基于RBF神经网络的加筋粘土本构模型  

A Constitutive Model of Reinforced Clay Based on RBF Neural Network

作　　者：石修松[1] 王路君[1] 程展林[1] 

机构地区：[1]长江科学院水利部岩土力学与工程重点实验室,武汉430010

出　　处：《长江科学院院报》2010年第7期31-35,共5页Journal of Changjiang River Scientific Research Institute

基　　金：国家自然科学基金;二滩水电开发有限公司雅砻江水电开发联合研究基金资助项目(50639050)

摘　　要：用室内三轴试验得到了加筋粘土的应力-应变关系,在此基础上建立了基于RBF神经网络的加筋粘土本构模型,利用此模型对加筋土在不同加筋层数情况下的本构模型进行仿真,并将其与试验值进行对比。结果表明,RBF神经网络能够很好地逼近加筋粘土的本构关系且具有较强的泛化能力,可以反映加筋层数和应力路径的影响。Indoor,triaxial tests were carried out to obtain the stress-strain relationship of reinforced clay.A RBF neural network constitutive model of reinforced clay was established based on test data.The authors used it to simulate the constitutive model of reinforced soil under different reinforced layers.Compared with the experimental value,the result shows that,the RBF neural network has a good approach to the constitutive relationship of reinforced clay and a strong generalization ability.It can reflect well the number of reinforced material layers and the stress path.

关 键 词：三轴试验 本构模型 RBF神经网络 加筋粘土 

分 类 号：TU411[建筑科学—岩土工程]