Neural network model for fluidised bed dryers

The application of an artificial neural network (ANN) to model a continuous fluidised bed dryer is explored. The ANN predicts the moisture and tempera ture of the output solid. A three-layer network with sigmoid transfer funct ion is used. The ANN learning is made by using a set of data that were obta ined by simulating the operation by a classical model of dryer. The number of hidden nodes, learning coefficient. size of learning data set and number of iterations in the learning of the ANN were optimised. The optimal ANN h as five input nodes and six hidden nodes. It is able to predict, with an er ror less than 10%. the moisture and temperature of the output dried solid i n a small pilot plant that can treat up to 5 kg/h of wet alpeorujo. This is a wet solid waste that is generated in the two-phase decanters used to obt ain olive oil.