SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2016 / Cilt: 6 Sayı: 2

Estimating stiffness modification factor for the coupling beam of coupled shear walls using a neural network model

Boşluklu Perdelerde Bağ Kirişi Rijitlik Düzeltme Çarpanlarının Yapay Sinir Ağı ile Tahmini

Bulent Akbas(Gebze Technical University, Department of Earthquake and Structural Engineering, Gebze, Kocaeli, Turkey)
Bilge Doran(Yildiz Technical University, Faculty of Civil Engineering, Department of Civil Engineering, Esenler, Istanbul, Turkey)
Sema Alacali(Yildiz Technical University, Faculty of Civil Engineering, Department of Civil Engineering, Esenler, Istanbul, Turkey)
Bora Akşar(Gebze Technical University, Department of Earthquake and Structural Engineering, Gebze, Kocaeli, Turkey)
Pages
273–282
Publication Date
2016-06-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The approach adapted in this study was shown to be capable of providing the best accurate estimates of the stiffness modification factor by using the three design parameters.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Neural Network NN have been widely used in modeling engineering problems, for the last two decades as a result of the developments in computer and software technology.
📊
Key Findings & Data:The results of NN models, if constructed properly, generally yield a more realistic and accurate predictions.
💡
Conclusion & Impact:The approach adapted in this study was shown to be capable of providing the best accurate estimates of the stiffness modification factor by using the three design parameters.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Geri yayılım algoritması · Boşluklu perde · Eşdeğer çerçeve

Abstract

Neural Network NN have been widely used in modeling engineering problems, for the last two decades as a result of the developments in computer and software technology. The results of NN models, if constructed properly, generally yield a more realistic and accurate predictions. This study is intended to estimate the stiffness modification factor for the coupling beam of coupled shear walls using a neural network model. A multi-layered feed-forward NN model trained with the back-propagation algorithm is developed to model the non-linear relationship between the geometrical and mechanical properties of a coupled shear walls and its stiffness modification factor. The approach adapted in this study was shown to be capable of providing the best accurate estimates of the stiffness modification factor by using the three design parameters.

Özet

Son 20 yılda bilgisayar teknolojisi ve bilgisayar yazılımlarındaki gelişmeler nedeniyle, Yapay Sinir Ağları YSA mühendislik problemlerinin modellenmesinde sıkça kullanılmaktadır. Doğru bir şekilde kurulması durumunda YSA model sonuçları genellikle daha gerçekçi ve doğruya yakın tahminler vermektedir. Bu çalışma ile boşluklu perdelerin bağ kirişleri için tarif edilmiş olan rijitlik düzeltme çarpanlarının YSA ile tahmini hedeflenmiştir. Boşluklu perdeli sistemlerde geometrik ve mekanik özellikler arasındaki doğrusal olmayan ilişki ile rijitlik düzeltme çarpanlarını modellemek üzere, geri yayılım algoritması ile eğitilen çok katmanlı, ileri beslemeli bir YSA modeli geliştirilmiştir. Çalışmada önerilen yaklaşım ile rijitlik düzeltme çarpanlarının üç tasarım parametresi kullanılarak en iyi şekilde tahmin edilebileceği görülmüştür

🔖

Cite This Article

Akbas, B., Doran, B., Alacali, S., Akşar, B. (2016). Estimating stiffness modification factor for the coupling beam of coupled shear walls using a neural network model. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 6 Sayı: 2, 273–282. https://ajindex.com/articles/1152691

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (6)

  1. Alacalı, SN., Doran, B., Akbas, B. 2006. Predicting Lateral Confinement Coefficient for R/C Rectangular Columns By a Neural Network Model. EAEE, First European Conference on Earthquake Engineering and Seismology, Geneva, Switzerland, 3-8 September, Paper Number: 1159.
  2. Wadsworth, HM. 1997. Handbook of Statistical Methods for Engineers and Scientists. McGrawHill Inc, NewYork.
  3. Williams, ME., Hoit, MI. 2004. Bridge pier live load analysis using neural networks. Adv. Eng. Softw., 35: 645–652.
  4. Yeung, WT., Smith, JW. 2005. Damage detection in bridges using neural networks for pattern recognition of vibration signatures. Eng. Struct., 27: 685–698.
  5. joints. Comput Struct., 44(5):1239-1247.
  6. Tehranizadeh, M., Safi, M. 2004. Application of artificial intelligence for construction of design spectra. Eng. Struct., 26: 707–720.