Loading...

Hysteretic response of confined masonry walls by Prandtl neural networks

Joghataie, A ; Sharif University of Technology | 2007

567 Viewed
  1. Type of Document: Article
  2. Publisher: 2007
  3. Abstract:
  4. In this paper a new method of modeling shear force-displacement relationship for confined masonry walls by neural networks has been presented. Although the mathematical models have been very useful in the simulations so far, however developing more accurate models is necessary. While developing precise mathematical models for highly hysteretic materials is itself challenging and practically cumbersome, the use of learning algorithms is an attractive alternative. The issue of material modeling by neural networks has been a challenging one itself, noticing available neural networks have some limitations in the learning of non-linearity. In this paper a new type neural network, called Prandtl Neural Network (PNN), which has recently been developed by the authors and used in the analysis of nonlinear structural systems, has been used in the modeling of the confined masonry walls. Before testing the method on data obtained from laboratory tests, it has been necessary to show that the PNN can learn to model the tri-linear characteristic. Hence the training and testing data of the neural network has been collected through the numerical simulation of the wall response under earthquakes based on the available mathematical models. The result has been very promising and the PNN has been capable of learning to predict the response with very high precision, close to exact. © AES-Advanced Engineering Solutions
  5. Keywords:
  6. Confined masonry walls ; Force-displacement relationships ; High precision ; Hysteretic materials ; Hysteretic response ; Laboratory test ; Material modeling ; Method of modeling ; Non-linear response ; Non-linearity ; Structural systems ; Training and testing ; Computer simulation ; Genetic algorithms ; Hysteresis ; Learning algorithms ; Masonry construction ; Materials ; Mathematical models ; Professional aspects ; Retaining walls ; Walls (structural partitions) ; Neural networks
  7. Source: 1st International Conference on Advances and Trends in Engineering Materials and their Applications, AES-ATEMA'2007, Montreal, QC, 6 August 2007 through 10 August 2007 ; 2007 , Pages 525-533 ; 19243642 (ISSN) ; 0978047907 (ISBN); 9780978047900 (ISBN)
  8. URL: https://www.researchgate.net/publication/283610230_Hysteretic_response_of_confined_masonry_walls_by_Prandtl_Neural_Networks