Use of a recurrent neural network in discrete sliding-mode control

The paper discusses a class of nonlinear discrete sliding-mode control. The control system is designed on the basis of a discrete Lyapunov function. P art of the equivalent control is estimated by an on-line estimator, which i s realised by a recurrent neural network (RNN) because of its outstanding a bility for modelling a dynamical process. A real-time iterative learning al gorithm is developed and used to train the RNN. Unlike the conventional lea rning algorithms for RNNs, the proposed algorithm ensures that the learning error converges to zero. As a result, the stability of the control system is always assured. In addition, this learning algorithm can be applied for on-line estimation. The proposed controller eliminates chattering and provi des sliding-mode motion on the selected manifolds in the state space. Numer ical examples are given and simulation results strongly demonstrate that th e control scheme is very effective.