Neural Network Tuning of FSMPC for Drives

TL;DR

This paper introduces a neural network-based tuner for finite state model predictive control of induction motors, optimizing controller parameters through experimental data to improve drive performance.

Contribution

It presents a novel neural network tuner specifically designed for FSMPC in induction motor drives, validated with experimental data.

Findings

Neural network tuner effectively optimizes controller parameters.

Improved control performance demonstrated on a five-phase machine.

Experimental validation confirms the approach's viability.

Abstract

This preprint presents a neural network tuner for the finite state model predictive control of an induction motor. The tuner deals with the parameters of the controllers in the speed loop and in the stator current loop. The results are assessed using a five phase machine in an experimental setup. Data for the neural network training is obtained from the experiments using step tests.