Concrete-to-concrete interface shear strength prediction based on explainable extreme gradient boosting approach

Xu, Ji‐Gang; Chen, Shizhi; Xu, Weijie; Shen, Zi-Sen

doi:10.1016/j.conbuildmat.2021.125088

Cited by 38 publications

(7 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developed ML‐models for post‐earthquake bridge tagging are “black‐box” models, which directly give the tagging results from the inputs. In order to understand how the input features can affect the tagging results, the SHapley Additive exPlanations (SHAP) technique 52–54 is adopted herein to explain the XGBoost model. The SHAP comes from the idea of game‐theory, which simplifies the output as the linear addition of the inputs, therefore, the SHAP can quantitatively evaluate the contribution of each input feature to the outputs.…”

Section: Results Of the Proposed Ml‐based Tagging Approachmentioning

confidence: 99%

Data‐driven rapid damage evaluation for life‐cycle seismic assessment of regional reinforced concrete bridges

Feng

Mangalathu³

et al. 2022

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

Rapid and accurate post‐earthquake damage evaluation of regional reinforced concrete (RC) bridges is a key issue for assessing the seismic resilience of cities and communities. Especially, RC bridges are susceptible to the aggressive environment, which can induce time‐dependent aging effects such as corrosion, and thus, it should be considered in the assessment. This paper presents an approach for regional seismic performance assessment of RC bridges in a life‐cycle context based on machine‐learning techniques. The life‐cycle seismic demand and capacity of the bridges are, firstly, obtained by the elaborated numerical model, which includes the deterioration induced by the aging corrosion effect. Then, the tagging‐based damage state (green, yellow, or red) is easily obtained by comparing the pairs of demand and capacity through machine learning. Four hundred and eighty bridge models are generated to develop the machine‐learning models and the performance of the machine learning models is evaluated. Results show that the extreme gradient boosting (XGBoost) model has the best performance, which has an accuracy of 81% in predicting the damage states. The proposed approach is demonstrated with a single bridge example and bridges in a sample region. It is shown that the machine learning model can accurately predict the post‐earthquake damage states of the single bridge, and it can also rapidly assess the damage states of the bridges in the sample region. Approximately 30% bridges in the sample region will experience damage states shift after 100 years, which highlights the importance of considering the aging effects on the post‐earthquake damage assessment of bridges.

show abstract

Section: Results Of the Proposed Ml‐based Tagging Approachmentioning

confidence: 99%

Data‐driven rapid damage evaluation for life‐cycle seismic assessment of regional reinforced concrete bridges

Feng

Mangalathu³

et al. 2022

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

show abstract

“…ML models for classification have proven valuable for damage detection in structures, as evidenced by studies on bridges [35][36][37][38], beam/column members [39][40][41], plate/panel members [42,43], and joints [44,45]. Regression models have applications in various predictive tasks, addressing shear resistance in beams [46,47], slabs [48], joints [49,50], axial strength of concrete columns [51], steel columns [52], concrete-filled steel tube (CFT) columns [53], deflection of concrete beams [54], and data-driven optimization for torsion design of CFRP-CFST [55].…”

Section: Literature Reviewmentioning

confidence: 99%

Augmented Data-Driven Machine Learning for Digital Twin of Stud Shear Connections

Roh,

Vu,

Jeon

et al. 2024

Buildings

View full text Add to dashboard Cite

Existing design codes for predicting the strength of stud shear connections in composite structures are limited when adapting to constant changes in materials and configurations. Machine learning (ML) models for predicting shear connection are often constrained by the number of input variables, resembling conventional design equations. Moreover, these models tend to overlook considerations beyond those directly comprising the connection. In addition, the data used in ML are often biased and limited in quantity. This study proposes a model using AutoML to automate and optimize the process for predicting the ultimate strength and deformation capacity of shear connections. The proposed model leverages a comprehensive dataset derived from experimental studies and finite element analyses, offering an advanced data-driven solution to overcome the limitations of traditional empirical equations. A digital twin model for the static design of pushout specimens was defined to replace existing empirical design codes. The digital twin model incorporates predictions of the geometry model, ultimate strength, and slip as input parameters and provides criteria for evaluating the limit state through a bilinear load–slip curve. This study advances predictive methodologies in structural engineering by emphasizing the importance of ML in addressing the dynamic and multifaceted nature of shear connection behaviors.

show abstract

“…Machine learning techniques have been widely used to predict structural status in recent years. Compared to traditional models, machine learning is a data-driven model that takes into account multiple parameters and is adaptive, and the accuracy of the model will improve as the size of the data increases in the future [20][21][22] Naderpour et al used decision tree and neural networks to predict the failure modes of reinforced concrete columns [23]. Zhang et al used six machine learning methods, neural networks, support vector machines, decision tree, gradient boosting decision tree, random forests, and extreme gradient boosting to predict the bond strength of FRP-concrete interfaces [24].…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Model for Predicting the Compressive Strengths of GFRP-Confined Reinforced Concrete Columns

Yang

2023

Buildings

View full text Add to dashboard Cite

This paper focuses on the compressive strength of Glass fiber reinforced polymer (GFRP)-confined reinforced concrete columns. Data from 114 sets of GFRP-confined reinforced concrete columns were collected to evaluate the researchers’ and proposed model. A data-driven machine learning model was used to model the compressive strength of the GFRP-confined reinforced concrete columns and investigate the importance and sensitivity of the parameters affecting the compressive strength. The results show that the researchers’ model facilitates the study of the compressive strength of confined columns but suffers from a large coefficient of variation and too high or conservative estimation of compressive strength. The back propagation (BP) neural network has the best accuracy and robustness in predicting the compressive strength of the confined columns, with the coefficient of variation of only 14.22%, and the goodness of fit for both the training and testing sets above 0.9. The parameters that have an enormous influence on compressive strength are the concrete strength and FRP thickness, and all the parameters, except the fracture strain of FRP, are positively or inversely related to the compressive strength.

show abstract

Concrete-to-concrete interface shear strength prediction based on explainable extreme gradient boosting approach

Cited by 38 publications

References 69 publications

Data‐driven rapid damage evaluation for life‐cycle seismic assessment of regional reinforced concrete bridges

Data‐driven rapid damage evaluation for life‐cycle seismic assessment of regional reinforced concrete bridges

Augmented Data-Driven Machine Learning for Digital Twin of Stud Shear Connections

Data-Driven Model for Predicting the Compressive Strengths of GFRP-Confined Reinforced Concrete Columns

Contact Info

Product

Resources

About