Machine learning prediction of structural response for FRP retrofitted RC slabs subjected to blast loading

Almustafa, Monjee K.; Nehdi, Moncef L.

doi:10.1016/j.engstruct.2021.112752

Cited by 35 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

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

show abstract

“…In addition, polyurea-woven glass fiber mesh composites and engineered cementitious composites were also reported as reinforcement materials for RC slabs [12,13]. Almustafa [14] investigated the practicality of using machine learning to predict the maximum displacement of fiber-reinforced polymer-strengthened RC slabs. There are a few relevant studies on large-sized RC slabs and large-charge explosion tests.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Response and Damage Characteristics of Large Reinforced Concrete Slabs under Explosion

Yao,

Li,

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

To investigate the damage characteristics of reinforced concrete (RC) buildings during explosive incidents, a large RC slab (4 m × 5 m × 0.15 m) was meticulously designed, fabricated, and subjected to explosion experiments, which were complemented by comprehensive numerical simulations. The dynamic response parameters of the RC slabs under 0.5–1 kg TNT explosions were tested using polyvinylidene fluoride (PVDF) pressure sensors, displacement sensors, and acceleration sensors. The damage morphologies under 5–40 kg TNT explosions were investigated using ANSYS/LS–DYNA 17.0 software. The results show that, with an increase in TNT charge, the RC slab gradually showed minor damage (5 kg), moderate damage (10–20 kg), heavy damage (25 kg), and complete destruction (30–40 kg). For the 20 kg TNT explosion condition, a 1020 mm × 760 mm explosion crater appeared on the top surface, which was in agreement with the 934 mm × 906 mm explosion crater obtained from the simulation. Based on the results, suitable P–I (pressure–impulse) curves for the 4 m × 5 m × 0.15 m RC slab were established. The results can provide a reference for damage assessments of large-sized buildings during explosion accidents.

show abstract

“…It is evident from some very recent research works in this field. A comprehensive historical dataset and an appropriate machine learning model is described beautifully in [20]. Our model adds some additional data through numerical experiment and tests the performance of a fully connected deep neural network for maximum displacement prediction application.…”

Section: Introductionmentioning

confidence: 99%

A New Deep Learning Accelerated Blast Loading Effect Analysis of FRP Retrofitted Concrete Slab

Padhi,

Bhandari,

Chakrabarti

et al. 2023

Proceedings of the 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering (COM

View full text Add to dashboard Cite

Sudden rapid release of energy in blast loading results in complex material behaviour in the surrounding. The study on these destructive events and its serious impact is only increasing day by day due to its geopolitical importance. Traditionally concrete structures have been used for many blast-resistant structures. It is well known that retrofitting reinforced concrete (RC) slabs with exterior fiber-reinforced polymer (FRP) improves blast resistance, reduces displacements and cracking, and helps to collect debris. Even with modern sophisticated computational tools there are still issues with accurate and efficient prediction of the results through numerical simulation. In this work we propose a machine learning assisted blast loading analysis model than can predict maximum displacement of the FRP retrofitted reinforced concrete (RC) slab subjected to blast loading from the standard input parameters including the features of the blast loading, reinforced concrete slab as well as FRP retrofitting. The dataset is collected from the literature which includes several experimental as well as numerical data. A deep learning model is trained with these data and its performance is tested for prediction of the maximum displacement. The model is seen to perform satisfactorily within acceptable engineering errors. Another advantage is that after training the prediction is extremely fast and can save a lot of time. Also, if the training sample includes variations of cases across several possible scenarios the machine learning can be quite robust. 2520COMPDYN 2023 9 th ECCOMAS Thematic Conference on Computational Methods in Structural Dynamics and Earthquake Engineering M. Papadrakakis, M. Fragiadakis (eds.

show abstract

Machine learning prediction of structural response for FRP retrofitted RC slabs subjected to blast loading

Cited by 35 publications

References 27 publications

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

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

Dynamic Response and Damage Characteristics of Large Reinforced Concrete Slabs under Explosion

A New Deep Learning Accelerated Blast Loading Effect Analysis of FRP Retrofitted Concrete Slab

Contact Info

Product

Resources

About