AN REP NEURAL-NETWORK-BASED ADAPTIVE-CONTROL FOR SISO LINEARIZABLE NONLINEAR-SYSTEMS

An RBF neural network-based adaptive control is proposed for Single-in put and Single-Output (SISO) linearisable nonlinear systems in this pa per. It is shown that a SISO nonlinear system is first linearised by u sing the differential geometric approach in the state space, and the l inearised nonlinear system is then treated as a partially known system . The known dynamics are used to design a nominal feedback controller to stabilise the nominal system, and an adaptive RBF neural network-ba sed compensator is then designed to compensate for the effects of unce rtain dynamics. The main function of the RBF neural network in this wo rk is to adaptively learn the upper bound of the system uncertainty, a nd the output of the neural network is then used to adaptively adjust the gain of the compensator so that the strong robustness with respect to unknown dynamics can be obtained and the tracking error between th e plant output and the desired reference signal can asymptotically con verge to zero. A simulation example is performed in support of the pro posed scheme.