Online aerodynamic parameter estimation of a miniature unmanned helicopter using radial basis function neural networks

This paper focuses on the online aerodynamic parameter estimation of a miniature helicopter using Radial Basis Functions (RBF) Neural Networks (NN). A simulation model of the miniature helicopter was developed within MAT-LAB/SIMULINK environment. Three flight conditions were analyzed: hover flight, forward flights at 10m/s and 20m/s respectively. The Delta Method (DM) and the Modified Delta Method (MDM) combined with a moving window algorithm were used to estimate the aerodynamic parameters. The online parameter estimation of the helicopter longitudinal and lateral dynamics produced satisfactory results although the presence of atmospheric turbulence and sensor noise had an adverse effect on number of high confidence values.