smooth operation in the upcoming [...] Read more.
Fuel burn accounts for up to 25% of an aircraft’s total operating cost and has become one of the most important decision factors in the airline industry. Hence, prudent fuel estimation is essential for airlines to ensure smooth operation in the upcoming financial year. Challenges arise when airlines need to estimate the total fuel consumption of new sectors where data are not available. This necessitates the derivation of a robust parametric model that can represent the characteristics of the new route even in the absence of relevant data. To address this issue, we propose a two-step approach to derive a model that can accurately estimate the aircraft fuel needed. The developed approach involves both unsupervised learning and a regression model. For the unsupervised learning step, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) is used to cluster the principal component analysis (PCA)-reduced data. This step can automatically separate flight sectors based on their underlying characteristics, as revealed by their principal components, upon filtering the noise in the data. Afterward, multivariate linear regression (MLR) is used to derive the equations for each cluster. The PCA-based clustered model is shown to be superior to using a global model for a single aircraft type. This approach yields fuel estimation with less than 5% root mean square error for existing routes within each cluster. More importantly, the proposed method can accurately estimate the total fuel of a new route with less than 2% aggregate error, thereby addressing one of the current limitations in the airline fuel estimation study. Full article
(This article belongs to the Special Issue Application of Data Science to Aviation II)
Show Figures

Figure 1

19 pages, 4264 KiB  
Article
Clustering Federated Learning for Bearing Fault Diagnosis in Aerospace Applications with a Self-Attention Mechanism
by Weihua Li, Wansheng Yang, Gang Jin, Junbin Chen, Jipu Li, Ruyi Huang and Zhuyun Chen
Aerospace 2022, 9(9), 516; https://doi.org/10.3390/aerospace9090516 - 15 Sep 2022
Cited by 8 | Viewed by 2415
Abstract
Bearings, as the key mechanical components of rotary machinery, are widely used in modern aerospace equipment, such as helicopters and aero-engines. Intelligent fault diagnosis, as the main function of prognostic health management systems, plays a critical role in maintaining equipment safety in aerospace [...] Read more.
Bearings, as the key mechanical components of rotary machinery, are widely used in modern aerospace equipment, such as helicopters and aero-engines. Intelligent fault diagnosis, as the main function of prognostic health management systems, plays a critical role in maintaining equipment safety in aerospace applications. Recently, data-driven intelligent diagnosis approaches have achieved great success due to the availability of large-scale, high-quality, and complete labeled data. However, in a real application, labeled data is often scarce because it requires manual labeling, which is time-consuming and labor-intensive. Meanwhile, health monitoring data are usually scattered in different regions or equipment in the form of data islands. Traditional fault diagnosis techniques fail to gather enough data for model training due to data security, economic conflict, relative laws, and other reasons. Therefore, it is a challenge to effectively combine the data advantages of different equipment to develop an intelligent diagnosis model with better performance. To address this issue, a novel clustering federated learning (CFL) method with a self-attention mechanism is proposed for bearing fault diagnosis. Firstly, a deep neural network with a self-attention mechanism is developed in a convolutional pipe for feature extraction, which can capture local and global information from raw input. Then, the CFL is further constructed to gather the data from different equipment with similar data distribution in an unsupervised manner. Finally, the CFL-based diagnosis model can be well trained by fully utilizing the distributed data, while ensuring data privacy safety. Experiments are carried out with three different bearing datasets in aerospace applications. The effectiveness and the superiority of the proposed method have been validated compared with other popular fault diagnosis schemes. Full article
(This article belongs to the Special Issue Application of Data Science to Aviation II)
Show Figures

Figure 1

29 pages, 2300 KiB  
Article
Using Reinforcement Learning to Improve Airspace Structuring in an Urban Environment
by Marta Ribeiro, Joost Ellerbroek and Jacco Hoekstra
Aerospace 2022, 9(8), 420; https://doi.org/10.3390/aerospace9080420 - 01 Aug 2022
Viewed by 1486
Abstract
Current predictions on future drone operations estimate that traffic density orders of magnitude will be higher than any observed in manned aviation. Such densities redirect the focus towards elements that can decrease conflict rate and severity, with special emphasis on airspace structures, an [...] Read more.
Current predictions on future drone operations estimate that traffic density orders of magnitude will be higher than any observed in manned aviation. Such densities redirect the focus towards elements that can decrease conflict rate and severity, with special emphasis on airspace structures, an element that has been overlooked within distributed environments in the past. This work delves into the impacts of different airspace structures in multiple traffic scenarios, and how appropriate structures can increase the safety of future drone operations in urban airspace. First, reinforcement learning was used to define optimal heading range distributions with a layered airspace concept. Second, transition layers were reserved to facilitate the vertical deviation between cruising layers and conflict avoidance. The effects of traffic density, non-linear routes, and vertical deviation between layers were tested in an open-source airspace simulation platform. Results show that optimal structuring catered to the current traffic scenario improves airspace usage by correctly segmenting aircraft according to their flight routes. The number of conflicts and losses of minimum separation was reduced versus using a single, uniform airspace structure for all traffic scenarios, thus enabling higher airspace capacity. Full article
(This article belongs to the Special Issue Application of Data Science to Aviation II)
Show Figures

Figure 1

19 pages, 4856 KiB  
Article
Recognition of the Airspace Affected by the Presence of Volcanic Ash from Popocatepetl Volcano Using Historical Satellite Images
by José Carlos Jiménez-Escalona, José Luis Poom-Medina, Julie Roberge, Ramon S. Aparicio-García, José Eduardo Avila-Razo, Oliver Marcel Huerta-Chavez and Rodrigo Florencio Da Silva
Aerospace 2022, 9(6), 308; https://doi.org/10.3390/aerospace9060308 - 07 Jun 2022
Cited by 2 | Viewed by 2209
Abstract
A volcanic eruption can produce large ash clouds in the atmosphere around a volcano, affecting commercial aviation use of the airspace around the volcano. Encountering these ash clouds can cause severe damage to different parts of the aircraft, mainly the engines. This work [...] Read more.
A volcanic eruption can produce large ash clouds in the atmosphere around a volcano, affecting commercial aviation use of the airspace around the volcano. Encountering these ash clouds can cause severe damage to different parts of the aircraft, mainly the engines. This work seeks to contribute to the development of methods for observing the dispersion of volcanic ash and to complement computational methods that are currently used for the prediction of ash dispersion. The method presented here is based on the frequency of occurrence of the regions of airspace areas affected by ash emission during a volcanic eruption. Popocatepetl volcano, 60 km east of Mexico City is taken as a case study. A temporal wind analysis was carried out at different atmospheric levels, to identify the direction towards which the wind disperses ash at different times of the year. This information showed two different trends, related to seasons in the direction of dispersion: the first from November to May and the second from July to September. To identify the ash cloud and estimate its area, a set of 920 MODIS images that recorded Popocatepetl volcanic activity between 2000 and 2021 was used. These satellite images were subjected to a semi-automatic, digital pre-processing of binarization by thresholds, according to the level of the brightness temperature difference between band 31 (11 µm) and band 32 (12 µm), followed by manual evaluation of each binarized image. With the information obtained by the processing of the MODIS image, an information table was built with the geographical position of each pixel characterized by the presence of ash for each event. With these data, the areas around Popocatepetl volcano with the highest frequency of affectation by ash emissions were identified during the period analyzed. This study seeks to complement the results obtained by numerical models that make forecasts of ash dispersions and that are very important for the prevention of air navigation risks. Full article
(This article belongs to the Special Issue Application of Data Science to Aviation II)
Show Figures

Figure 1

Back to TopTop