A COMPARISON OF MATHEMATICAL AND ARTIFICIAL NEURAL NETWORK MODELING FOR ROSA PETALS USING HOT AIR DRYING METHOD

Abstract

Damask rose (scientific name: Rosa damascene) belongs to the Rosaceae family and is valuable in medicine. In this study, the influence of air temperature and velocity are investigated on hot air dryer of the rose petals. Artificial drying of the agricultural products is one of the most common maintenance procedures. Suitable drying methods reduce the waste and damage during the storage and save the quality of the products. Optimization and control of the drying process is also based on the precise modeling. Here, moisture ratio was estimated at any temperature and air velocity by mathematical models. Later, artificial networks including feed-forward and recurrent network were applied to predict the moisture ratio via temperature, air velocity and time. The obtained results show that neural network is the best for modeling; nevertheless, the recurrent network has the best performance in predicting the moisture ratio.