Prediction model for compressive arch action capacity of RC frame structures under column removal scenario using gene expression programming

By Iftikhar Azim, Jian Yang, Muhammad Faisal Javed, Muhammad Farjad Iqbal, Z. Mahmood, Feiliang Wang, Qing-feng Liu. Structures, 2020

147 citations recorded by the source corpus.

Abstract Compressive arch action (CAA) is one of the important resistance mechanisms against progressive collapse in reinforced concrete (RC) frame buildings at small deformations. In this study, the distinguishing features of Gene Expression Programming (GEP) are utilized in order to establish a prediction model for the CAA capacity of RC beam-column substructures. The proposed equation correlates CAA capacity with six input parameters, i.e., compressive strength of concrete (fꞌc), double-beam span-to-depth ratio ( L d ), width of beam (b), top and bottom longitudinal reinforcement ratio at the joints (ρt & ρb, respectively), and the ratio of axial restraints stiffness to the axial stiffness of beam (α). The data for the above-mentioned variables is collected from different studies to develop the proposed model and subsequently implemented for the verification purpose. Different statistical and external validations criteria recommended in literature are carried out to assess the performance of the developed model. Furthermore, sensitivity and parametric analyses are also performed using criteria available in literature. The performance of the genetically developed GEP model was checked and compared with models developed by using regression techniques. The GEP model demonstrated superior performance to linear and non-linear regression methods. The results show that the developed model is successfully capable of evaluating the CAA capacity of RC beam-column substructures and is incredibly imperative for prediction rationales.

Subfields: Building and Construction, Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/64a87477eed1261fe140bb454d5ba5c88b01d795

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Civil and Structural Engineering

Citations in the corpus

Applications of Gene Expression Programming and Regression Techniques for Estimating Compressive Strength of Bagasse Ash based Concrete (2020, background): “Moreover, lower values of RMSE and higher values of R2 and NSE show that the developed models adequately simulated the results [40].”