Identification and control of class of non-linear systems with non-symmetric deadzone using recurrent neural networks

In this study, a neuro-controller with adaptive deadzone compensation for a class of unknown SISO non-linear systems in a Brunovsky form with uncertain deadzone input is presented. Based on a proper smooth parameterisation of the deadzone, the unknown dynamics is identified by using a continuous time recurrent neural network whose weights are adjusted on-line by stable differential learning laws. On the basis of this neural model so obtained, a feedback linearisation controller is developed in order to follow a bounded reference trajectory specified. By means of Lyapunov analysis, the boundedness of all the closed-loop signals as well as the weights and deadzone parameter estimations is rigorously proven. Besides, the exponential convergence of the actual tracking error to a bounded zone is guaranteed. The effectiveness of this scheme is illustrated by a numerical simulation.