AffiliationAirbus Defense and Space
MetadataShow full item record
CitationAlvarez, P. R. & Herrero, F. C. (2023). AITA. Automatic Manoeuvre Detection Based on Wavelets. International Telemetering Conference Proceedings, 58.
AbstractMost of the Test analyses are repetitive and therefore can be automated. The instrumentation of prototypes is becoming heavier and all parameters require validation. Most Test analyses tasks are manual, time consuming and prone to human errors. AITA is an Airbus R&T project with the aim of developing a framework based on AI to automate most of these tasks and replace the obsolete tools currently in place. This paper will describe the technique used for Automatic Manoeuvre Detection and Validation which is part of the AITA project. The Automatic Manoeuvre Detection is based on Pattern identification. The analysis methodology used consists of building adaptive wavelets in the sense of least squares to a specific pattern. Once the wavelet is available, the CWT (Continuous Wavelet Transform) is used to find the pattern in the time history. This Methodology is an improvement of the one included in the BMAD item  (Big-data Manoeuvre Automatic Detection) project. Besides improving the pattern generation, including new parameters that help determine the manoeuvres validation, the data access and pattern search library has been optimized by migrating python library to C++ and parallelizing the process. This paper explains the steps followed for the automatic manoeuvre detection validation using real flights belonging to ADS aircraft fleet.