Skip to content


Research projects For Aircraft Operators

PERF-AI will apply Machine Learning techniques on flight data to accurately measure actual aircraft performance throughout its lifecycle.

Current airline operations work with a planned trajectory, which is used as input to the Flight Management System (FMS). All this pre-flight phase is based on a single manufacturer’s performance model that is the same for every aircraft of the same type, and also on a weather forecast that is computed long before the flight. Therefore, flight route is pre-established at specific altitudes and speeds, from take-off to landing. However, the actual flight is often very different one because of ATC constraints, adverse weather, wind changes and tactical re-routing.

PERF-AI focusses on identifying adequate machine learning algorithms, testing their accuracy and capability to perform flight data statistical analysis and developing mathematical models to optimise in-turn real flight trajectories with respect to the aircraft performance. Thus, minimising fuel consumption throughout the flight.

The consortium consists of Safety-Line (FR), INRIA Lille and Thales as Topic Leader. With Transavia France and Lufthansa participating to the advisory board, it will test and validate different statistical models that will allow to accurately solve some optimization problems and implement them in an operational environment.

The project leading to this application has received funding from the Clean Sky 2 Joint Undertaking under the European Union’s Horizon 2020 research and innovation programme under grant agreement No 815914