Performance analysis of 4 types of conjugate gradient algorithms in the nonlinear dynamic modelling of a TRMS using feedforward neural networks

Nowadays aircrafts are expected to perform varied and complex tasks which have presented unprecedented control challenges to the aero dynamicists and control engineers. This implies that linear characterization of aircrafts is not well enough to describe the systems characteristics for control purposes and nonlinear modelling techniques are required. Neural network based nonlinear characterization look promising in this regard. This paper investigates into the development of nonlinear modelling paradigms for modern air vehicles with application to a twin rotor multi-input-multi-output system (TRMS). The system is modelled using a nonlinear autoregressive process with external input (NARX) paradigm with a feedforward neural network. Four different types of conjugate gradient algorithms (CGAs) are used in this investigation for supervised learning of the network and their performances are compared in terms of input-output mapping and speed of convergence.