PROJECT TITLE :

A Robust Adaptive RBFNN Augmenting Backstepping Control Approach for a Model-Scaled Helicopter

ABSTRACT:

This temporary investigates the trajectory tracking downside for a model-scaled helicopter with a novel sturdy adaptive radial basis function neural network (RBFNN) augmenting backstepping management approach. The helicopter model is initial decomposed into an approximate strict-feedback format with some unmodeled dynamics. Backstepping technique is employed as the most management framework, which is augmented by sturdy RBFNNs to approximate the unmodeled dynamics. Every robust RBFNN utilizes an n th-order swish switching function to combine a conventional RBFNN with a robust management. The standard RBFNN dominates within the neural active region, whereas the robust control retrieves the transient outside the active region, thus that the stability range will be widened. As well, command filters are utilized to approximate derivatives of the virtual controls within the backstepping procedure. This systematic design methodology is proven to realize ultimate boundedness of the closed-loop helicopter system. Simulations validate the effectiveness of the proposed management approach.