Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Design of Columns under a Centric Load01:17

Design of Columns under a Centric Load

104
The design of columns under centric load is a fundamental aspect of structural engineering and is critical for ensuring the stability and integrity of structures. Euler's and Secant's formulas are central to understanding and calculating the critical load and deformation behaviors of columns, providing a basis for safe and effective structural design.
Euler's formula is applicable under the assumption that the column is a perfect, straight, homogenous prism, and it is operating...
104
Stress Concentrations in Circular Shafts01:18

Stress Concentrations in Circular Shafts

165
Consider the elastic torsion formula, which applies to a circular shaft with a consistent cross-section. This formula assumes that the shaft's ends are loaded with rigid plates firmly attached. However, in many cases, torques are applied to the shaft through mechanisms like flange couplings or gears, which are connected by keys inserted into keyways. This application method modifies the stress distribution near the point of torque application, causing it to deviate from the distributions...
165
Design of Columns under an Eccentric Load01:21

Design of Columns under an Eccentric Load

449
Designing columns to withstand eccentric loads is a critical aspect of structural engineering, ensuring structures can support off-center loads without failure. This design process must account for the additional normal stresses introduced by eccentric loading, which can significantly influence a column's stress distribution and overall stability. An eccentric load applied to a column induces normal stresses that can be conceptualized as a combination of stresses due to an equivalent...
449
Euler's Formula for Pin-Ended Columns01:21

Euler's Formula for Pin-Ended Columns

292
In structural engineering, the stability of columns under compressive axial loads is a critical consideration, described as buckling. A typical example involves a column PQ, which is pin-connected at both ends and subjected to a centric axial load F applied at one end, with a reaction force of F' = -F at the other end. Here, it is crucial to understand that when an applied load exceeds the critical load, buckling occurs as the system becomes unstable.
To calculate the critical load,...
292
Eccentric Loading01:16

Eccentric Loading

323
Eccentric loading is a crucial concept in the study of structural engineering and mechanics, particularly when analyzing the stability and stress distribution in columns. Unlike centric loading, where the force is applied along the centroidal axis, causing uniform compression, eccentric loading occurs when a force is applied off-center. This off-center application introduces not only direct compressive stress but also bending stress, significantly influencing the column's behavior under...
323
Stresses under Combined Loadings01:23

Stresses under Combined Loadings

146
When analyzing a bent tube with a circular cross-section subjected to multiple forces, it is crucial to determine the stress distribution in order to maintain structural integrity under varied load conditions.
The process begins by slicing the tube at critical points and analyzing the internal forces and stress components at these sections, focusing on the centroid. Normal stresses, generated by axial forces and bending moments, are either compressive or tensile and vary across the section from...
146

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Predicting flexural strength of hybrid FRP-steel reinforced beams using symbolic regression and ML techniques.

Scientific reports·2025
Same author

Prediction of the axial compression capacity of ECC-CES columns using adaptive sampling and machine learning techniques.

Scientific reports·2025
Same author

Symbolic regression for strength prediction of eccentrically loaded concrete-filled steel tubular columns.

Scientific reports·2025
Same author

Strength prediction of ECC-CES columns under eccentric compression using adaptive sampling and ML techniques.

Scientific reports·2025
Same author

STM-based symbolic regression for strength prediction of RC deep beams and corbels.

Scientific reports·2024
Same author

Prediction and reliability analysis of shear strength of RC deep beams.

Scientific reports·2024

Related Experiment Video

Updated: Jun 9, 2025

Determination of the Mechanical Properties of Flexible Connectors for Use in Insulated Concrete Wall Panels
05:26

Determination of the Mechanical Properties of Flexible Connectors for Use in Insulated Concrete Wall Panels

Published on: October 19, 2022

1.6K

Circular rubber aggregate CFST stub columns under axial compression: prediction and reliability analysis.

Khaled Megahed1, Nabil Said Mahmoud2, Saad Elden Mostafa Abd-Rabou2

  • 1Department of Structural Engineering, Mansoura University, PO BOX 35516, Mansoura, Egypt. k.megahed@mans.edu.eg.

Scientific Reports
|November 1, 2024
PubMed
Summary

Machine learning models accurately predict the axial strength of rubber aggregate concrete (RBAC)-filled steel tube (RCFST) columns, outperforming current design codes. A new design expression offers practical accuracy for structural safety assessments.

Keywords:
Bayesian optimization (BO) techniqueCatBoostConcrete-filled steel tubesGaussian process regressionLightGBMRandom forestReliability analysisRubber aggregate concreteStub columnsSymbolic regressionXGBoost

More Related Videos

Predicting Catalyst Extrudate Breakage Based on the Modulus of Rupture
09:53

Predicting Catalyst Extrudate Breakage Based on the Modulus of Rupture

Published on: May 13, 2018

8.3K
Finite Element Modeling for the Simulation of the Quasi-Static Compression of Corrugated Tapered Tubes
06:34

Finite Element Modeling for the Simulation of the Quasi-Static Compression of Corrugated Tapered Tubes

Published on: January 6, 2023

1.6K

Related Experiment Videos

Last Updated: Jun 9, 2025

Determination of the Mechanical Properties of Flexible Connectors for Use in Insulated Concrete Wall Panels
05:26

Determination of the Mechanical Properties of Flexible Connectors for Use in Insulated Concrete Wall Panels

Published on: October 19, 2022

1.6K
Predicting Catalyst Extrudate Breakage Based on the Modulus of Rupture
09:53

Predicting Catalyst Extrudate Breakage Based on the Modulus of Rupture

Published on: May 13, 2018

8.3K
Finite Element Modeling for the Simulation of the Quasi-Static Compression of Corrugated Tapered Tubes
06:34

Finite Element Modeling for the Simulation of the Quasi-Static Compression of Corrugated Tapered Tubes

Published on: January 6, 2023

1.6K

Area of Science:

  • Structural Engineering
  • Materials Science
  • Machine Learning Applications

Background:

  • Steel tubes enhance rubber aggregate concrete (RBAC) structural integrity, forming RBAC-filled steel tubes (RCFST).
  • Existing design codes have limitations in assessing the axial compressive behavior and ensuring the structural safety of circular stub RCFST (CS-RCFST) columns.
  • A scarcity of research exists on the structural safety of these composite columns.

Purpose of the Study:

  • To explore machine learning (ML) capabilities for predicting the axial strength of CS-RCFST columns.
  • To compare the performance of various ML models for this prediction task.
  • To develop a practical design expression and assess the reliability of ML models in structural design.

Main Methods:

  • Utilized an experimental database of 145 CS-RCFST columns.
  • Applied six ML models: symbolic regression (SR), XGBoost, CatBoost, random forest, LightGBM, and Gaussian process regression.
  • Employed Bayesian Optimization for hyperparameter tuning and conducted reliability analysis.

Main Results:

  • The CatBoost model demonstrated superior accuracy (R²=0.999 training, R²=0.993 testing).
  • A practical design expression based on SR showed good accuracy (average test-to-prediction ratio of 0.99).
  • ML models significantly outperformed AISC360 and EC4 in predicting axial strength.

Conclusions:

  • ML models offer a highly reliable and accurate approach for predicting CS-RCFST column axial strength compared to current design codes.
  • The developed SR-based design expression provides acceptable accuracy for practical applications.
  • Reliability analysis confirms the suitability of ML models for practical structural design, with proposed resistance design factors.