Abstract
This paper investigates the potential application of artificial neural networks in permanent deformation parameter identification for rockfill dams. Two kinds of neural network models, multilayer feedforward network (BP) and radial basis function (RBF) networks, are adopted to identify the parameters of seismic permanent deformation for Zipingpu Dam in China. The dynamic analysis is carried out by three‐dimensional finite element method, and earthquake‐induced permanent deformation is calculated by an equivalent nodal force method. Based on the sensitivity analysis of permanent deformation parameters, an objective function for network training is established by considering parameter sensitivity, which can improve the accuracy of parameter identification. By comparison, it is found that RBF outperforms the BP network in this problem. The proposed inverse analysis model for earth‐rockfill dams can identify the seismic deformation parameters with just a small amount of sample designs, and much calculation time can be saved by this method.
Highlights
The dynamic response of rockfill dams under earthquake actions, mainly including absolution acceleration and permanent deformation, attracts more and more attention from engineers
The aim of this paper is to present an inverse analysis model for seismic permanent deformation parameters of earth-rockfill dams based on artificial neural networks
For a large-scale multiple parameter and nonlinear problem such as backanalysis of displacement of an earth-rockfill dam, the workload is so daunting that sometimes the backanalysis cannot be carried out
Summary
The dynamic response of rockfill dams under earthquake actions, mainly including absolution acceleration and permanent deformation, attracts more and more attention from engineers. The former is used to assess the dynamical load and seismic resistance of the dam. The latter is adopted to provide a basis for the dam height reserved during the design phase. The prediction of permanent deformation is an essential problem in the seismic design for rockfill dams. It is important to select model parameters of rockfill dams reasonably, which makes for improving the accuracy of the numerical calculation. Because of the difference of construction technology and construction quality and so on, the spatial distribution of material properties
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have