The Detection of the Rotor Temperature in an Induction Machine Based on a Neural Network with Particle Filtering

Abstract

This paper introduces a method for estimating the temperature of the rotor of an Induction Machine (IM) based on a feed-forward neural network used as an observation function within a particle filter. The temperature of the stator case is measured and the information is used as an input to a feed-forward network. The state transition function is a thermal model with first-order dynamics. The set-point temperature is computed out of the rotor current, stator current and angular speed. Experimental data is used from a real IM test bench and the results prove the applicability and good performances.