三轴加载条件下混凝土的神经网络本构模型  

TRIAXIALCONSTITUTIVE MODELOF CONCRETE USING NEURAL NETWORKS

作　　者：逯静洲[1,2] 林皋[3] 李庆斌[1] 

机构地区：[1]清华大学水利水电工程系 [2]大连理工大学土木工程系,辽宁大连116024 [3]大连理工大学土木工程系

出　　处：《工程力学》2004年第6期21-25,共5页Engineering Mechanics

基　　金：国家自然科学基金重点基金项目(50139010);中国博士后科学基金(2002)17 号

摘　　要：神经网络由大量并行处理单元构成,适合于描述多影响因素的非线性复杂因果规律,为研究材料本构特性提供了一条崭新的途径。利用 BP 网络的模拟能力来代替传统的方法,建立了一个三轴加载情况下混凝土的神经网络本构模型,用于描述混凝土在侧压力恒定轴向单调加载条件下的本构关系。从模型对训练和检验样本的模拟结果可以看出,这个经过训练的含有双隐层的神经网络本构模型具有很高的学习精度和良好的泛化能力,适合在结构工程问题中应用。Neural networks are composed of massive parallel processing units. They have unique learning capabilities, which can be used in learning complex nonlinear causal relations, and offering a fundamentally different approach in modeling of constitutive behavior of materials. An error-back-propagation (BP) neural network for triaxial constitutive model of concrete was developed, which is suitable to model axial monotonic loading under constant confining pressures. And a good agreement between the measured data and the predicted results demonstrates that the BP neural network model with two hidden layers is able to capture significant variability inherent in the concrete samples.

关 键 词：结构工程 本构模型 神经网络 混凝土 三轴 

分 类 号：TU375[建筑科学—结构工程]