What question did this study set out to answer?

The aim is to predict the structural performance of long-bolted steel connections using machine learning techniques.

March 17, 2026AI in Civil EngineeringOpen Access

Machine learning-based prediction of the structural performance of a long-bolted steel connection

View Full Paper

Ask AI

Bookmark

Authors

MEMostafa ElhadaryLakehead University ABAhmed BediwyAbu Dhabi University AEAhmed ElshaerLakehead University

Discussion

Member takes

Overview

An analysis demonstrates machine learning predicts failure modes and capacity in modular steel connections, suggesting innovative design improvements.

Key Points

The aim is to predict the structural performance of long-bolted steel connections using machine learning techniques.
Developed a finite element model (FEM) using LS-DYNA software.
Trained machine learning models on a matrix of 240 FEMs with various design parameters.
Utilized algorithms including neural networks, genetic regression, and decision trees.
Applied hyperparameter optimization to enhance model accuracy.
Generated mathematical formulas for predicting moment capacity using symbolic regression.
Machine learning approaches effectively predict the ultimate moment capacity of bolted connections.
High accuracy was achieved in predicting failure modes and capacity.
Formulas developed demonstrated reliability when validated with testing data.

Cite This Study

Elhadary et al. (2026) studied this question.

synapsesocial.com/papers/69b8f0fddeb47d591b8c5c19 https://doi.org/10.1007/s43503-026-00087-9

View Full Paper

Ask AI

Bookmark

March 17, 2026AI in Civil EngineeringOpen Access

Machine learning-based prediction of the structural performance of a long-bolted steel connection

View Full Paper

Ask AI

Bookmark

Authors

MEMostafa ElhadaryLakehead University ABAhmed BediwyAbu Dhabi University AEAhmed ElshaerLakehead University

Discussion

Member takes

Overview

An analysis demonstrates machine learning predicts failure modes and capacity in modular steel connections, suggesting innovative design improvements.

Key Points

The aim is to predict the structural performance of long-bolted steel connections using machine learning techniques.
Developed a finite element model (FEM) using LS-DYNA software.
Trained machine learning models on a matrix of 240 FEMs with various design parameters.
Utilized algorithms including neural networks, genetic regression, and decision trees.
Applied hyperparameter optimization to enhance model accuracy.
Generated mathematical formulas for predicting moment capacity using symbolic regression.
Machine learning approaches effectively predict the ultimate moment capacity of bolted connections.
High accuracy was achieved in predicting failure modes and capacity.
Formulas developed demonstrated reliability when validated with testing data.

Cite This Study

Elhadary et al. (2026) studied this question.

synapsesocial.com/papers/69b8f0fddeb47d591b8c5c19 https://doi.org/10.1007/s43503-026-00087-9

Also Consider

Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark