遗传算法的参数设计与性能研究

Study on parameter designing and performance for genetic algorithm

利用无符号整数数组代替传统的字符串进行二进制编码,用改进的适应度函数、自适应交叉率、自适应变异率取代传统的适应度数和固定的交叉率及变异率来改进遗传算法,并与基本遗传算法进行了实验比较,结果证明改进的遗传算法显著提高了收敛性能,并且具有很强的自适应能力。

A new genetic algorithm (IGA) is improved by using unsigned integer matrix instead of traditional string for binary coding. It also presents a new fitness function, an adaptive crossover probability and an adaptive mutation probability. Through the comparison between IGA and GA experiments show that IGA has significantly improved the convergent performance and has a strong self-adjusting ability.