ENAC  Laboratoire de Mathématiques Appliquées Informatique et Automatique pour l'Aérien (Toulouse)
Overview
Works:  10 works in 16 publications in 2 languages and 17 library holdings 

Genres:  Academic theses 
Roles:  Other, 981 
Publication Timeline
.
Most widely held works by
ENAC  Laboratoire de Mathématiques Appliquées Informatique et Automatique pour l'Aérien (Toulouse)
Contribution to fault tolerant flight control under actuator failures by
Lunlong Zhong(
Book
)
2 editions published in 2014 in English and held by 3 WorldCat member libraries worldwide
The objective of this thesis is to optimize the use of redundant actuators for a transportation aircraft once some actuators failure occurs during the flight. Here, the fault tolerant ability resulting from the redundant actuators is mainly considered. Different classical concepts and methods related to a fault tolerant flight control channel are first reviewed and new concepts useful for the required analysis are introduced. The problem which is tackled here is to develop a design methodology for fault tolerant flight control in the case of a partial actuator failure which will allow the aircraft to continue safely the intended maneuver. A two stages control approach is proposed and applied to both the remaining maneuverability evaluation and a fault tolerant control structure design. In the first case, an offline handling qualities assessment method based on Model Predictive Control is proposed. In the second case, a fault tolerant control structure based on Nonlinear Inverse Control and online actuator reassignment is developed. In both cases, a Linear Quadratic (LQ) programming problem is formulated and different failure cases are considered when an aircraft performs a classical maneuver. Three numerical solvers are studied and applied to the offline and online solutions of the resulting LQ problems
2 editions published in 2014 in English and held by 3 WorldCat member libraries worldwide
The objective of this thesis is to optimize the use of redundant actuators for a transportation aircraft once some actuators failure occurs during the flight. Here, the fault tolerant ability resulting from the redundant actuators is mainly considered. Different classical concepts and methods related to a fault tolerant flight control channel are first reviewed and new concepts useful for the required analysis are introduced. The problem which is tackled here is to develop a design methodology for fault tolerant flight control in the case of a partial actuator failure which will allow the aircraft to continue safely the intended maneuver. A two stages control approach is proposed and applied to both the remaining maneuverability evaluation and a fault tolerant control structure design. In the first case, an offline handling qualities assessment method based on Model Predictive Control is proposed. In the second case, a fault tolerant control structure based on Nonlinear Inverse Control and online actuator reassignment is developed. In both cases, a Linear Quadratic (LQ) programming problem is formulated and different failure cases are considered when an aircraft performs a classical maneuver. Three numerical solvers are studied and applied to the offline and online solutions of the resulting LQ problems
Optimisation des procédures de départ et d'arrivée dans une zone terminale by
Jun Zhou(
Book
)
2 editions published in 2017 in French and held by 2 WorldCat member libraries worldwide
This thesis proposes a methodology for the optimization of departure and arrival routes in the Terminal Maneuvering Area (TMA). The design of these routes takes into account the configuration and environment around airports, and the related constraints, in particular the avoidance of obstacles and the separation between routes. We propose a mathematical formulation leading to a combinatorial optimization problem, as well as efficient ad hoc resolution methods for the problem. The problem is solved in two steps. First, we design an individual route avoiding obstacles with respect to minimum route length by using a Branch and Bound (B&B) method. Afterwards, the design of multiple routes is solved by two different approaches: a B&Bbased approach (where routes are generated sequentially in a given order) and a Simulated Annealing approach (where routes are generated simultaneously). The simulation results of a set of (artificial and real) test problems show the efficiency of our approach
2 editions published in 2017 in French and held by 2 WorldCat member libraries worldwide
This thesis proposes a methodology for the optimization of departure and arrival routes in the Terminal Maneuvering Area (TMA). The design of these routes takes into account the configuration and environment around airports, and the related constraints, in particular the avoidance of obstacles and the separation between routes. We propose a mathematical formulation leading to a combinatorial optimization problem, as well as efficient ad hoc resolution methods for the problem. The problem is solved in two steps. First, we design an individual route avoiding obstacles with respect to minimum route length by using a Branch and Bound (B&B) method. Afterwards, the design of multiple routes is solved by two different approaches: a B&Bbased approach (where routes are generated sequentially in a given order) and a Simulated Annealing approach (where routes are generated simultaneously). The simulation results of a set of (artificial and real) test problems show the efficiency of our approach
Contribution to engineout aircraft trajectory management and control by
Hongying Wu(
Book
)
2 editions published in 2013 in English and held by 2 WorldCat member libraries worldwide
Engineout is an undoubted critical situation for flight safety. The objective of this thesis is to improve the management of emergency manoeuvres for transportation aircraft once all engines go out at a given point during the flight. Here we consider the evolution of the gliding aircraft along a vertical plane possibly leading directly to a safe landing place. The gliding qualities of standard transportation aircraft are first analyzed and reachable areas from given initial situations are established. Once a safe reachable area exists the problem which is tackled here is to develop design principles for a guidance system which makes the aircraft perform a feasible glide trajectory towards such landing area. Reverse dynamic programming is used to build backwards sets of feasible trajectories leading to final conditions compatible with engineout landing. To get an online device to produce efficient directives for the autopilot or the human pilot (through a flight director), a neural network is built from the generated database. Then simulation results are analyzed for validation and further improvements of the proposed approach are considered
2 editions published in 2013 in English and held by 2 WorldCat member libraries worldwide
Engineout is an undoubted critical situation for flight safety. The objective of this thesis is to improve the management of emergency manoeuvres for transportation aircraft once all engines go out at a given point during the flight. Here we consider the evolution of the gliding aircraft along a vertical plane possibly leading directly to a safe landing place. The gliding qualities of standard transportation aircraft are first analyzed and reachable areas from given initial situations are established. Once a safe reachable area exists the problem which is tackled here is to develop design principles for a guidance system which makes the aircraft perform a feasible glide trajectory towards such landing area. Reverse dynamic programming is used to build backwards sets of feasible trajectories leading to final conditions compatible with engineout landing. To get an online device to produce efficient directives for the autopilot or the human pilot (through a flight director), a neural network is built from the generated database. Then simulation results are analyzed for validation and further improvements of the proposed approach are considered
Optimisation des trajectoires avion dans l'Atlantique Nord by
Olga Rodionova(
Book
)
2 editions published in 2015 in English and held by 2 WorldCat member libraries worldwide
This thesis investigates the ways to improve the air traffic system in the highly congested North Atlantic oceanic airspace (NAT). First, we consider the current system, where aircraft follow predefined NAT tracks. We favor the reroutings between tracks, decreasing congestion in preoceanic airspace, and apply stochastic methods of optimization to find a conflictfree flight configuration with reduced separation between aircraft. Second, we simulate trajectory prediction by Wind Networking (WN). While the main source of time prediction errors is the uncertainty in wind forecast, WN permits aircraft to exchange measured winds and adjust their predictions using this recent and accurate information. Third, we study the impact of introducing the free flight concept in NAT. We apply a stochastic method of optimization on data provided by NASA consisting of NAT flights with wind optimal trajectories. The aim is to reduce the number of conflicts on the strategic level, while keeping the trajectories close to the optimal routes. Our computational experiments show that the air traffic situation in NAT can be improved in several different ways, considering new technologies and new trajectory planning concepts
2 editions published in 2015 in English and held by 2 WorldCat member libraries worldwide
This thesis investigates the ways to improve the air traffic system in the highly congested North Atlantic oceanic airspace (NAT). First, we consider the current system, where aircraft follow predefined NAT tracks. We favor the reroutings between tracks, decreasing congestion in preoceanic airspace, and apply stochastic methods of optimization to find a conflictfree flight configuration with reduced separation between aircraft. Second, we simulate trajectory prediction by Wind Networking (WN). While the main source of time prediction errors is the uncertainty in wind forecast, WN permits aircraft to exchange measured winds and adjust their predictions using this recent and accurate information. Third, we study the impact of introducing the free flight concept in NAT. We apply a stochastic method of optimization on data provided by NASA consisting of NAT flights with wind optimal trajectories. The aim is to reduce the number of conflicts on the strategic level, while keeping the trajectories close to the optimal routes. Our computational experiments show that the air traffic situation in NAT can be improved in several different ways, considering new technologies and new trajectory planning concepts
Flight guidance along 3D+T trajectories and space indexed traffic management by
Mastura Ab Wahid(
Book
)
2 editions published in 2015 in English and held by 2 WorldCat member libraries worldwide
With the increase in air traffic, surely a question of flight efficiency (delays), environment impact and safety arise. This calls for improvements in accuracy of spatial and temporal trajectory tracking. The first main objective of this thesis is to contribute to the synthesis of a spaceindexed nonlinear guidance control law for transportation aircraft presenting enhanced tracking performances and to explore the performances and feasibility of a flight guidance control law which is developed based on a spaceindexed reference to track a 3D+T reference trajectory using nonlinear dynamic inversion control. The proposed guidance control law present reduced tracking errors and able to meet more easily overfly time constraints. Before presenting the main approaches for the design of the 3D+T guidance control laws; the modern flight guidance and flight dynamics of transportation aircraft, including explicitly wind components are first introduced. Then, a description of the current and modern air traffic organization including the organization of air traffic in high density flow will be shown and this will lead to a description of the Airstreams concept. This proposed concept is to organize main traffic flows in congested airspace along airstreams which are characterized by a three dimensional (3D) common reference track (ASRT). Finally, a scenario to perform basic maneuvers inside the airstream following a 3D+T trajectory using a common spaceindexed will be developed and will be used to illustrate the traffic management along an airstream
2 editions published in 2015 in English and held by 2 WorldCat member libraries worldwide
With the increase in air traffic, surely a question of flight efficiency (delays), environment impact and safety arise. This calls for improvements in accuracy of spatial and temporal trajectory tracking. The first main objective of this thesis is to contribute to the synthesis of a spaceindexed nonlinear guidance control law for transportation aircraft presenting enhanced tracking performances and to explore the performances and feasibility of a flight guidance control law which is developed based on a spaceindexed reference to track a 3D+T reference trajectory using nonlinear dynamic inversion control. The proposed guidance control law present reduced tracking errors and able to meet more easily overfly time constraints. Before presenting the main approaches for the design of the 3D+T guidance control laws; the modern flight guidance and flight dynamics of transportation aircraft, including explicitly wind components are first introduced. Then, a description of the current and modern air traffic organization including the organization of air traffic in high density flow will be shown and this will lead to a description of the Airstreams concept. This proposed concept is to organize main traffic flows in congested airspace along airstreams which are characterized by a three dimensional (3D) common reference track (ASRT). Finally, a scenario to perform basic maneuvers inside the airstream following a 3D+T trajectory using a common spaceindexed will be developed and will be used to illustrate the traffic management along an airstream
Passengers : customers, actors and sensors of the air transportation system by
Philippe Monmousseau(
Book
)
2 editions published in 2020 in English and held by 2 WorldCat member libraries worldwide
Air transportation uses planes to transport passengers efficiently between two airports, and its development has been driven by the continuous improvement of planes as a safe and efficient means of transportation. However, if the COVID19 pandemic has taught the air transportation system one lesson, it's that a problem affecting passengers can be far more detrimental to the air transportation system than a problem affecting planes. Acknowledging the fact that passengers are omnipresent and necessary to the air transportation system, this study proposes to consider passengers as sensors of the air transportation system and harness data generated by passengers to evaluate in near real time the flightcentric metrics traditionally used to evaluate the air transportation system performance. Data generated by passengers have the additional benefit of offering a means of evaluating the interactions between passengers and the other stakeholders of the air transportation system, such as airlines and airports. The journey of a passenger starting and ending beyond the boundaries of airport facilities, the data generated by passengers throughout their journey can also be used to evaluate the full doortodoor journey of a passenger of the air transportation system
2 editions published in 2020 in English and held by 2 WorldCat member libraries worldwide
Air transportation uses planes to transport passengers efficiently between two airports, and its development has been driven by the continuous improvement of planes as a safe and efficient means of transportation. However, if the COVID19 pandemic has taught the air transportation system one lesson, it's that a problem affecting passengers can be far more detrimental to the air transportation system than a problem affecting planes. Acknowledging the fact that passengers are omnipresent and necessary to the air transportation system, this study proposes to consider passengers as sensors of the air transportation system and harness data generated by passengers to evaluate in near real time the flightcentric metrics traditionally used to evaluate the air transportation system performance. Data generated by passengers have the additional benefit of offering a means of evaluating the interactions between passengers and the other stakeholders of the air transportation system, such as airlines and airports. The journey of a passenger starting and ending beyond the boundaries of airport facilities, the data generated by passengers throughout their journey can also be used to evaluate the full doortodoor journey of a passenger of the air transportation system
Evitement de conflits aériens par une régulation subliminale en vitesse : modélisation & résolution via le contrôle optimal by
Loïc Cellier(
Book
)
1 edition published in 2015 in French and held by 1 WorldCat member library worldwide
The purpose of this doctoral thesis is to study models and solution techniques based on optimal control approaches to address air tra_c management problems. Motivated by the growth of air tra_c volume, and by the advances in optimal control theory, this research works focus on analysing aircraft conflict avoidance problem. This study allows development of new approaches and algorithms to help air tra_c controllers. In the framework of air tra_c management, to ensure the minimum safety distances between aircraft, in tactical phases and enroute flight configurations, this thesis focusses on a subliminal velocity regulation strategy to perform the separation, while preserving the aircraft predefined trajectories. A numerical optimal control solution approach as the direct shooting method, wherein involves a total or partial discretization of the problem, transforms the initial problem into a large scale nonlinear programming problem. This kind of methods could generate largesize optimization problems which are numerically di_cult to solve. Depending on the number of variables which involved, this approaches could be too expensive in terms of computation time. Moreover, the statevariables constraints of the problem lead to numerical di_culties, e.g., considering the indirect numerical shooting method. Tailored on aircraft conflict avoidance problems, a detection and a determination of a priori conflict zones allow the decomposition of the optimal control problem into subproblems, easier to solve than the original one. Solving the o_zones subproblems can be addressed using the Pontryagin maximum principle, which allows in this case directly the solution. A combination of direct numerical shooting method and application of conditions of Pontryagin's maximum principle is proposed, and numerical experiments validate this approach
1 edition published in 2015 in French and held by 1 WorldCat member library worldwide
The purpose of this doctoral thesis is to study models and solution techniques based on optimal control approaches to address air tra_c management problems. Motivated by the growth of air tra_c volume, and by the advances in optimal control theory, this research works focus on analysing aircraft conflict avoidance problem. This study allows development of new approaches and algorithms to help air tra_c controllers. In the framework of air tra_c management, to ensure the minimum safety distances between aircraft, in tactical phases and enroute flight configurations, this thesis focusses on a subliminal velocity regulation strategy to perform the separation, while preserving the aircraft predefined trajectories. A numerical optimal control solution approach as the direct shooting method, wherein involves a total or partial discretization of the problem, transforms the initial problem into a large scale nonlinear programming problem. This kind of methods could generate largesize optimization problems which are numerically di_cult to solve. Depending on the number of variables which involved, this approaches could be too expensive in terms of computation time. Moreover, the statevariables constraints of the problem lead to numerical di_culties, e.g., considering the indirect numerical shooting method. Tailored on aircraft conflict avoidance problems, a detection and a determination of a priori conflict zones allow the decomposition of the optimal control problem into subproblems, easier to solve than the original one. Solving the o_zones subproblems can be addressed using the Pontryagin maximum principle, which allows in this case directly the solution. A combination of direct numerical shooting method and application of conditions of Pontryagin's maximum principle is proposed, and numerical experiments validate this approach
Méthodes exactes et heuristiques pour l'ordonnancement des atterrissages d'avions by
Sana Ikli(
)
1 edition published in 2021 in French and held by 1 WorldCat member library worldwide
Airport runways are considered to be one of the main bottlenecks in the airport system and one of the key factors that determine airport capacity. Optimizing the utilization of the runways to reduce delays motivates the numerous studies of the aircraft landing problem. In this thesis, we focus on the problem of scheduling aircraft landings in two different contexts: scheduling landings on one runway considered as an independent resource, and scheduling aircraft arrivals on critical airspace fixes and at the runway threshold. The objective is to minimize the total delay cost. For the first problem, we consider a realistic delaycost representation that is rarely considered in the literature: a convex, piecewise linear function. To solve this problem, two optimization methods are proposed in this thesis: an exact method based on mixedinteger linear programming and a heuristic method based on an optimistic planning algorithm used in reinforcement learning. We also propose in this thesis new realistic and challenging instances for the aircraft landings problem, as the instances of the literature are nowadays easily solved with current versions of optimization software. Numerical tests performed on our instances show that the delays can be significantly reduced when an optimization approach is adopted to schedule aircraft landings. However, the exact method requires prohibitive computation times with the increasing size of the instance (increasing numbers of aircraft). For the second problem, we propose a preliminary study in which we adopt a mixedinteger linear programming approach. The comparison of this approach with the technique traditionally used by air traffic controllers reveals once again how beneficial an optimization approach can be for reducing delays
1 edition published in 2021 in French and held by 1 WorldCat member library worldwide
Airport runways are considered to be one of the main bottlenecks in the airport system and one of the key factors that determine airport capacity. Optimizing the utilization of the runways to reduce delays motivates the numerous studies of the aircraft landing problem. In this thesis, we focus on the problem of scheduling aircraft landings in two different contexts: scheduling landings on one runway considered as an independent resource, and scheduling aircraft arrivals on critical airspace fixes and at the runway threshold. The objective is to minimize the total delay cost. For the first problem, we consider a realistic delaycost representation that is rarely considered in the literature: a convex, piecewise linear function. To solve this problem, two optimization methods are proposed in this thesis: an exact method based on mixedinteger linear programming and a heuristic method based on an optimistic planning algorithm used in reinforcement learning. We also propose in this thesis new realistic and challenging instances for the aircraft landings problem, as the instances of the literature are nowadays easily solved with current versions of optimization software. Numerical tests performed on our instances show that the delays can be significantly reduced when an optimization approach is adopted to schedule aircraft landings. However, the exact method requires prohibitive computation times with the increasing size of the instance (increasing numbers of aircraft). For the second problem, we propose a preliminary study in which we adopt a mixedinteger linear programming approach. The comparison of this approach with the technique traditionally used by air traffic controllers reveals once again how beneficial an optimization approach can be for reducing delays
Trafic aérien : détermination optimale et globale des trajectoires d'avion en présence de vent by
Brunilde Girardet(
)
1 edition published in 2014 in French and held by 1 WorldCat member library worldwide
In the context of the future Air Traffic Management system (ATM), one objective is to reduce the environmental impact of air traffic. With respect to this criterion, the "freeroute" concept, introduced in the mid 1990's, is well suited to improve over nowadays airspace based ATM. Aircraft will no longer be restricted to fly along airways and may fly along fueloptimal routes. The objective of this thesis is to introduce a novel pretactical trajectory planning methodology which aims at minimizing airspace congestion while taking into account weather conditions so as to minimize also fuel consumption.The development of the method was divided in two steps. The first step is dedicated to compute a timeoptimal route for one aircraft taking into account wind conditions. This optimization is based on an adaptation of the Ordered Upwind Method on the sphere.The second step introduces a hybrid algorithm, based on simulated annealing and on the deterministic algorithm developed in the first step, in order to minimize congestion. Thus the algorithm combines the ability to reach a globallyoptimal solution with a localsearch procedure that speeds up the convergence
1 edition published in 2014 in French and held by 1 WorldCat member library worldwide
In the context of the future Air Traffic Management system (ATM), one objective is to reduce the environmental impact of air traffic. With respect to this criterion, the "freeroute" concept, introduced in the mid 1990's, is well suited to improve over nowadays airspace based ATM. Aircraft will no longer be restricted to fly along airways and may fly along fueloptimal routes. The objective of this thesis is to introduce a novel pretactical trajectory planning methodology which aims at minimizing airspace congestion while taking into account weather conditions so as to minimize also fuel consumption.The development of the method was divided in two steps. The first step is dedicated to compute a timeoptimal route for one aircraft taking into account wind conditions. This optimization is based on an adaptation of the Ordered Upwind Method on the sphere.The second step introduces a hybrid algorithm, based on simulated annealing and on the deterministic algorithm developed in the first step, in order to minimize congestion. Thus the algorithm combines the ability to reach a globallyoptimal solution with a localsearch procedure that speeds up the convergence
Apprentissage artificiel appliqué à la prévision de trajectoire d'avion by
Richard Alligier(
Book
)
1 edition published in 2014 in French and held by 1 WorldCat member library worldwide
L'organisme Eurocontrol prévoit une forte hausse du trafic aérien européen d'ici l'année 2035. Cette hausse de trafic justifie le développement de nouveaux concepts et outils pour pouvoir assurer les services dus aux usagers de l'espace aérien. La prévision de trajectoires d'avion est au coeur de ces évolutions. Parmi ces outils, les outils de détection et résolution de conflits utilisent les trajectoires prédites pour anticiper les pertes de séparation entre avions et proposer des solutions aux contrôleurs aériens. L'horizon de prédiction utilisé pour cette application est de l'ordre de dix à vingt minutes. Parmi les algorithmes réalisant une détection et résolution de conflits, certains sont mis en œuvre au sol, obligeant ainsi les prédictions à être calculées en n'utilisant que les informations disponibles dans les systèmes sols. Dans ces systèmes, la masse des avions ainsi que les profils de vitesse ou de poussée des moteurs ne sont pas connus. Ainsi, le calcul d'une trajectoire prédite avec un modèle physique se fait en utilisant des valeurs de référence pour les paramètres inconnus. Dans ce cadre, nous nous intéressons à la phase de montée pour laquelle ces paramètres influent grandement sur la trajectoire de l'avion. Ce travail s'appuie sur le modèle physique BADA développé et maintenu par Eurocontrol. Ce modèle physique modélise, entre autres, les performances des avions. Il fournit également des valeurs de référence pour les paramètres inconnus comme la masse de l'avion, son profil de vitesse en montée, ou la commande de poussée des moteurs. Ce modèle, largement utilisé dans le monde entier, est particulièrement imprécis pour la phase de montée, car les valeurs réelles de ces paramètres sont parfois très éloignées des valeurs de référence. Dans cette thèse, nous proposons soit d'estimer directement certains paramètres, comme la masse, à partir des points passés de la trajectoire, soit d'utiliser des méthodes d'apprentissage supervisé afin d'apprendre, à partir d'exemples, des modèles prédisant les valeurs des paramètres manquants (masse, loi de poussée, vitesses cibles). Ces différentes méthodes sont testées sur des données radar ModeC et ModeS sur plusieurs types d'avions. Les prédictions obtenues avec ces méthodes sont comparées à celles obtenues avec les paramètres de référence. Elles sont également comparées avec les prédictions obtenues par des méthodes de régression prédisant directement l'altitude de l'avion plutôt que les paramètres du modèle physique. Nos méthodes permettent de réduire, suivant le type de l'avion, de 50 % à 85 % par rapport à la méthode BADA de référence, la racine de l'erreur quadratique moyenne sur l'altitude prédite à un horizon de dix minutes
1 edition published in 2014 in French and held by 1 WorldCat member library worldwide
L'organisme Eurocontrol prévoit une forte hausse du trafic aérien européen d'ici l'année 2035. Cette hausse de trafic justifie le développement de nouveaux concepts et outils pour pouvoir assurer les services dus aux usagers de l'espace aérien. La prévision de trajectoires d'avion est au coeur de ces évolutions. Parmi ces outils, les outils de détection et résolution de conflits utilisent les trajectoires prédites pour anticiper les pertes de séparation entre avions et proposer des solutions aux contrôleurs aériens. L'horizon de prédiction utilisé pour cette application est de l'ordre de dix à vingt minutes. Parmi les algorithmes réalisant une détection et résolution de conflits, certains sont mis en œuvre au sol, obligeant ainsi les prédictions à être calculées en n'utilisant que les informations disponibles dans les systèmes sols. Dans ces systèmes, la masse des avions ainsi que les profils de vitesse ou de poussée des moteurs ne sont pas connus. Ainsi, le calcul d'une trajectoire prédite avec un modèle physique se fait en utilisant des valeurs de référence pour les paramètres inconnus. Dans ce cadre, nous nous intéressons à la phase de montée pour laquelle ces paramètres influent grandement sur la trajectoire de l'avion. Ce travail s'appuie sur le modèle physique BADA développé et maintenu par Eurocontrol. Ce modèle physique modélise, entre autres, les performances des avions. Il fournit également des valeurs de référence pour les paramètres inconnus comme la masse de l'avion, son profil de vitesse en montée, ou la commande de poussée des moteurs. Ce modèle, largement utilisé dans le monde entier, est particulièrement imprécis pour la phase de montée, car les valeurs réelles de ces paramètres sont parfois très éloignées des valeurs de référence. Dans cette thèse, nous proposons soit d'estimer directement certains paramètres, comme la masse, à partir des points passés de la trajectoire, soit d'utiliser des méthodes d'apprentissage supervisé afin d'apprendre, à partir d'exemples, des modèles prédisant les valeurs des paramètres manquants (masse, loi de poussée, vitesses cibles). Ces différentes méthodes sont testées sur des données radar ModeC et ModeS sur plusieurs types d'avions. Les prédictions obtenues avec ces méthodes sont comparées à celles obtenues avec les paramètres de référence. Elles sont également comparées avec les prédictions obtenues par des méthodes de régression prédisant directement l'altitude de l'avion plutôt que les paramètres du modèle physique. Nos méthodes permettent de réduire, suivant le type de l'avion, de 50 % à 85 % par rapport à la méthode BADA de référence, la racine de l'erreur quadratique moyenne sur l'altitude prédite à un horizon de dix minutes
Audience Level
0 

1  
General  Special 
Related Identities
 Université Toulouse 3 Paul Sabatier (1969....). Degree grantor
 École doctorale Mathématiques, informatique et télécommunications (Toulouse) Other
 MoraCamino, Félix (1951....). Opponent Thesis advisor
 École doctorale Systèmes (Toulouse) Other Degree grantor
 Institut national des sciences appliquées (Toulouse / 1961....). Degree grantor
 École doctorale AéronautiqueAstronautique (Toulouse) Other
 Sbihi, Mohammed (1978....). Thesis advisor
 Mongeau, Marcel (19......; chercheur en aéronautique) Opponent Thesis advisor
 Zhong, Lunlong (1979....). Author
 Delahaye, Daniel (19......; chercheur à l'Ecole nationale de l'aviation civile) Opponent Thesis advisor