长江科学院院报 ›› 2010, Vol. 27 ›› Issue (7): 31-35.

• 岩土工程 • 上一篇    下一篇

基于RBF神经网络的加筋粘土本构模型

石修松, 王路 君,程展林   

  1. 长江科学院 水利部岩土力学与工程重点实验室,武汉 4300
  • 出版日期:2010-07-01 发布日期:2010-07-01

A Constitutive Model of Reinforced Clay Based on RBF Neural Network

SHI Xiu-song, WANG Lu-jun, CHENG Zhan-lin   

  1. Key Laboratory of Geotechnical Mechanics and Engineering of The Ministry of Water Resources,  Yangtze River Scientific Research Institute, Wuhan 430010 , China
  • Published:2010-07-01 Online:2010-07-01

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。

关键词: 三轴试验 , 本构模型 , RBF神经网络 , 加筋粘土

Abstract: 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.

Key words: triaxial test, constitutive model , RBF neural network , reinforced clay

中图分类号: