1个单纯形搜索法和免疫进化的微粒群算法的混合算法

A Hybrid Simplex Search and Particle Swarm Optimization Algorithm with Immune Evolutionary

基于单纯形搜索法和免疫进化微粒群算法,提出1个求解无约束最优化问题的新的混合算法—单纯形搜索法和免疫进化微粒群算法的混合算法.由于它不需要梯度信息,所以具有易实施、收敛速度快和计算准确的优点.为了证明混合算法能够改进免疫进化微粒群算法的性能,首先利用6个测试函数进行仿真计算比较,计算结果表明,新的混合算法在求解质量和收敛速率上都优于其它进化算法(IEPSO,PSOPC,GSPSO,LSPSO and CPSO);其次,将新混合算法和最新的3种混合算法进行鲁棒性分析比较,结果表明,新混合算法在解的搜索质量、效率和关于初始点的鲁棒性方面都优于其它算法.

The hybrid NM-IEPSO algorithm is proposed based on the Nelder-mead （NM）simplex search method and particle swarm optimization algorithm with immune evolutionary （IEPSO）for unstrained optimization. NM-IEPSO is very easy to implement in practice since it does not require gradient computation, and intends to produce faster and more accurate convergence. The main propose is to demonstrate how the IEPSO can be improved by incorporating a hybridization strategy. In a suit of 6 test function problems taken from the literature, computational results, show that the hybrid NM-IEPSO approach outperforms five relevant search techniques （i. e. , IEPSO, PSOPC, GSPSO, LSPSO and CPSO） in terms of solution quality and convergence rate. In a later part of the comparative experiment, the NM-IEPSO algorithm is compared to three hybrid algorithms procedures appearing in the literature. The comparison report still largely favors the NM-IEPSO algorithm in the performance of accuracy, robustness and function evaluation. As evi- denced by the overall assessment based on two kinds of computational experience, the new algorithm has demonstrated to be extremely effective and efficient at locating best-practice optimal solutions for unstrained optimization.