Prediction of shear capacity of steel channel sections using machine learning algorithms

This study presents the application of popular machine learning algorithms in prediction of the shear resistance of steel channel sections using experimental and numerical data. Datasets of 108 results of stainless steel lipped channel sections and 238 results of carbon steel LiteSteel sections were...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Thin-walled structures Jg. 175; S. 109152
Hauptverfasser: Dissanayake, Madhushan, Nguyen, Hoang, Poologanathan, Keerthan, Perampalam, Gatheeshgar, Upasiri, Irindu, Rajanayagam, Heshachanaa, Suntharalingam, Thadshajini
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.06.2022
Schlagworte:
Channel sections
Design rules
Machine learning
Shear capacity
Shear capacity
Channel sections
Design rules
Machine learning
ISSN:0263-8231, 1879-3223
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study presents the application of popular machine learning algorithms in prediction of the shear resistance of steel channel sections using experimental and numerical data. Datasets of 108 results of stainless steel lipped channel sections and 238 results of carbon steel LiteSteel sections were gathered to train machine learning models including support vector regression (SVR), multi-layer perceptron (MLP), gradient boosting regressor (GBR), and extreme gradient boosting (XGB). The cross-validation with 10 folds has been conducted in the training process to avoid over-fitting. The optimal hyperparameter combinations for each machine learning model were found during the hyperparameter tuning process and four performance indicators were used to evaluate the performance of the trained models. The comparison results suggest that all four implemented machine learning models reliably predict the shear capacity of both stainless steel lipped channel sections and carbon steel LiteSteel sections while the implemented SVR algorithm is found to be the best performing model. Moreover, it is shown that the implemented machine learning models exceed the prediction accuracy of the available design equations in estimating the shear capacity of steel channel sections. •Optimal hyperparameter combinations were found for SVR, MLP, GBR and XGB models.•Each machine learning model was evaluated based on four performance indicators.•The implemented SVR algorithm is proved to be the best performing model.•Four implemented models perform better than the available design equations.
ISSN:0263-8231
1879-3223
DOI:10.1016/j.tws.2022.109152