Application of neural network predictive control to a stepping motor

Abstract EN

Tn this paper, an application of the neural network predictive controller for stepping motor will be presented.

This approach has been considered in order to assure high control performance of the system.

The advantage of this type of control with respect to the classical P1D controller will be illustrated.

In the neural network predictive control approach the model of the system to be controlled is first determined in a system identification phase.

The system model is used to predict future behavior of the system, and an optimization algorithm is used to select the control input that optimizes future performance.