Offset-free combined neural network/switching control for nonlinear servomechanisms with DSP-based implementation

In this paper, we present a combined neural network/switching controller which is shown to provide offset-free regulation and control in the presence of disturbances. The controller is applicable to nonlinear servomechanisms of the type commonly encountered in motion control. In the paper, the properties of the controller are discussed and the implementation of the overall control system using a microcomputer host with a digital signal processor (DSP) accelerator is described. The paper also includes the results of real-time experiments in applying the proposed controller for position control of a nonlinear servomechanism which provides experimental verification of the effectiveness of the proposed method