Neural networks can be an attractive alternative to mathematical model
ling of complex and poorly understood processes if input/output data c
an easily be obtained. Woodchip refining falls into this category. The
mechanism of the refining process is still being studied and no thoro
ugh models have yet been developed. A feed-forward neural network is p
roposed for modelling of woodchip refiners. The outputs predicted by t
he neural network are compared with industrial refiner data. It is als
o shown that a modified neural network structure can be used to optimi
ze refiner operation and product quality. The advantages and disadvant
ages of neural network model application in simulation and optimizatio
n of industrial processes are discussed.