Controlling air temperature variations inside refrigeration cabines based on artificial neural network experiments

Abstract

One problem associated with the loss-efficiency in refrigerators/freezers is the air infiltration. Therefore, knowledge of the air temperature field inside of these units is limited and large air temperature gradients often exist that can put the stored products at risk. This work studies temperatures in a commercial household refrigerator that were monitored with thermocouples located at several points. The measured temperatures were then used to build an Artificial Neural Network with supervised learning performed using a Genetic Algorithm. The aim is to obtain knowledge of the air temperature fields inside the refrigerated unit detecting in this way the anomalous variations due to inefficient isolation parts.