Write your message
Volume 6, Issue 3 (10-2016)                   Disaster Prev. Manag. Know. 2016, 6(3): 284-294 | Back to browse issues page

XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Alidadi N, Mahdavian A. Modeling the amplification of seismic waves with artificial Neural network (Case Study: Urmia City). Disaster Prev. Manag. Know. 2016; 6 (3) :284-294
URL: http://dpmk.ir/article-1-88-en.html
1- Shahid Beheshti University,Faculty of Civil, Water and Enviromental Engineering
2- Shahid Beheshti University,Faculty of Civil, Water and Enviromental Engineering
Abstract:   (5730 Views)

Background and objective: Soil effects in seismic design codes is often based on soil type and average shear wave velocity in different layers. In some seismic design codes, some effects such as the effects of thickness and depth of the bedrock seismic structure are ignored. Past earthquakes experience has proved that thickness of soil layers has a significant impact on the earth response and is unavoidably. Since, Iran is located in the seismic belt areas of the world, and Urmia city is also located in a high seismic potential area of Iran, so in this research, the effect of amplifying seismic waves in marl and sandy soils with different thicknesses has been examined in this area.

Methodology: One dimensional analysis of sandy and marl with unequal thicknesses done by considering the place geotechnical characteristics. It is used from artificial accelerograms simulated based on seismic hazard analysis results as input motion of analysis in this analysis. This amplification ratio is modeled by neural network. Artificial neural network model is a new way to create a knowledge system based on collecting sample data.

Finding: Knowledge used in this model is a neural network to predict the seismic response that is mainly based on real data which can be utilized by using this model. In this paper, a model is designed using artificial neural network (ANN) to predict seismic magnification coefficients. The main advantage of this method is high performance in operation and high speed response of structures under Accelerograms be determined.

Conclusion:In this study, the results of artificial neural network using correlation coefficients and root mean square error criteria has been used to offer precise answer and the obtained results can be used in evaluating sand and marl soils in seismic in Urmia city.

Full-Text [PDF 937 kb]   (1680 Downloads)    
Type of Study: ترویجی | Subject: General
Received: 2016/06/1 | Accepted: 2016/08/3 | ePublished: 2016/09/26

Add your comments about this article : Your username or Email:
CAPTCHA

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2024 CC BY-NC 4.0 | Disaster Prevention and Management Knowledge (quarterly)

Designed & Developed by : Yektaweb