Similarity matching selection of genetic algorithm
遗传算法的相似性配对方式

A new matching selection called similarity-matching selection of genetic algorithm was presented and the probabilities of the selection were calculated.An experimental calculation based on the proposed matching selection for a maximum problem was performed.The results show that such a matching selection guarantees the centralization and continuity of the excellent genes and can help to maintain the good gene constructions from the point of real world's view.Furthermore,from the point of calculation convergence view,the calculation using the new matching selection is not easy to diverge in the small area around the global maximum.Therefore,the speed of convergence can be accelerated.