Neural network-based adaptive sliding mode control for uncertain non-linear MIMO systems

Abstract

The purpose of this paper is the design of neural network-based adaptive sliding mode controller (NASMC) for uncertain unknown MIMO non-linear systems. A special architecture adaptive neural network, with hyperbolic tangent activation functions, is used to emulate the equivalent and switching control terms of the classic sliding mode controller (SMC). The bounded motion of the system around the sliding surface and the stability of the global system, in the sense that all signals remain bounded, are guaranteed. Unlike other works, this is not a combination of neural networks and SMC approaches, but a new implementation of adaptive SMC using multiple neural networks approach, with special architecture. A two-link robot example and its simulation results are presented to illustrate the proposed approach.