Gaussian networks for control of a class of systems with friction

摘要

Identification and stable adaptive control of a class of systemswith friction is considered using Gaussian networks. Preliminary resultsare presented for a proposed strategy using an experimental systemconsisting of a DC motor and a load. The nonlinearity due to friction,which is significant at low velocities, is first identified using aGaussian network and then compensated for using the network in afeedforward mode. The Gaussian network is shown to have a `general'structure suited for friction problems. The network development takesadvantage of the constructive methodology for generating stable adaptivelaws for Gaussian networks proposed by Sanner and Slotine (1993)