Explainable machine learning models for predicting the axial compression capacity of concrete filled steel tubular columns

Çakıroğlu, Celal; Islam, Kamrul; Bekdaş, Gebrai̇l; Işıkdağ, Ümit; Mangalathu, Sujith

doi:10.1016/j.conbuildmat.2022.129227

Cited by 53 publications

(18 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Solhmirzaei et al (2020) presented a data-driven ML framework, which uses multiple ML algorithms to predict the failure mode and shear capacity of ultra-high-performance concrete (UHPC) beams. In addition, the importance of explainability in ML models is highlighted in a study by Cakiroglu et al (2022). They developed data-driven ML models using 719 experiments to predict the axial compression capacity of rectangular concrete-filled steel tubular columns Cakiroglu et al (2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Damage detection on steel-reinforced concrete produced by corrosion via YOLOv3: A detailed guide

Guzmán-Torres

Domínguez-Mota

Martínez-Molina

et al. 2023

Front. Built Environ.

View full text Add to dashboard Cite

Damage assessment applied to reinforced concrete elements is one of the main activities of infrastructure maintenance tasks. Among these elements, the problem of corrosion in reinforced concrete is particularly critical and requires careful consideration. Annually, governments invest a large amount of economic resources in this activity. However, most methodologies for damage assessment rely on visual inspection, which may be subjectively interpreted, producing inconsistent results and requiring a considerable amount of time and resources. This study evaluates the performance of real-time object detection using You Only Look Once, version 3, for detecting corrosion damage in concrete structures. The architecture of YOLOv3 is based on a complex, but efficient, convolutional neural network fed by a dataset proposed and labeled by the authors. Two training stages were established to improve the model precision, using transfer learning with medium- and high-resolution training images. The test results show satisfactory concrete-corrosion detection through validation photographs and videos demonstrating the capabilities of explainable artificial intelligence and its applications in civil engineering.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In addition, the importance of explainability in ML models is highlighted in a study by Cakiroglu et al (2022). They developed data-driven ML models using 719 experiments to predict the axial compression capacity of rectangular concrete-filled steel tubular columns Cakiroglu et al (2022).…”

Section: Introductionmentioning

confidence: 99%

Damage detection on steel-reinforced concrete produced by corrosion via YOLOv3: A detailed guide

Guzmán-Torres

Domínguez-Mota

Martínez-Molina

et al. 2023

Front. Built Environ.

View full text Add to dashboard Cite

show abstract

“…Almustafa and Nehdi (2022) developed a prediction model of the maximum displacement of RC columns exposed to blast loading using ensemble tree-based algorithms. Many scholars have also tried to predict the axial loading bearing capacity of CFST columns with various machining learning techniques including artificial neural network (ANN), random forest, gradient boosting, support vector machines (SVM) and genetic algorithms, and so on (Cakiroglu et al, 2022; Hou and Zhou, 2022; Naser et al, 2021; Vu et al, 2021). The machine learning-based prediction models all yield extremely high prediction accuracy since there are up to 3000 available axial compression tests of CFST columns.…”

Section: Introductionmentioning

confidence: 99%

Post-blast capacity evaluation of concrete-filled steel tubular (CFST) column based on machine learning technique

Pang

Mu³

et al. 2023

Advances in Structural Engineering

View full text Add to dashboard Cite

In the present study, the post-blast axial load-bearing capacity of the CFST column under the close-in explosion is investigated. Dynamic response and residual axial load capacity (RALBC) of 1599 circular CFST columns are numerically studied using a validated finite element model. The effects of column dimensions, material properties, blast loading, and axial load ratio are discussed. Based on the huge database, prediction models of RALBC are developed using three commonly used machine learning techniques including Extreme Gradient Boosting (known as XGBoost), Artificial Neutral Network (ANN), and Support Vector Regression (SVR). Comparison results show that the prediction model generated by the XGBoost performs the best among the three methods followed by the ANN and SVR methods. The RALBC of the CFST columns can be estimated rapidly and accurately with the prediction model developed in the present study. Finally, the feature importance of the input variables is analyzed using the additive feature attribution method SHAP (Shapley Additive ExPlanation). The results show that geometric parameters are the main factors impacting the RALBC of the CFST columns under close-in explosion.

show abstract

“…The prediction of the ultimate loads of rectangular columns undergoing axial loading was conducted by Cakiroglu et al using machine learning models. The predicted ultimate loads presented a high accuracy of up to 98.3% [ 35 ].…”

Section: Introductionmentioning

confidence: 99%

Eccentric Compression Behaviors of Self-Compacting Concrete-Filled Thin-Walled Steel Tube Columns

Wang,

Sun,

Zhang

et al. 2023

Materials

View full text Add to dashboard Cite

For the sake of solving sustainability issues and analyzing the complicated service force states, eccentric compression experiments on self-compacting concrete-filled thin-walled medium-length steel tube columns with a circular cross-section were carried out in the present study. Thereafter, the influence of the eccentric ratios and the wall thickness factors on the mechanical behavior and failure characteristics of both the eccentrically loaded and axially loaded columns was comprehensively analyzed. Finally, prediction formulas for the ultimate load of the columns under eccentric compression were proposed, and a comprehensive comparison of the ultimate loads between the predicted values and experimental values was also conducted. The results indicated that the typical failure characteristics of the eccentrically loaded columns presented lateral deflection together with buckling, while the axially compressed columns displayed expansion and rupture at local positions. Moreover, the ultimate loads of the eccentrically loaded columns decreased by 43.0% and 34.5% in comparison to the columns under axial compression, with the wall thickness factor decreasing from 116.7 to 46.7, respectively. Meanwhile, the ratios of the ultimate loads calculated using design codes to the tested values were in the range of 0.70~0.90, which demonstrated that the design codes could predict the ultimate loads conservatively. Additionally, the ratios of the ultimate loads calculated using the proposed formulas to the tested values were within the range of 0.99~1.08, implying that the proposed formulas were more accurate than the design codes. At the same time, the initial stiffness of the columns under eccentric compression was correspondingly lower than that of the columns undergoing axial compression. The lateral deflections along the height of the columns were almost symmetrical at different loading levels. This study could provide a meaningful approach for designing columns and facilitate their application in civil industry.

show abstract

Explainable machine learning models for predicting the axial compression capacity of concrete filled steel tubular columns

Cited by 53 publications

References 70 publications

Damage detection on steel-reinforced concrete produced by corrosion via YOLOv3: A detailed guide

Damage detection on steel-reinforced concrete produced by corrosion via YOLOv3: A detailed guide

Post-blast capacity evaluation of concrete-filled steel tubular (CFST) column based on machine learning technique

Eccentric Compression Behaviors of Self-Compacting Concrete-Filled Thin-Walled Steel Tube Columns

Contact Info

Product

Resources

About