一种求解高维复杂函数优化问题的混合粒子群优化算法.pdfVIP

33 1 Vol.33, o. 1 2004 2 Information and Control Feb. , 2004 : 1002-0411(2004) 01-0027-04 李炳宇, 萧蕴诗, 汪 镭 ( , 200092) :,, . , , . : , . X : ;; : TP13 : B A Hybrid Particle Swarm Optimization Algorithm for Solving Complex Functions with High Dimensions LI Bing-yu, XIAO Yun-shi, WA G Lei ( School of Electronic and I nf or mation Engineer ing, Tongj i University, Shanghai 200092, China) Abstract For complex functions with high dimensions, canonical optimization methods are easy to be trapped in local minima and simple random search methods are slow on convergence. This paper proposes an effective hybrid optimization which combines particle swarm optimization with simple method, and it adopts quick and broad search- ing of the former, and quick convergence of the latter simultaneously. Simulation results on benchmark complex functions with high dimensions show that the hybrid algorithm is effective, efficient and fairly robust to initial cond-i tions. The performance of the hybrid algorithm excels those of single optimization methods. Keywords particle swarm optimization algorithm; simplex method; swarm intelligence 1 ( Introduction) . PSO , , , . , , , ,. , , ,. , . , , . , 2 PSO ( Theory of PSO algo- . rithm) 90,Eberhart Kennedy [1,2\ ) ) ) 2. 1 (Particle