Titre:	Abordagem de agrupamento no planejamento de voo sob tempo severo convectivo
Auteur(s):	Barbosa, Iuri Souza Ramos
Orientador(es)::	Weigang, Li
Assunto::	Planejamento de voo Meteorologia Metodologia computacional Aprendizagem - computadores
Date de publication:	21-fév-2020
Data de defesa::	21-jui-2019
Référence bibliographique:	BARBOSA, Iuri Souza Ramos. Abordagem de agrupamento no planejamento de voo sob tempo severo convectivo. 2019. xx, 104 f., il. Dissertação (Mestrado em Informática)—Universidade de Brasília, Brasília, 2019.
Abstract:	Aircraft detect the existence of adverse weather conditions on their way with the help of their onboard weather radar. Knowing the location of the weather obstacle, the pilot then decides whether or not to change the course of the aircraft. However, the onboard weather radar has some limitations related to the detection range of convection cells (cumulonimbus clouds) in the airspace. Therefore, the course of actions that the pilot can perform is limited to the accuracy of this device. The proposed work builds an intelligent system for flight planning under adverse weather conditions. The proposed methodology mainly uses two data sources. On the one hand, it consumes flight tracking information to delimit the boundaries of airways while, on the other hand, consumes weather information on convection cells obtained from ground-based weather radars in the Brazilian airspace. Therefore, knowing the locations of convection cells and the boundaries of the airways in the airspace, it is possible to identify in two steps whether an aircraft is heading towards the tracked convection cells. Firstly, tracked flight positions are used to identify the boundaries that delimit the airways in the airspace. Secondly, the locations obtained for the airways in the previous step are then compared with the locations of the convection cells in order to identify possible intersections between them. To delimit the boundaries of airways connecting departure and destination airports, a linear interpolation algorithm is used to transform the tracked flight positions into normalized flight positions. Next, a clustering algorithm is used to group these new flight positions into clusters, which in turn define the boundaries of the airways. An intersection between the newly defined airways and the tracked convection cells is found if the measured distance is less than or equal to the radius of the convection cell. The identified intersections are then used for flight planning by stakeholders. Regarding the delimitation of airways, after running simulations using different algorithms and parameters in several test scenarios, the best results are obtained using the Density-Based Spatial Clustering of Applications with Noise algorithm along with the Haversine formula as its distance measure parameter. Both the usage of Hierarchical Density-Based Spatial Clustering of Applications with Noise algorithm, and the usage of Euclidean distance provide poor results. Finally, the proposed solution contributes to the optimization of air traffic flow, reduction of aircraft delay, reduction of fuel consumption, etc., in other words, has a positive impact factor in Air Traffic Management.
metadata.dc.description.unidade:	Instituto de Ciências Exatas (IE) Departamento de Ciência da Computação (IE CIC)
Description:	Dissertação (mestrado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Ciência da Computação, 2019.
metadata.dc.description.ppg:	Programa de Pós-Graduação em Informática
Licença::	A concessão da licença deste item refere-se ao termo de autorização impresso assinado pelo autor com as seguintes condições: Na qualidade de titular dos direitos de autor da publicação, autorizo a Universidade de Brasília e o IBICT a disponibilizar por meio dos sites www.bce.unb.br, www.ibict.br, http://hercules.vtls.com/cgi-bin/ndltd/chameleon?lng=pt&skin=ndltd sem ressarcimento dos direitos autorais, de acordo com a Lei nº 9610/98, o texto integral da obra disponibilizada, conforme permissões assinaladas, para fins de leitura, impressão e/ou download, a título de divulgação da produção científica brasileira, a partir desta data.
Collection(s) :	Teses, dissertações e produtos pós-doutorado

Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.