基于自适应遗传算法的渗流参数辨识研究  

Study on seepage coefficient identification based on adaptive genetic algorithms

作　　者：邓祥辉[1,2] 

机构地区：[1]西安理工大学水利水电学院,陕西西安710048 [2]西安工业大学建工系,陕西西安710032

出　　处：《西北农林科技大学学报（自然科学版）》2009年第10期221-224,共4页Journal of Northwest A&F University(Natural Science Edition)

基　　金：国家自然科学基金项目(50579092);二滩水电开发有限责任公司雅砻江水电开发联合研究基金项目

摘　　要：【目的】针对简单遗传算法难以确定交叉率和变异率的最佳值、计算量较大及易早熟等缺点,提出以自适应遗传算法来进行渗流参数辨识,为获得工程所需的计算参数提供参考。【方法】利用水头实测资料,以渗透系数为待辨识参数,在采用简单遗传算法进行参数辨识研究的基础上,力求使改进的遗传算法计算量更小,收敛性更强,同时结合三维稳定渗流有限元工程实例进行了反演计算。【结果】自适应遗传算法在保持简单遗传算法优点的同时,有效地提高了算法的收敛性,并在一定程度上克服了简单遗传算法的早熟问题。【结论】自适应遗传算法为渗流领域的参数辨识提供了新的途径。[Objective] Aimed at overcoming the limitation of simple genetic algorithm, the seepage coefficients needed by real engineering was studied. [Method] The real water head was used to overcome the problems such as high computational cost,the optimization probability of crossover and mutation determinated difficultly,premature convergent et al. Adaptive genetic algorithm was used to analyze the parameter of the three dimension real examples. [Result] The improved method was effective in improving the computational convergence and overcoming the premature of simple genetic algorithm partly. [Conclusion] Adaptive genetic algorithm is efficient and feasible in back analysis for seepage coefficient of arch dam.

关 键 词：渗透系数 参数辨识 自适应遗传算法 

分 类 号：TU457[建筑科学—岩土工程] O357.3[建筑科学—土工工程]