The use of evolutionary algorithms to solve practical problems in polymer extrusion

Abstract

This work aims at selecting the operating conditions and designing screws that optimize the performance of single-screw and co-rotating twin-screw extruders, which are machines widely used by the polymer processing industry. A special MOEA, denoted as Reduced Pareto Set Genetic Algorithm, RPSGAe, is presented and used to solve these multiobjective combinatorial problems. Twin screw design is formulated as a Travelling Salesman Problem, TSP, given its discrete nature. Various case studies are analyzed and their validity is discussed, thus demonstrating the potential practical usefulness of this approach.