基于遗传编程的可持续模拟退火算法及应用  

Studies and Applications on Sustainable Simulated Annealing Algorithm Based on Genetic Programming (GP-HFCSA)

作　　者：李少波[1] 徐立章[1] 胡建军 

机构地区：[1]贵州大学教育部现代制造技术重点实验室,贵阳550003 [2]美国南卡罗莱纳州大学计算机科学与工程系,哥伦比亚SC29208

出　　处：《系统仿真学报》2009年第7期1908-1911,共4页Journal of System Simulation

基　　金：国家自然科学基金(50575047);“西部之光”人才培养计划(科发人教字〔2005〕404号);贵州省优秀人才省长专项资金资助项目

摘　　要：研究分析了模拟退火算法(SA)的缺陷,采用分等级搜索机制,提出了可持续模拟退火算法(HFCSA)后,针对HFCSA算法编码受限问题,引入遗传编程的思想和编码方式,提出一种基于遗传编程的可持续模拟退火算法—GP-HFCSA算法。该算法可以在开放式搜索空间中搜索,实现结构和参数的协同进化。在算法对比测试实验(8特征值问题)中,GP-HFCSA算法的设计结果优于参照算法,证明了GP-HFCSA算法具有良好的效率及自动设计能力,具有广泛的学术价值及应用前景。In view of the sustainable insufficiencies of simulated annealing algorithm, adopting hierarchical fair competition model and genetic programming coding, a new sustainable simulated annealing algorithm （GP-HFCSA） for open-ended search design was investigated. This algorithm can search in an open-ended space and evolve structure and parameter in the same time. Combining with bond graph, GP-HFCSA can automatically design the multi-field dynamic system which is from an embryo system to an aimed one. So this supplies a new way of auto design in multi-field dynamic system. In the experiment-8-eigenvalue placement problem, GP-HFCSA algorithm shows strong automatic design ability and outperforms the compared algorithm in design result. So, it＇s proved that GP-HFCSA algorithm has good ability of auto design and will be applied in broad fields in future.

关 键 词：可持续模拟退火算法 HFC模型 GP-HFCSA算法 遗传编程 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP273[自动化与计算机技术—控制科学与工程]