改进的双群人工鱼群算法
Improved Double Swarm Artificial Fish Swarming Algorithm

针对传统人工鱼群算法在后期收敛速度较慢以及难以跳出局部最优值找到全局最优值的问题，提出了一种改进的双群人工鱼群算法。该算法第一种群采用位置向量交换行为快速寻优，第二种群采用混乱行为产生的新的鱼群再次寻优，最终得到两次寻优的结果得到的交叉解。为了证明双群人工鱼群算法的有效性，在实验中在采用了10种经典的测试函数，并且与前人提出的改进方法包括规范鱼群算法(NFSA)、基于扩展记忆粒子群优化算法的人工鱼群(PSOEM_FSA)算法、综合改进人工鱼群(CIAFSA)等算法进行全方面综合对比。实验结果表明，双群人工鱼群算法较规范鱼群算法、基于扩展记忆粒子群优化算法的人工鱼群算法、综合改进人工鱼群算法在局部寻优以及全局寻优具有更精准更有效率的寻优结果。
Aiming at the problem that the traditional artificial fish school algorithm converges slowly in the later stage and it is difficult to jump out of the local optimal value to find the global optimal value, an improved dual-group artificial fish school algorithm is proposed. In this algorithm, the first group uses position vector exchange to quickly find the best, and the second fish group uses the new fish group generated by chaotic behavior to find the best again, and finally obtains the cross solu-tion obtained from the results of the two optimizations. In order to prove the effectiveness of the two-swarm artificial fish swarm algorithm, 10 classic test functions are used in the experiment, and the improved methods proposed by the predecessors include the normalized fish swarm algorithm (NFSA) and the particle swarm optimization algorithm based on extended memory. Artificial fish school (PSOEM_FSA) algorithm, comprehensive improved artificial fish school (CIAFSA) and other algorithms are comprehensively compared. The experimental results show that the dual- group ar-tificial fish school algorithm is more accurate and more efficient than the standard fish school algo-rithm, the artificial fish school algorithm based on the extended memory particle swarm optimiza-tion algorithm, and the comprehensive improvement of artificial fish swarm algorithm has more accurate and efficient optimization results in local optimization and global optimization.