Abstract
In the course of drying process one of the main problems is to exactly determine the moisture content in the material bed. The measurement is an option, but its accuracy is not satisfactory. Another way to determine the moisture distribution is to use physically based or blackbox models. Physically based models give a moderately good result, but it normally takes a great effort to identify their parameters, and to solve the model itself. Derivation of the classical black-box models seems to be an uncomplicated approach. However, the application of such models is mainly limited mainly for process control. Therefore, this paper overviews the application opportunities of the use of artificial intelligence methods. Among those methods (neural network, Fuzzy modelling, genetic algorithm, etc) the main emphasize is given to the use of artificial neural network (ANN) modelling especially for grain drying as a widely applied dehydration technology. A methodology is given to the selection aspects of neural network structure and specifically to the main influencing model parameters as sampling time, randomised training, different training algorithms, number of hidden neurones, number of linked data series and type of validation data. Based on the recent study, it is concluded that the ANN can be used during effectively in case of post-harvest processes especially for estimation the temperature and moisture content distribution.