基于遗传模拟退火算法的岩土弹-粘塑性参数反分析  

Back analysis of elastic-viscoplastic parameters of geomaterials based on genetic simulated annealing algorithm

作　　者：黄耀英[1] 郭兴文[1] 吴中如[1] 

机构地区：[1]河海大学水利水电工程学院,江苏南京210098

出　　处：《水利水运工程学报》2006年第4期10-14,共5页Hydro-Science and Engineering

基　　金：国家重点基础研究发展规划(973)资助项目(2002CB412707)

摘　　要：根据常荷载作用下当所有应变率为零时,弹-粘塑性问题可得到弹塑性解的特性,建立了岩土弹-粘塑性参数反分析模型.提出了反分析弹-粘塑性问题参数的两步法,即先利用岩土材料应力屈服函数的统一表达式确定屈服函数的系数;再利用P.Perzyna本构方程中的常用Φ函数表达式来确定岩土材料的流动系数γ和常数N.在反分析中,应用遗传算法对参数空间进行全局搜索,并借助模拟退火算法对部分最优个体进行局部搜索.通过典型的厚壁圆筒算例分析表明,这一方法是可行的.The back analysis model of elastic-viscoplastic parameters for geomaterials is developed based on the characteristic that the elastic plastic solution can be obtained for the elastic-viscoplastic problem when all strain rates are equal to zero under constant load. The two-step method which can be used to back-analyze elasticviscoplastic parameters is provided in this paper： first, to determine the yield function＇s coefficients by using the uniform expression of stress yield function for geomaterials, and then, to determine the yielding coefficient y and constant N of geomaterials by using the common Ф function of P. Perzyna constitutive model. Genetic algorithm＇s whole search for all parameters and annealing algorithm＇s local search for some optimum individuals are used during back analysis. Results of one typical thick cylinder example show this method is feasible.

关 键 词：弹-粘塑性参数 遗传模拟退火算法 岩土材料 参数反分析 

分 类 号：TU452[建筑科学—岩土工程]