Semi-parametric Regression based on Machine Learning Methods for UAS Stall Identification

Vincent Guibert (1, 2) , Mathieu Brunot (1) , Murat Bronz (2) , Jean-Philippe Condomines (2)

1 ONERA / DTIS, Université de Toulouse [Toulouse]
2 ENAC - Ecole Nationale de l'Aviation Civile

A semi-parametric regression methodology is formulated to identify the unsteady lift characteristics of a small UAS undergoing dynamic stall. Based on the trailing edge separation model of Leishmann and Beddoes, the nonlinear evolution of the separation point is formulated so that it can be estimated by non-parametric Machine Learning methods. Validation of the methodology is presented with the identification of the lift coefficient based on quasi-steady wind tunnel tests.

Mots clés: Nonlinear system identification; Machine learning; Grey box modelling; Unmanned aircraft system; Stall modelling; Non-parametric methods

Domaines: Sciences de l'ingénieur [physics]; Automatique / Robotique

Vincent Guibert, Mathieu Brunot, Murat Bronz, Jean-Philippe Condomines. Semi-parametric Regression based on Machine Learning Methods for UAS Stall Identification. 19th IFAC Symposium on System Identification, Jul 2021, Padova (virtual), Italy. ⟨10.1016/j.ifacol.2021.08.355⟩. ⟨hal-03286034⟩