A Fast Multi-Objective Evolutionary Algorithm applied to Industrial Problems
Geoffrey Basil Leyland, Daniel Favrat, Adam Molyneaux · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2002
The CEPA, an Evolutionary Algorithm that preserves diversity by finding clusters in the population, has had its convergence performance improved by a technique tentatively called ‘evolutionary operator selection’. Performance is compared to results found in the literature, though at the moment it is not entirely clear how the evolutionary operator selection mechanisms work. The resulting algorithm has been applied to a number of problems - including a hybrid vehicle configuration and coke production in Shanxi Province, China.