M. Chemachema
Adaptive non-linear control, neural networks, fuzzy systems, sliding mode control
Based on state feedback linearization technique, a direct adaptive neural network (NN) control is presented for a class of SISO non- linear systems. An additional sliding mode control (SMC) term is added to the basic NN adaptive controller to deal with approximation errors without persistent chattering phenomenon usually found in SMC control. Thus, contrary to the SMC approaches available in the literature, the implementation of the proposed control law doesn’t need any smoothening procedure. Furthermore, the updating signal used in the adaptation laws is an estimate of the control error instead of the tracking error. Lyapunov direct method is then used to prove the global boundedness of all the signals involved in the closed loop and the asymptotic convergence of the tracking error to zero. Simulation results demonstrate the effectiveness of the proposed approach.
Important Links:
Go Back
