量子统计力学演化算法  

Quantum Statistical Mechanics Evolutionary Algorithm

作　　者：黄星焱[1] 刘淑芬[1] 危明[2] 卫楚一[1] 张加远[1] 陈亮[1] 裴升[1] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]武汉大学软件工程国家重点实验室,武汉430072

出　　处：《吉林大学学报（理学版）》2009年第4期759-764,共6页Journal of Jilin University:Science Edition

基　　金：国家科技攻关项目基金(批准号:2004BA907A20);吉林省科技发展计划重大项目基金(批准号:20060328)

摘　　要：将进化理论和量子统计力学理论相结合,提出一种新的量子统计力学演化算法.将整个遗传系统作为一个量子统计系统,并借鉴量子信息论中量子比特的叠加性,采用量子编码表征染色体,使系统中的量子能够表示多种线性叠加状态.算法类比量子统计力学中的相关概念,定义了量子系统的能量和熵,并利用量子系统中能量和熵竞争的模式系统地协调进化理论中选择压力和种群多样性间的冲突,使算法在提高选择压力和维持种群多样性之间保持了适当的平衡,可以快速的收敛到全局最优解.实验结果表明,该算法有较高的执行效率和求解能力.The authors presented a new evolutionary algorithm based on the combination of the evolutionary theory and quantum statistical mechanics. The whole evolutionary system is regarded as a quantum statistical system, where quantum coding is adopted to express chromosomes, and superposition of quantum bits is used to simulate the linear superposition state of the system. Quantum system entropy and statistical energy are defined by analogy with corresponding concepts in quantum statistical mechanics. And the competition between the quantum statistical energy and entropy of the system is used to simulate the conflict between selection pressure and diversity of population, which helps the algorithm to keep a delicate balance between these two issues, and obtain optimal solution rapidly. Numerical experiments show that this new algorithm has a high efficiency and strong ability to get global optimal solution.

关 键 词：量子系统 量子力学 遗传算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]