基于自适应信息遗传算法的路面模量反算研究  

Adaptive Informational Genetic Algorithm Based Back-calculation of Pavement Modulus

作　　者：李跃军[1,2] 李亮[1] 吴亚中 

机构地区：[1]中南大学土木建筑工程学院,湖南长沙410007 [2]湖南省交通科学研究院,湖南长沙410015 [3]湖南省交通厅,湖南长沙410011

出　　处：《公路交通科技》2011年第7期47-55,共9页Journal of Highway and Transportation Research and Development

基　　金：湖南省科技厅重点项目(05FJ4031)

摘　　要：针对在模量反算中,目标函数在最优值附近表现为大片狭长平坦区域的特点,提出了一类反算新算法——自适应信息遗传算法,新算法的优点是根据信息量大小来进行自适应细分模量解空间,从而节约大量的计算时间。改进了实数交叉算子,使用了新的探险策略,从而加强了新算法后期的局部搜索能力。随后的工程实例表明,这种新机制、新策略的引入,能够在保持较高反算精度的前提条件下,大大提高模量反算的求解效率,这意味着新算法能够更好地满足工程实际应用需要。Due to the existence of a long flat region around the optimum value in objective function for back-calculation of pavement modulus,a new back calculating algorithm,i.e.,adaptive informational genetic algorithm,was proposed.One advantage of the new algorithm is that it can adaptively subdivide the searching moduli space according to the level of information to save a great amount of computing time.A new detective strategy and a modified real-coded crossover operator were used to improve the local search ability of the new algorithm in later stage.The succedent engineering examples illustrate that the introduced new mechanism and strategy can help the new algorithm to greatly improve the back-calculation efficiency for higher precision of results.This means that the new algorithm can better meet the requirements for further engineering application.

关 键 词：道路工程 路面模量反算 自适应信息遗传算法 落锤式弯沉仪(FWD) 实数交叉算子 

分 类 号：U416.23[交通运输工程—道路与铁道工程]