一种求解约束优化问题的改进粒子群算法及其应用.pdfVIP

中国工程热物理学会 热机气动热力学 学术会议论文 编号：082083 一种求解约束优化问题的改进粒子群 算法及其应用 1 1 2 廖猜猜 席光 徐建中 (1.西安交通大学能源与动力工程学院,西安 710049；2.中科院工程热物理研究所,北京 100080） （TelEmail：xiguang@mail.xjtu.edu.cn ） 摘要：针对复杂约束优化问题, 提出一种改进的粒子群方法。该粒子群算法对于不满足约束条件的粒子 实行全概率接收，但令其目标函数值同为一个很小的常数，以保持粒子的多样性并使最优解在可行域 内。另外，在PSO 算法的基础上，使惯性权值按对数规律单调递减，同时引进选择遗传算子，以增强 其全局寻优性能。数值实验表明：与 PSO 算法和一些其它优化算法相比，改进算法具有较强的寻优能 力和寻优效率。工程应用表明，改进算法具有一定的优越性。 关键词：约束优化问题；粒子群算法；选择遗传；惯性权值；寻优能力 An Improved PSO Algorithm for Solution of Constraint Optimization Problem and Its Application Liao Cai-Cai 1 Xi Guang1 Xu Jian-Zhong2 (1.School of Energy Power Engineering, Xi’an Jiaotong University, Xi’an 710049, China; 2. Institute of Engineering Thermophysics, Chinese Academy of Sciences, Beijing 100080, China) Abstract : An improved particle swarm optimization (PSO) algorithm was developed to solve the complicated constrained optimization problems. This algorithm accepted all the particles which don’t satisfy the constrained conditions and made their objective function values be a very small constant to keep the diversity of the particles, and help the optimum solution to be in feasible region. In addition, based on PSO algorithm, the inertial weight was reduced by the logarithm regular. At the same time, the selected genetic operator is used to improve the optimization capability of PSO algorithm. Several numerical experiments indicate that the improved PSO algorithm has better optimization capability and efficiency than the PSO algorithm and some other optimization algorithms. Applied in engineering practice indicates that the improved algorithm