论文部分内容阅读
为了提高遗传算法的收敛速度及局部搜索能力,设计了一种基于优良模式的局部搜索算子.同时对传统免疫算法中基于浓度的选择算子进行了改进,设计了一种基于适应度值和浓度的混合选择算子,从而有效的阻止了算法出现“早熟”现象.进一步给出了算法的步骤,并利用有限马尔可夫链证明了该算法的收敛性,最后通过对四个经典测试算法性能的函数的数字仿真,说明该算法对多峰值函数优化问题明显优于基本遗传算法.
In order to improve the convergence speed and the local search ability of the genetic algorithm, a local search operator based on good mode is designed.At the same time, the density-based selection operator in the traditional immune algorithm is improved, and a fitness- Density mixed selection operator, which effectively prevented the algorithm from appearing “precocious ” phenomenon.Further gives the steps of the algorithm, and prove the convergence of the algorithm by using the finite Markov chain, and finally through the four classic The numerical simulation of the function of the test algorithm shows that the algorithm is obviously better than the basic genetic algorithm for multi-peak function optimization.