NEURAL-NETWORK-BASED APPROACH FOR OPTIMIZATION APPLIED TO AN INDUSTRIAL NYLON-6,6 POLYMERIZATION PROCESS

The basic idea of the proposed optimisation method is to replace the m odel equations by an equivalent neural network (NN) that mimics the ph enomenological model, and use-this NN to carry out a grid search, mapp ing all the region of interest. The proposed optimisation approach was applied to the industrial process of nylon-6,6 polymerisation in a tw in-screw extruder reactor. This corresponds to the finishing stage of an industrial polymerisation plant. A qualitative optimisation procedu re is used taking in account safe operation conditions, wear and tear of the equipment, product quality and energy consumption. The chosen o perational variables are then checked with the phenomenological model. This approach provides more comprehensive information for the enginee r's analysis than the conventional non-linear programming procedure. ( C) 1998 Published by Elsevier Science Ltd. All rights reserved.