Machine learning-based prediction of shear strength in interior beam-column joints
Abstract The beam-column joint is a critical structural element in reinforced concrete structures, especially under lateral loading conditions. These joints are prone to failure due to high shear stress concentrations, making their accurate design and assessment essential for structural safety.This...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-05-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-06941-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract The beam-column joint is a critical structural element in reinforced concrete structures, especially under lateral loading conditions. These joints are prone to failure due to high shear stress concentrations, making their accurate design and assessment essential for structural safety.This study aims to assess the accuracy of existing building code provisions for predicting joint shear strength of interior beam-column joints and to develop an advanced predictive model that addresses the code provisions limitations. By analyzing a database consist of 158 tested specimens, a significant discrepancy was observed between code provisions and experimental joint shear strengths, highlighting the unreliability of existing code provisions. To address this, an artificial neural networks (ANNs) were employed to create a model considering key factors influencing joint behavior. Statistical analysis demonstrated the ANN model’s exceptional accuracy in predicting joint shear strength of interior beam-column joints, achieving a correlation coefficient of 0.98 with experimental data. This performance significantly outperformed the 0.66–0.73 range observed for code-based predictions. The model's parameters are presented in a user-friendly format for easy implementation using spreadsheet software, making it a valuable tool for enhancing shear strength predictions in future building codes. |
|---|---|
| ISSN: | 3004-9261 |