Evaluation of the transition matrix for comminuting pea seeds in an impactmill using a linear neural network

In the food industry, many industrial processes involve the grinding of veg etable products such as grains and seeds. The ability to be conveniently gr ound is an element of the quality of such products. We attempted to describ e the grinding of pea seeds, taken as an example, as a discrete time Markov ian process. The pea samples were passed several times through a laboratory grinder from which the screen was removed. After each series of passages, the particle site distribution of the ground products was assessed by sievi ng. The transition matrix of the Markovian process was estimated from these particle size distributions by using an original method based on a linear neural network. (C) 1999 Elsevier Science S.A. All rights reserved.