Search Results

The evaluation of aircraft characteristics through flight test maneuvers is fundamental to aviation safety and understanding flight attributes. This research project proposes a comprehensive methodology to detect and analyze aircraft maneuvers using full flight data, combining signal processing and machine learning techniques. Leveraging the Wavelet Transform, we unveil intricate temporal details within flight data, uncovering critical time-frequency insights essential for aviation safety. The integration of Long Short-Term Memory (LSTM) models enhances our ability to capture temporal dependencies, surpassing the capabilities of machine learning in isolation. These extracted maneuvers not only aid in safety but also find practical applications in system identification, air-data calibration, and performance analysis, significantly reducing pre-processing time for analysts.

Aerodynamic database update from the flight tests using system identification techniques is a crucial tool for the development of control laws and high fidelity simulators. For the certification of aircraft under test, aero-database needs to be validated from flight tests throughout the flight envelope and also to certain levels beyond the envelope boundaries. Validation of aero-database close to envelope boundaries entails additional complexities which necessitates careful handling of flight data identification and update process. This paper discusses the approach adopted for aero-database update and flight clearance, followed by a discussion on the issues relevant in the extreme flight test regimes, such as, flow angle accuracy at higher angles-of-attack, center-of-gravity variation with fuel pitch angle for high-g maneuvering conditions and inaccuracies in Mach number at transonic speeds.