ON-LINE ADAPTIVE NEURAL NETWORK IN VERY REMOTE CONTROL SYSTEM

Abstract

Remote control involves several issues that degrade seriously the performance of the plant to be controlled. This paper presents a strategy improving the characteristics of the remote control system, using an on-line adaptive neural net, in order to learn the variations of the remote system parameters to minimize the errors. This strategy is successfully applied to a client-server remote control system for a two link robot arm. Tests show that an error position in a remote control brushless motor can be highly reduced since its first "reference command" using a prevision of that error to modify the original reference. The neural net, used only by the client, is previously trained using local test data and then it is trained using on-line feedback data front the remote plant.