Intelligent Control of Mechatronic Systems

Abstract

This thesis considers the theoretical aspects of adaptive neural network (NN) control and its applications. NNs can approximate, to an arbitrary degree of accuracy, any real continuous function on a compact set, by exploiting the approximation capabilities of the NNs, a NN based control can be developed where NNs are used to compensate for the functional and parametric uncertainties in the system model. In this thesis, an Adaptive Variable Structure Control (AVSC) is proposed, based on NN parametrization, for a class of uncertain nonlinear pure-feedback single-input single-output (SISO) systems. Subsequently, the application of intelligent control is studied, where the focus is on the control of marine shafting systems. A case study on the application of intelligent control in marine shafting systems modeled as a chained multiple mass-spring system is presented.