Proceedings of the 2nd International Symposium on Information Processing (ISIP 2009) Huangshan, China, August 2123, 2009 Editors: Fei Yu, Jian Shu, and Guangxue Yue AP Catalog Number: APPROCCS09CN002 ISBN: 9789525726022 (Print), 9789525726039 (CDROM) Page(s): 197200 

Estimating Model Parameters of Conditioned Soils by Using Artificial Network Shangguan Zichang, Li Shouju, Sun Wei, and Luan Maotian 
Full text: PDF 
Abstract 

The parameter identification of nonlinear constitutive model of soil mass is based on an inverse analysis procedure, which consists of minimizing the objective function representing the difference between the experimental data and the calculated data of the mechanical model. The illposeness of inverse problem is discussed. The classical gradientbased optimization algorithm for parameter identification is also investigated. Neural network models are developed for estimating model parameters of conditioned soils in EBP shield. The weights of neural network are trained by using the LevenbergMarquardt approximation which has a fast convergent ability. The parameter identification results illustrate that the proposed neural network has not only higher computing efficiency but also better identification accuracy. The results from the model are compared with simulated observations. The models are found to have good predictive ability and are expected to be very useful for estimating model parameters of conditioned soils in EBP shield. 

Index Terms 

parameter estimation, neural network, inverse problem, shield machine 

Copyright @ 2009 ACADEMY PUBLISHER — All rights reserved 