Nonlinear modelling of a twin rotor MIMO system using radial basis function networks

Modelling of innovative aircraft such as UAVs, X-wing, tilt body and delta-wing is not easy. This paper presents a nonlinear system identification method for modelling air vehicles of complex configuration. This approach is demonstrated through a laboratory helicopter. Extensive time and frequency-domain model-validation tests are employed to instil confidence in the estimated model. The estimated model has a good predictive capability and can be utilized for nonlinear flight simulation studies. The approach presented is suitable for modelling new generation air vehicles.