Prediction of quality indices during drying of apples using artificial neural networks models for process optimization

K. DI SCALA; G. MESCHINO; A. VEGA-GÁLVEZ; J. VERGARA; S. ROURA; R.H. MASCHERONI

Valencia

Conferencia; International Conference on Food Innovation FOODINNOVA 2010; 2010

UPV

The increasing demand for high-quality dried fruits requires the simulation and further optimization of the drying conditions to minimize physico-chemical, nutritional and organoleptical changes that occur during processing (Di Scala & Crapiste, 2008). The ability of Artificial Neural networks (ANN) to model non linear complex systems such as drying is increasing (Jindal & Chauhan, 2001). The multi-layer perceptron (MLP) is one of the types of ANN most applied in food engineering problems (Hernández-Pérez et al., 2004; Movagharnejad & Nikzad, 2007). Recently, genetic algorithms (GAs) are successfully applied for optimization problems (Shopova & Vaklieva-Bancheva, 2006). The aim of this work was to develop an artificial neural network to estimate quality indices of apples during drying and to find out the optimal process conditions that minimize product quality loss.