Robust Adaptive Control for Complex Systems Employing ANN Emulation of Nonlinear Functions

Abstract

A new robust adaptive control design synthesis, which employs both high-order neural networks and math-analytical results, for a class of complex nonlinear mechatronic systems possessing similarity property has been derived. This approach makes an adequate use of the structural feature of composite similarity systems and neural networks to resolve the representation issue of uncertainty interconnections and subsystem gains by on-line updating the weights. This synthesis does guarantee the real stability in closed-loop but requires skills to obtain larger attraction domains. Mechatronic example of an axis-tray drive system, possessing uncertainties, is used to illustrate the proposed technique