基于改进GA-PSO的可重构测试资源匹配方法  

Reconfigurable Test Resource Matching Method Based on Improved Genetic-Particle Swarm Optimization Algorithm

作　　者：朱海振[1] 肖明清[1] 祁业兴 李超[1] ZHU Hai-zhen;XIAO Ming-qing;QI Ye-xing;LI Chao(Aeronautics and Astronautics Engineering College,Air Force Engineering University,Xi＇an 710038,China;Unit 93185 of the PLA,Anshan 114001,China)

机构地区：[1]空军工程大学航空航天工程学院 [2]中国人民解放军93185部队

出　　处：《测控技术》2018年第6期24-28,共5页Measurement & Control Technology

摘　　要：为提高测点信号与可重构测试资源匹配效率,建立了基于STD标准的测点信号与可重构测试资源的数学描述模型。针对可重构测试资源的特点,结合工程实际提出了基于Sigmoid函数的匹配函数,以资源可靠性、配置文件大小及配置时间因子作为罚函数,利用匹配函数构造出遗传算法的适应度函数。为解决遗传算法搜索速度较慢的问题,改进了遗传算法的选择算子和交叉算子,将粒子群算法应用到遗传算法中,解决了遗传算法在算法后期迭代效率低下的问题,最后通过实例验证了算法的有效性。In order to improve the matching efficiency between test point signal and reconfigurable test resource, a mathematical description model based on STD standard for test point signal and reconfigurable test resource is established. According to the characteristics of reconfigurable test resources, a matching function based on Sigmoid function was proposed in combination with engineering practice. Additionally, the fitness function of the genetic algorithm was constructed by using the matching function, taking the reliability of the resource, the size of the configuration file and the time factor as penalty function. The selection operator and crossover operator of genetic algorithm were improved to tackle the problem of slow search speed of genetic algorithm, the particle swarm algorithm is applied to the genetic algorithm, which solves the problem of the low iterative efficiency of genetic algorithm in the late algorithm. Finally, the validity of the algorithm is verified by an example.

关 键 词：可重构 测试资源 信号模型 匹配函数 遗传-粒子群算法 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置] V248[自动化与计算机技术—控制科学与工程]