Modeling moisture sorption isotherms of corn dried distillers grains with solubles (DDGS) using artificial neural network.

Moisture sorption isotherms of corn dried distillers grains with solubles (DDGS) were modeled using artificial neural networks (ANNs). Equilibrium moisture content (EMC) of DDGS, with varying chemical composition, was measured at 10°C, 20°C, 25°C, 30°C, and 40°C. Samples with different chemical composition were prepared by adjusting the condensed distillers solubles (CDS) and wet distillers grains (WDG) ratio during the production process in rotary drum dryers. Two different ANN models were tested, one with ERH and temperature only, and the other model with ERH, temperature, and five chemical components (protein, fiber, sugars, minerals, and glycerol), to predict the EMC. Prediction of EMC by ANN was improved by inclusion of chemical components, with low RMSE values. The R2 value was 0.99 for calibration and 0.98 for validation samples. Relative importance of chemical components in the sorption process of DDGS was also determined using ANN. Protein, fiber, sugars, minerals, and glycerol influenced the EMC of DDGS. The effect of protein was higher (35.26%), followed by fiber (26.12%). The results from this study underline the importance of knowledge of chemical composition to predict the sorption behavior of DDGS.