RESM

    

Submission & tracking

For submitting new manuscripts or tracking the existing ones, login or register to the Submission Tracking System.


LOGIN / REGISTER

Upcoming events

PARTNERS




Special issue

Special Issue Proposals:

The journal of RESM is open to proposals for special issues on emerging related topics. More info is here.

Research Article

Seismic response prediction using a hybrid unsupervised and supervised machine learning in case of 3D RC frame buildings

Benbokhari Abdellatif1, Benazouz Chikh1, Mébarki Ahmed2,3

1Laboratoire des Travaux publics, ingénierie de Transport, environnement, Ecole Nationale Supérieure des Travaux Publics, Algeria
2UPEC, CNRS, Laboratory Modélisation et Simulation Multi Echelle, University Gustave Eiffel, France
3Nanjing Tech University, China

Keywords

Abstract


Nonlinear dynamic analysis; 

 Machine learning; 

Seismic response prediction; 

Unsupervised algorithms; 

Artificial neural networks



The seismic vulnerability assessment represents an important step in monitoring the buildings’ capacity and checking their performance during and after earthquake events. The Nonlinear Time History Analysis (NL-THA) is considered the most reliable method that is used to calculate the exact structural behavior of any building. However, this sophisticated method is known for its complexity, the use of Finite Element (FE) software, and computational time consuming, especially in the case of tall buildings. For that reason, An Artificial Neural network (ANN) is used to develop a new model able to predict the essential Engineering Demand Parameters (EDPs), i.e., the Maximum Base Shear (MBS), the Maximum Inter-story Drift (MIDR) and the Maximum Roof Drift Ratio (RDR). Unsupervised algorithms such as the Principal Component Analysis PCA and the Autoencoder are coupled with the ANN to reduce the dimensionality, improve the dataset quality, and reduce the irrelevant features. More than 192,000 buildings are analyzed using the NL-THA and eighty artificial ground motions (GMs) to generate the dataset. The buildings’ characteristics are generated randomly from the selection range. The results showed that the Autoencoder-ANN model represents the highest performance compared to the PCA-ANN and ANN models. The Autoencoder-ANN model could quickly and accurately predict the seismic responses of unseen ground motions using only the building’s characteristics and the GM parameters without using any FE software.

© 2024 MIM Research Group. All rights reserved.

LATEST News

20/08/2024 Engineering Village Ei Compendex Index: Journal of Research on Engineering Structures and Materials has been accepted for inclusion in the Ei Compendex index. Ei Compendex, formerly known as the Engineering Index, is one of Elsevier's flagship databases, renowned for providing comprehensive and reliable content in the field of engineering dating back to 1884. This inclusion will enhance the visibility of our journal and further support the dissemination of high-quality research.


20/04/2024 Collaboration for HSTD-2024Editorial Board of our journal and Organizing Committee of the III. International Conference on High-Speed Transport Development (HSTD) have agreed to collaborate. Extended versions of the selected papers from the conference will be published in our journal. For more see Events.

20/04/2024 Collaboration for DSL2024-SS1Editorial Board of our journal and Organizing Committee of the DSL2024 Fluid Flow, Energy Transfer & Design (SS1) have agreed to collaborate. Extended versions of the selected papers from the session will be published in our journal. For more see Events. .



(More details of the news may be given in the News section)


For more see News...

LATEST AWARDS


2023 Reviewer Awards:

Please, visit Reviewer Awards section for the winners of the 2022 RESM reviewer awards.



2023 Best Paper Award:

The paper authored by Ferzan Fidan, Naim Aslan, Mümin Mehmet Koç entitled as “Morpho-structural and compressive mechanical properties of graphene oxide reinforced hydroxyapatite scaffolds for bone tissue applications” is awarded.



2023 Most Cited Paper Award:

The paper authored by Ercan Işık, Ehsan Harirchian, Hüseyin Bilgin, Kirti Jadhav entitled as “The effect of material strength and discontinuity in RC structures according to different site-specific design spectra" is awarded.


abstractıng/ındexıng

  • Asos Indeks
  • CiteFactor
  • Cosmos
  • CrossRef
  • Directory of Research Journal Indexing
  • Ei Compendex (Elsevier)
  • Engineering Journals (ProQuest)
  • EZB Electronic Journal Library
  • Global Impact Factor
  • Google Scholar
  • InfoBase Index
  • International Institute of Organized Research (I2OR)
  • International Scientific Indexing (ISI)
  • Materials Science & Engineering Database (ProQuest)
  • Open Academic Journals Index
  • Publication Forum
  • Research BibleScientific Indexing Service
  • Root Indexing
  • Scopus
  • Ulakbim TR Index (Tubitak)
  • Universal Impact Factor
  • Scope Database




MIM RESEARCH GROUP

©2014. All rights reserved


Contact :

For publication issues

jresm@jresm.net

editor.jresm@gmail.com


For administrative issues:

mim@mimrg.net


Postal Address:

Kemal Öz Mah. 3. Bilgi Sok., 4A, No:13 Usak/Turkey



Last update

of this page:


30.11.2024

(dd.mm.yyyy)


Go to main page for last version