遗传算法多极值函数优化及其在MUSIC算法中的应用

本文就遗传算法解决多极值函数优化问题的方法进行了分析总结，提出了一种基于多生境排挤机制的改进算法，并将其应用到ＭＵＳＩＣ谱的谱峰搜索过程中。实验证明，改进后的方法较原算法计算效率更高，能够在一次搜索过程中同时确定目标函数多个极值点的位置。对于ＭＵＳＩＣ谱谱峰搜索问题，计算量较等步长遍历搜索节省在两个数量级以上．

A Genetic Algorithm for Multimodal Function Optimization and Its Application in MUSIC Method

Many search and optimtzation problems require the investigation of multiple local optima. In this paper, genetic algorithms for there problems are reviewed and a modified mutil_niche crowding method is developed. We use the estimation of the arrival directions of spatial emitters as an example to test the ability of our new method. The objctive functions are the spectrums estimated by the MUSIC method. It is shown by simulation that the modified algorithm which is more effcient than the formerly one can find all the local optima of the objective functions and its computation consimption is at most one per cent of the conventional MUSIC meethod.