Evaluating the behaviour of centrally perforated unreinforced masonry walls: Applications of numerical analysis, machine learning, and stochastic methods

The presence of openings greatly affects the response of unreinforced masonry (URM) walls. This topic greatly attracts the attention of many researchers. Perforated unreinforced masonry (PURM) walls under in-plane loads through the truss discretization method (TDM) along with several machine learning approaches such as Multilayer perceptron (MLP), Group of Method Data Handling (GMDH), and Radial basis function (RBF) are described in this paper. A new method named Multi-pier (MP) that is fast and accurate, is used to determine the behavior of PURM walls. The results of the MP method are expressed as a ratio of lateral load-bearing capacity and initial stiffness of PURM walls to the solid wall in order to generalize the obtained results to other PURM walls. The outcomes of the MP method are employed to predict the behavior of PURM walls using various machine learning approaches. Using the validated network with suitable accuracy, empirical functions and curves are presented in an effort to provide a simplified and practical approach to assess the reduction in the load-bearing capacity and initial stiffness of PURM walls. Results indicate that the adjacent piers of opening have a remarkable impact on the overall response of the PURM wall. Finally, the ability of the MP method to conduct stochastic analysis is evaluated. Moreover, the effect of randomness in the mechanical characteristics and their spatial variation within the PURM wall is presented. (c) 2021 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Ain Shams University.

Automated summary

This paper describes the response of perforated unreinforced masonry (PURM) walls under in-plane loads and uses various machine learning methods for prediction. The results of the study indicate that the adjacent piers of the opening have a remarkable impact on the overall response of the PURM wall.