Machine learning base models to predict the punching shear capacity of posttensioned UHPC flat slabs.

The aim of this research is to present correction factors for the punching shear formulas of ACI-318 and EC2 design codes to adopt the punching capacity of post tensioned ultra-high-performance concrete (PT-UHPC) flat slabs. To achieve that goal, the results of previously tested PT-UHPC flat slabs were used to validate the developed finite element method (FEM) model in terms of punching shear capacity. Then, a parametric study was conducted using the validated FEM to generate two databases, each database included concrete compressive strength, strands layout, shear reinforcement capacity and the aspect ratio of the column besides the correction factor (the ratio between the FEM punching capacity and the design code punching capacity). The first considered design code in the first database was ACI-318 and in the second database was EC2. Finally, there different "Machine Learning" (ML) techniques manly "Genetic programming" (GP), "Artificial Neural Network" (ANN) and "Evolutionary Polynomial Regression" (EPR) were applied on the two generated databases to predict the correction factors as functions of the considered parameters. The results of the study indicated that all the developed (ML) models showed almost the same level of accuracy in terms of the punching ultimate load (about 96%) and the ACI-318 correction factor depends mainly on the concrete compressive strength and aspect ratio of the column, while the EC2 correction factor depends mainly on the concrete compressive strength and the shear reinforcement capacity.