Strength prediction of concrete-filled steel tubular columns using Categorical Gradient Boosting algorithm

•Categorical gradient Boosting (CatBoost) is presented to predict the strength of concrete-filled steel tubular columns.•A total of 3103 tests, which is divided in four datasets, is collected to train and test the learners•The comparison of the present results and those from the code predictions sho...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Engineering structures Ročník 238; s. 112109
Hlavní autoři: Lee, Seunghye, Vo, Thuc P., Thai, Huu-Tai, Lee, Jaehong, Patel, Vipulkumar
Médium: Journal Article
Jazyk:angličtina
Vydáno: Kidlington Elsevier Ltd 01.07.2021
Elsevier BV
Témata:
Algorithms
Building codes
Categorical gradient Boosting (CatBoost)
Code predictions
Composite structures
Concrete columns
Concrete-filled steel tubular columns
Datasets
Diameters
Material strengths
Mechanical properties
Predictions
Slenderness ratio
Steel
Steel columns
Steel tubes
Strength of materials
Concrete-filled steel tubular columns
Slenderness ratio
Code predictions
Categorical gradient Boosting (CatBoost)
Material strengths
ISSN:0141-0296, 1873-7323
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Categorical gradient Boosting (CatBoost) is presented to predict the strength of concrete-filled steel tubular columns.•A total of 3103 tests, which is divided in four datasets, is collected to train and test the learners•The comparison of the present results and those from the code predictions shows very high prediction accuracy•The coefficient of determination (R2), which is the lowest value (R2 = 0.964) for Dataset 2 and the highest one (R2 = 0.996) for Dataset 1. Due to complexities from the interaction between steel tube and concrete filling of concrete-filled steel tubular (CFST) columns, their strengths are very complicated, which is a highly nonlinear relation with material strengths and geometry. Categorical gradient Boosting (CatBoost), which is advanced boosting machine, is presented to solve the problems. A total of 3103 tests, which is divided in four datasets, is trained and tested the learners to determine the ultimate axial strength as the output variable while the strength of materials (concrete and steel) and geometry (e.g., diameters/width/heights, thickness, effective length, eccentricities) are the input ones. The comparison of the present results from 10-fold cross validation and those from the code predictions (AISC 360-16, Eurocode 4 and AS/NZS 2327) and previous study shows very high prediction accuracy in terms of coefficient of determination (R2), which is the lowest value (R2 = 0.964) for Dataset 2 and the highest one (R2 = 0.996) for Dataset 1. While the predictions from three codes beyond material limit and slenderness are less conservative than those within it, CatBoost provides nearly similar experiment results with the mean values as unity without any limits. This algorithm can be used to predict an accurate strength of CFST columns.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0141-0296
1873-7323
DOI:10.1016/j.engstruct.2021.112109