MODELING OF CONVECTIVE LAYER DRYERS - USI NG NEURAL NETWORKS

Dryer modelling is considered in this paper. A dryer scale approach is implemented in order to write the classical differential equations th rough parameters such as the heat transfer coefficient or drying kinet ics. The behaviour of the dryers is described by a non-linear system w hich integrates these equations in a transfer network using the finite difference method. The finite difference method is easy to implement, but appears to be too slow for dryer designing. So, in the second par t of the study, neural networks are used to model drying process in st eady state. When applying neural networks method to the design of drye rs, one of the main problems is to find necessary and sufficient input s so that the neural networks can learn transfers laws. To reduce the problem, each output is defined by a single neural network and non-dim ensional numbers are used. The following step deals with the determina tion of the number of neurones and the minimization of output error fo r each efficiency (change of training points). Then, neural networks a re used to simulate different configurations of dryers. Results are co mpared with the finite difference method and an industrial application is studied in the last chapter.