Use of Artificial Neural Network Models for Prediction of Drying rates of Agricultural Products
Special Symposium - Innovations in Food Technology (LMC Congress)
Modern Analysis: Chemical & Multivariate Analysis (Food-6b)
Keywords: Drying,Neural Networks, Modeling,Dried Products
Drying is the oldest method of food preservation. Open-Air sun drying has been known from ancient times, but it is not suited for large scale production needed by modern communities. So Numerous industrial dryers have been used to produce dried products. The moisture content and drying rates of the drying materials are two of the most important factors for the design and operation of drying equipments. Drying rates are traditionally described by fitting experimental data versus time in form of several well known mathematical equations. But this method lacks the extensivity and reliability which is needed in industrial applications. On the other hand Artificial Neural Network Models have been successfully applied for property predictions in several different fields including drying rates. In this study the drying rates of several agricultural products (Tomato, Potato, Garlic, Pomegranate, Orange,Tangerine) have been determined by means of extensive experiments. The experimental results have been used as a basis for constructing of tradisional mathematical equations as well as Artificial Neural Network Models. The latter models have shown several advantages which are discussed in detail.
The Neural Network Architecture are also investigated and appropriate architectures have been discovered and recommended in each case. It is concluded that Artificial Neural Network Models can be used as a powerful tool in design and operation of drying processes and equipments.
Presented Thursday 20, 10:15 to 10:20, in session Modern Analysis: Chemical & Multivariate Analysis (Food-6b).
