Simple adaptive control using neural networks with offset error reduction for an SISO magnetic levitation system

Abstract

This paper proposes the implementation of the method of SAC using neural networks with offset error reduction to control a single-input single-output (SISO) magnetic levitation system. In this paper, the control input for the SISO magnetic levitation system is given by the sum of the output of a simple adaptive controller and the output of neural networks. The role of neural networks is to compensate for constructing a linearised model so as to minimise the output error caused by non-linearities in the magnetic levitation system. The neural networks use the back-propagation algorithm for the learning process. The role of simple adaptive controller is to perform the model matching for the linear system with unknown structures to a given linear reference model. In this method, only part of the control input is fed to the parallel feedforward compensator (PFC). Thus, the error will be reduced using this method, and the output of the magnetic levitation system can follow significantly closely the output of th...