【作者】 陈俊风； 任子武； 范新南；

【Author】 Chen Junfeng, Ren Ziwu, Fan Xinnan College of Computer & Information Engineering, Hohai University, Changzhou 213022, China Control & Simulation Centre, Harbin Institute of Technology, Harbin 150001, China

【机构】 河海大学计算机及信息工程学院； 哈尔滨工业大学控制与仿真中心；

【摘要】 针对粒子群优化算法后期存在的收敛速度慢、早熟、易陷入局部极小等问题,提出了一种改进单纯形法与粒子群优化算法相结合的混合优化方法。该方法将带“扩张”和“伸缩”功能的改进单形法作为一个算子嵌入到粒子群优化算法中,利用改进单纯形搜索方法,对经过一次粒子群操作的部分精英粒子以阶段性概率调用改进单纯形法构造“单纯形”图形进行搜索寻优,引导粒子群体快速进化。仿真实验表明该方法不但显著提高了算法的全局搜索能力,而且也加快了收敛速度,提高了求解的质量和优化结果的可靠性,是求解优化问题的一种有效的算法。更多还原

【Abstract】 Aiming at the problem that the particle swarm optimization is difficult to deal with local convergence and premature problem, a hybrid computational algorithm based on an improved simplex method and particle swarm optimization has been presented in this paper. In the given hybrid algorithm the improved simplex method which has expansion function and contraction function is embedded in the particle swarm optimization as an operator. Using this improved simplex method with certain probability, simplex searching for the optimization is implemented to elitist particles that passed through the particle swarm optimization one time, which can induce the evolution of the swarm rapidly. The experimental results show that this new algorithm not only improves the global optimization performance, but also quickens the convergence speed and obtains robust results with good quality, which indicates this new algorithm is an effective approach for solving global optimization problems.更多还原