Dynamic Models for Drying and Wet-Milling Quality Degradation of Corn Using Neural Networks

Non-linear dynamic models of corn drying and wet-milling quality degradation are obtaineddirectly from experimental data. No assumptions about the underlying mechanisms are made. Relative advantages of recurrent versus explicit-time models and technical issues are discussed. This type of model is well suited for very fast on-line simulations, for example in a predictive optimal control algorithm.