Related Experiment Video
Updated: Jun 24, 2025

A Coupled Experiment-finite Element Modeling Methodology for Assessing High Strain Rate Mechanical Response of Soft Biomaterials
Published on: May 18, 2015
Predictive modeling of wide-shallow RC beams shear strength considering stirrups effect using (FEM-ML) approach
Ahmed A Soliman1, Dina M Mansour2, Ayman H Khalil3
1Structural Engineering & Construction Management Department, Faculty of Engineering & Technology, Future University in Egypt, New Cairo, Egypt.
This study predicts shear strength in wide-shallow reinforced concrete beams using Finite Element Analysis (FEA) and machine learning. Artificial Neural Network (ANN) models achieved 99% accuracy, offering valuable engineering design insights.
Area of Science:
- Structural Engineering
- Materials Science
- Computational Mechanics
Background:
- Accurate prediction of shear strength in reinforced concrete beams is crucial for structural safety and design optimization.
- Wide-shallow beams present unique challenges due to their geometry, necessitating advanced analytical approaches.
- Existing methods may not fully capture the complex behavior of concrete and reinforcement under shear stress.
Purpose of the Study:
- To develop and validate predictive models for the shear strength of wide-shallow reinforced concrete beams.
- To explore the efficacy of Finite Element Analysis (FEA) and various machine learning techniques in shear strength prediction.
- To identify key parameters influencing the shear behavior of these structural elements.
Main Methods:
- Development and validation of a detailed Finite Element Model (FEM) against experimental data (13 specimens).
- Conducting a parametric study to generate a dataset of 77 wide beam configurations.
- Training and comparing machine learning models: Genetic Programming (GP), Evolutionary Polynomial Regression (EPR), and Artificial Neural Network (ANN).
Main Results:
- The FEM demonstrated good accuracy, with maximum differences of 8% and 12% for loads and deflections, respectively.
- Machine learning models showed high predictive capabilities: GP and EPR achieved >95% correlation, while ANN reached 99% accuracy.
- Sensitivity analysis highlighted concrete strength and beam aspect ratio as dominant factors affecting shear strength.
Conclusions:
- FEA combined with machine learning offers a powerful approach for predicting shear strength in wide-shallow reinforced concrete beams.
- ANN models provide highly accurate predictions, valuable for enhancing structural design and engineering practices.
- Understanding the influence of material properties and geometric ratios is essential for reliable shear strength assessment.
Related Concept Videos
Shearing Stresses in a Beam: Problem Solving
Shear on the Horizontal Face of a Beam Element
Distribution of Stresses in a Narrow Rectangular Beam
Shear and Bending Moment Diagram: Problem Solving
Draw a Free-Body Diagram: Start by drawing a free-body diagram of the entire beam, including the concentrated loads, distributed load, and reaction...
Prismatic Beams: Problem Solving
The design begins with analyzing the beam as a free body to identify moments and force balances, thereby determining support reactions. Next, the...
Design of Prismatic Beams for Bending

