一种新的智能优化及其改进研究

Novel Intelligent Optimization Algorithm and its Improvement

研究了一种新的进化算法-和声搜索(HS)算法,针对其在处理复杂函数优化问题时容易陷入局部最优、收敛精度低的缺点,提出一种改进的和声搜索算法,算法在保留和声搜索的搜索机理的同时,把混合蛙跳算法中的局部搜索策略引入其中,维持了和声库的多样性,从而提高了对复杂问题的搜索效率.与同类算法相比,本文提出的和声搜索算法全局搜索能力强,收敛速度快,数值实验结果验证了算法的有效性和鲁棒性.

A novel evolutionary algorithm,Harmony Search,is studied. it trapped into local optima easily and had a low convergence accuracy when it was used to address complex functions,in order to overcome the shortcomings,an improved HS algorithm is proposed.. With the main search mechanism of HS algorithm,the proposed algorithm integrates the strategy of local search in the Shuffled Frog Leaping Algorithm （SFLA） into HS algorithm and thus maintains the diversity of harmony memory,and enhances the efficiency of search for complex functions. Compared with HS and a recently developed variant of HS,the experiments show that the improved HS algorithm outperforms the two HS variations in all the functions. Also,numerical results demonstrate the effectiveness and robustness of the improved HS algorithm.