Dynamic Modeling Using Cascade-Correlation RBF Networks for Tilt Rotor Aircraft Platform

Cascade-correlation algorithm has usually been used for training feedforward multilayer networks with sigmoidal activation in the hidden units. Modeling using modified cascade-correlation radial basis function (CCRBF) networks for an experimental platform is presented. The behavior of the four degrees-of-freedom (DOF) platform exemplifies a high order nonlinear system with significant cross-coupling between longitudinal, latitudinal directional motions, and tilt rotor nacelles rolling movement. We develop a practical algorithm coupled with model validity tests for identifying nonlinear autoregressive moving average model with exogenous inputs (NARMAX). The effectiveness of this modeling procedure is demonstrated by a four DOF platform and experimental results show that the modified CCRBF networks for the platform are more appropriate than the conventional ones. It is proved that black-box modeling using CCRBF networks is more suitable for modeling novelty configuration air vehicles. The estimated model can be utilized for nonlinear flight simulation and control studies