Comparison between artificial neural networks and mathematical models for moisture ratio estimation in two varieties of green malt

Introduction Artificial neural network (ANN) is a technique with flexible mathematical structure, which is capable of identifying complex non-linear relationship between input and output data. Objectives The aim of this study was a comparison between ANNs and mathematical models for moisture ratio estimation in two varieties of green malt. Methods In this study, drying characteristics of two varieties green malt Sahra and Dasht were studied at different temperatures (40, 55, 70 and 85?C) by measuring the decrease in the mass of green malt with respect to time. A feed forward back propagation (FFBP) neural network was used to estimate the moisture ratio of green malt during drying. ANN was used to model green malt drying at different temperatures and a comparison was also made with the results obtained from Page's model. The variety, drying temperature and time were used as input parameters and the moisture ratio was used as output parameter. Results The results were compared with experimental data and it was found that the estimated moisture ratio by FFBP neural network is more accurate than Page's model. It was also found that moisture ratio decreased with increasing of drying time and temperature. Conclusion The ANN model was more suitable than other models for moisture ratio estimation in green malt.