Machine learning model for predicting structural response of RC columns subjected to blast loading

Almustafa, Monjee K.; Nehdi, Moncef L.

doi:10.1016/j.ijimpeng.2021.104145

Cited by 40 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an important step in measuring the performance of the machine learning models. References from work by Thai et al [20], Almustafa et al [9], Yin et al [21], Zhang et al [22] and Zhou et al [23] are considered for selecting the statistical performance measures used for the model evaluation in this research. They are the coefficient of determination, R 2 , the root average squared error, RASE and the average absolute error, AAE.…”

Section: Performance Indicatorsmentioning

confidence: 99%

See 1 more Smart Citation

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

Punnappilly,

Baskar

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Since limited research results are available in the area of blast wave interactions with structural surfaces, a comparative study is undertaken to ascertain the interaction effects of blast waves generated by exploding spherical and cylindrical charges on the surface of a concrete structural unit. The effective blast pressure experienced by a concrete unit is evaluated and its distribution across the front face is studied here for two distinct charge shapes, namely spherical and cylindrical. The finite element analysis is carried out for nine different scaled distances. Random forests algorithm was utilized to analyze the 450 observations to evaluate the results and build predictive models. The best models were selected based on standard performance indicators. For cylindrical charges, the aspect ratio was also factored in the analysis. The distribution of effective pressure indicates unique patterns for the two different charge shapes in the graphical comparison. The effective pressures caused by the cylindrical charge shape for the specific aspect ratios considered here are lower by 84 % on average compared to the effect caused by a spherical charge, which results from the distinct characteristics of blast waves generated by the explosion of cylindrical charges.

show abstract

Section: Performance Indicatorsmentioning

confidence: 99%

“…Ensemble tree-based algorithms have been used by Almustafa et al [9] to predict the maximum displacement of blast loaded reinforced concrete columns. The authors report high prediction performance of the proposed model by employing tree-based algorithms.…”

Section: Introductionmentioning

confidence: 99%

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

Punnappilly,

Baskar

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Zhou et al (2022c) proposed a multi-layer long-short-term memory neural network model and a multi-hidden layer neural network model to predict the failure model and damage degree of the RC column after the explosion. 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).…”

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

“…Currently, many researchers have applied ML methods to study the impact resistance of reinforced concrete (RC) structures. For example, Almustafa et al [18,19] utilized ML methods to analyze the feasibility of predicting the maximum displacement of RC columns and FRP-strengthened RC panels under blast loads. Thai et al [20] employed a gradient-boosting machine learning (GBML) approach to predict local damage in RC panels under impact loads.…”

Section: Introductionmentioning

confidence: 99%

Prediction and Interpretation of Residual Bearing Capacity of Cfst Columns under Impact Loads Based Interpretable Stacking Fusion Modeling

Yang,

Zhang

2023

Buildings

View full text Add to dashboard Cite

The utilization of Concrete-filled steel Tubular (CFST) columns is increasingly widespread. However, the assessment of the residual bearing capacity of CFST columns currently relies mainly on costly and time-consuming experiments and numerical simulations. In this study, we propose a machine learning-based model for rapidly identifying the residual bearing capacity of CFST columns. The results demonstrate that the predictions of the proposed Stacking-KRXL model align well with the actual values, with most prediction errors falling within ±10%. The RSquared value of 0.97 significantly surpasses that of other methods. The stability and robustness of the model are analyzed. Additionally, the Shapley additive explanations method is applied for global and local interpretations, revealing positive or negative correlations between different parameters and the residual bearing capacity of CFST columns, mainly influenced by the concrete area in the core region.

show abstract

Machine learning model for predicting structural response of RC columns subjected to blast loading

Cited by 40 publications

References 17 publications

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

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

Prediction and Interpretation of Residual Bearing Capacity of Cfst Columns under Impact Loads Based Interpretable Stacking Fusion Modeling

Contact Info

Product

Resources

About