Thales

Dorian Martinez

François Coulmeau

Christophe Pierre

Guillaume Meulle

Guillaume Pabia

Emilie Bies

Bastien Crete

Jori Ferrus

Philippe Francez

Devices and computer-implemented methods for analyzing aircraft trajectories, the method includes the steps of receiving data associated with a plurality of aircraft trajectories; breaking the trajectories down into a plurality of vectors, a vector comprising one or more sequences of enumerators; aligning multiple vectorized trajectories by shifting sequences of enumerators by one or more positions; and detecting one or more anomalies in one or more trajectories by unsupervised classification (e.g. DBSCAN). Developments describe the supervised determination of trajectory anomaly detection models, the use of density-based algorithms, the use of one or more neural networks and/or decision trees, one or more display steps, notably displaying root causes (explainable or understandable artificial intelligence), the processing of avionics data flows, etc. System (e.g. computing) and software aspects are described.

Analysis of aircraft trajectories

Systems and methods for managing the flight of an aircraft, include the steps of receiving data from recordings of the flight of an aircraft; the data comprising data from sensors and/or data from the onboard avionics; determining the aircraft state at a point N on the basis of the received data; determining the state of the aircraft at the point N+1 on the basis of the state of the aircraft at point N by applying a model learnt by means of machine learning. Developments describe the use of the flight parameters SEP, FF and N1; offline and/or online unsupervised machine learning, according to a variety of algorithms and neural networks. Software aspects are described.

Machine learning in avionics

Methods and systems for optimizing the flight of an aircraft are disclosed. The trajectory is divided into segments, each of the segments being governed by distinct sets of equations, depending on engine thrust mode and on vertical guidance (climb, cruise or descent). By assuming two, aerodynamic and engine-speed, models, data from flight recordings are received and a number of parameters from a parameter-optimization engine is iteratively determined by applying a least-squares calculation until a predefined minimality criterion is satisfied. The parameter optimization engine is next used to predict the trajectory point following a given point. Software aspects and system (e.g. FMS and/or EFB) aspects are described.

Optimizing a parametric model of aircraft performance

A method is provided for managing the revising of a flight plan of an aircraft implemented by at least two systems, one being of avionics type (qualified, certified) and the other not. From a flight plan, flight plan revisions are determined, even assessed, then one or more of these revisions are selected and/or combined. Subsequently, these combinations are processed by the avionics system and the corresponding avionics parameters are calculated. By comparing the different results of avionics quality, the impact of each revision can be quantified then rendered to the pilot to assist in his or her decision-making, in particular with regard to negotiating the revisions with air traffic control. Combinatorial optimization and learning steps are described, as are system and software aspects.

Growing community of inventors

Toulouse, France

Dorian Martinez