Parameters inversion of fluid-saturated porous media based on neural networks |
| |
Authors: | Wei Peijun Zhang Zimao and Han Hua |
| |
Institution: | (1) Institute of Mechanics, Northern Jiaotong University, 100044 Beijing, China;(2) LNM, Institute of Mechanics, Chinese Academy of Sciences, 100080 Beijing, China |
| |
Abstract: | The multi-layers feedforward neural network is used for inversion of material constants of fluid-saturated porous media. The
direct analysis of fluid-saturated porous media is carried out with the boundary element method. The dynamic displacement
responses obtained from direct analysis for prescribed material parameters constitute the sample sets training neural network.
By virtue of the effective L-M training algorithm and the Tikhonov regularization method as well as the GCV method for an
appropriate selection of regularization parameter, the inverse mapping from dynamic displacement responses to material constants
is performed. Numerical examples demonstrate the validity of the neural network method.
Project supported by the National Natural Science Foundation of China (Nos. 19872002 and 10272003) and Climbing Foundation
of Northern Jiaotong University. |
| |
Keywords: | fluid-saturated porous media parameter inversion neural networks boundary elements |
本文献已被 SpringerLink 等数据库收录! |