Multiple neural-network-based adaptive controller using orthonormal activation function neural networks

A direct adaptive control scheme is developed using orthonormal activation function-based neural networks (OAFNN's) for trajectory tracking control of a class of nonlinear systems. Multiple OAFNN's are employed in these contr ollers for feedforward compensation of unknown system dynamics, Choice of m ultiple OAFNN's allows a reduction in overall network size reducing the com putational requirements. The network weights are tuned on-line, in real tim e. The overall stability of the system and the neural networks is guarantee d using Lyapunov analysis. The developed neural controllers are evaluated e xperimentally and the experimental results are shown to support theoretical analysis. The effects of network parameters on system performance are expe rimentally evaluated and are presented in this research. The superior learn ing capability of OAFNN's is demonstrated through experimental results. The OAFNN's were able to model the true nature of the nonlinear system dynamic s characteristics for a rolling-sliding contact as well as for stiction.