Neuronal Approach and the Use of KIK-NET N Response Spectrum on the Surfaceetwork to Generate
Journal: Jordan Journal of Civil Engineering (JJCE) (Vol.4, No. 1)Publication Date: 2010-01-01
Authors : Boumédiène Derras; Abdelmalek Bekkouche; Djawad Zendagui;
Page : 12-21
Keywords : Site effect; Artificial neural networks; Acceleration response spectrum; Seismic data; Soil dynamics;
Abstract
The determination of response spectrum of a seismic excitation recorded on a chosen site is necessary in the structural dynamic design. The response spectrum can be obtained directly from recorded seismic data but this operation is expensive. The aim of this work is to avoid this problem where the acceleration response spectrum at the free face of a classified site is generated from that of reference by using the method of Artificial Neural Networks (ANN). The recorded spectrum value and corresponding period represent the inputs of the RNA, while the output is only the spectrum response value on the free field. The seismic data and the sites of the KIK-NET accelerograph network are used for the training and the validation of the neuronal model. The promising results obtained by this approach open a new research orientation on the use of the ANN in the field of soil dynamics and signal treatment, thus allowing the enrichment of the
paraseismic codes into force.
Other Latest Articles
- Study of Flow and Energy Dissipation in Stepped Spillways
- Evaluation of Transportation Demand Management (TDM) Strategies and Its Prospect in Saudi Arabia
- Comparative Study of Load Carrying Capacity of Steel Tube Columns Filled with Lightweight Concrete and Normal Concrete
- Influence of High Temperatures on Surface Cracking of Concrete Studied by Image Scanning Technique
- Role of the Geologic Structures on the Aquifers Vulnerability in Arid Areas: Case Study from Swaqa - Ghabawi / Jordan
Last modified: 2014-10-11 19:34:35