Machine-learning-assisted design of high strength steel I-section columns

High strength steel has been attracting attention in the building industry due to its superior mechanical properties. The accurate design of high strength steel structures is crucial to boost its wide application. In this paper, an accurate and unified design approach for high strength steel I-secti...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng, Jinpeng, Li, Xuelai, Jiang, Ke, Li, Shuai, Su, Andi, Zhao, Ou
Other Authors: School of Civil and Environmental Engineering
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/179387
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-179387
record_format dspace
spelling sg-ntu-dr.10356-1793872024-07-29T06:12:26Z Machine-learning-assisted design of high strength steel I-section columns Cheng, Jinpeng Li, Xuelai Jiang, Ke Li, Shuai Su, Andi Zhao, Ou School of Civil and Environmental Engineering Engineering Buckling Columns High strength steel has been attracting attention in the building industry due to its superior mechanical properties. The accurate design of high strength steel structures is crucial to boost its wide application. In this paper, an accurate and unified design approach for high strength steel I-section columns with different material grades, boundary conditions, geometric dimensions (including cross-section sizes and member lengths) and failure modes is proposed based on machine learning. Firstly, 871 experimental and numerical data were collected from the literature to establish a database. Then, seven machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbour, Adaptive Boosting, Extreme Gradient Boosting and Categorical Boosting, were applied to establish machine learning regression models to predict buckling resistances of high strength steel I-section columns. The model performance was then evaluated through statistic indices, with the evaluation results indicating that the Categorical Boosting trained model yields the highest level of accuracy. Based on the data in the collected database, the regression model trained by Categorical Boosting and existing codified design provisions, as given in the European code and American specification, were assessed and compared. The European code and American specification were found to yield scattered and inaccurate failure load predictions, while the Categorical Boosting trained model led to substantially more accurate and consistent failure load predictions for high strength steel I-section columns with different material grades, boundary conditions, geometric dimensions and failure modes. 2024-07-29T06:12:26Z 2024-07-29T06:12:26Z 2024 Journal Article Cheng, J., Li, X., Jiang, K., Li, S., Su, A. & Zhao, O. (2024). Machine-learning-assisted design of high strength steel I-section columns. Engineering Structures, 308, 118018-. https://dx.doi.org/10.1016/j.engstruct.2024.118018 0141-0296 https://hdl.handle.net/10356/179387 10.1016/j.engstruct.2024.118018 2-s2.0-85190719516 308 118018 en Engineering Structures © 2024 Elsevier Ltd. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Buckling
Columns
spellingShingle Engineering
Buckling
Columns
Cheng, Jinpeng
Li, Xuelai
Jiang, Ke
Li, Shuai
Su, Andi
Zhao, Ou
Machine-learning-assisted design of high strength steel I-section columns
description High strength steel has been attracting attention in the building industry due to its superior mechanical properties. The accurate design of high strength steel structures is crucial to boost its wide application. In this paper, an accurate and unified design approach for high strength steel I-section columns with different material grades, boundary conditions, geometric dimensions (including cross-section sizes and member lengths) and failure modes is proposed based on machine learning. Firstly, 871 experimental and numerical data were collected from the literature to establish a database. Then, seven machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbour, Adaptive Boosting, Extreme Gradient Boosting and Categorical Boosting, were applied to establish machine learning regression models to predict buckling resistances of high strength steel I-section columns. The model performance was then evaluated through statistic indices, with the evaluation results indicating that the Categorical Boosting trained model yields the highest level of accuracy. Based on the data in the collected database, the regression model trained by Categorical Boosting and existing codified design provisions, as given in the European code and American specification, were assessed and compared. The European code and American specification were found to yield scattered and inaccurate failure load predictions, while the Categorical Boosting trained model led to substantially more accurate and consistent failure load predictions for high strength steel I-section columns with different material grades, boundary conditions, geometric dimensions and failure modes.
author2 School of Civil and Environmental Engineering
author_facet School of Civil and Environmental Engineering
Cheng, Jinpeng
Li, Xuelai
Jiang, Ke
Li, Shuai
Su, Andi
Zhao, Ou
format Article
author Cheng, Jinpeng
Li, Xuelai
Jiang, Ke
Li, Shuai
Su, Andi
Zhao, Ou
author_sort Cheng, Jinpeng
title Machine-learning-assisted design of high strength steel I-section columns
title_short Machine-learning-assisted design of high strength steel I-section columns
title_full Machine-learning-assisted design of high strength steel I-section columns
title_fullStr Machine-learning-assisted design of high strength steel I-section columns
title_full_unstemmed Machine-learning-assisted design of high strength steel I-section columns
title_sort machine-learning-assisted design of high strength steel i-section columns
publishDate 2024
url https://hdl.handle.net/10356/179387
_version_ 1814047203635757056