Modelling aspects of grain drying with a neural network

This paper deals with a neural network (NN) application to an agricultural fixed-bed dryer. The aim of the study was to set-up a NN in order to determine the relationship between the moisture distribution of the material to be dried and the physical parameters of the drying air temperature, humidity and air flow rate. Input data was randomly changed, while output was generated by OʹCallaghanʹs model based on the input specifically for barley. A selected NN structure was used for studying the influence of sampling time, randomised training, different back-propagation training algorithms and the number of hidden neurones. It was concluded that the artificial NN could be effective for modelling of the grain drying process.