Prediction of ultimate condition of FRP-confined recycled aggregate concrete using a hybrid boosting model enriched with tabular generative adversarial networks

Zhao, Xinyu; Chen, Jinxin; Chen, G.M.; Xu, Jinjun; Zhang, Wenhua

doi:10.1016/j.tws.2022.110318

Cited by 41 publications

(14 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By the same token, RA properties significantly affect the mechanical and chemical properties of concrete. Studies have exhibited that the mechanical strength of RAC is lower than that of virgin aggregates 10 , primarily due to the adhered old cement mortar 11 , 12 . The lower performance of RAC, as opposed to conventional concrete, is a major issue in recycling construction and demolition waste in the production of RAC products.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive quantitative bottom-up analysis of fiber-reinforced recycled-aggregate concrete behavior

Hosseinzadeh

Dehestani

Samadvand³

2023

Sci Rep

View full text Add to dashboard Cite

This study provides a more profound understanding of the influence of the phases of fiber-reinforced recycled-aggregate concrete (FRRAC), on its elastic properties, in particular Young’s modulus and Poisson’s ratio. Multi-scale modeling analyses of mortar and FRRAC were conducted to assess the effect of variations in the fiber content, fiber elastic modulus, RA content, and water-to-cement ratio (w/c) on the elastic properties at each scale. Thus, the analytic Mori–Tanaka (MT) homogenization algorithm developed in Python programming language and the three-dimensional finite element (FE) homogenization scheme were applied to evaluate the elastic properties of FRRAC. As such, different fiber types including steel, basalt, glass, and propylene, at a volume fraction range of 0–2%, along with the variations in fiber elastic modulus, and different RA replacement levels ranging from 0 to 100% were incorporated in the modeling process at different w/c ratio. Based on the results, the Poisson’s ratio of steel FRRAC in the MT approach surges with increasing fiber content. Furthermore, the elastic modulus of FRRAC is highly susceptible to an increase in Young’s modulus of polypropylene fiber, among other fiber types. The elastic modulus of concrete experiences a sharp decrease with increasing w/c for all fiber types in both FE and MT approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

A comprehensive quantitative bottom-up analysis of fiber-reinforced recycled-aggregate concrete behavior

Hosseinzadeh

Dehestani

Samadvand³

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…RCA has a range of positive benefits, their properties have been found to have a large converse impact on the overall durability of concrete, causing a significant increase in creep and shrinkage deformations compared to CC. Thus, it is critical to investigate the effect of varying substitution levels of RCA may have in conjunction with other prime concrete properties such as cement content, w/c ratio, density, water absorption, and recycled aggregate size 1–17 . Significantly minimal information is also found in the literature for RAC prediction models, thereby providing ambiguity regarding the optimal concrete properties required to sustain recycled aggregates in concrete.…”

Section: Introductionmentioning

confidence: 99%

“…It can be noted from the literature that varying levels of RCA substitution can have a significant influence on the overall mechanical and durability components of the concrete mix. By further elaboration on these two components, the study of creep and shrinkage can be further investigated 2–11 . Lye et al 18 conducted several experiments analysing the creep and shrinkage variations experienced by CC replaced with varying substitution levels of RCA.…”

Section: Introductionmentioning

confidence: 99%

Development of creep and shrinkage prediction models for recycled aggregate concrete

Rabadia,

Aslani

2023

Structural Concrete

View full text Add to dashboard Cite

Studies have found utilization of recycled aggregate concrete (RAC) for engineering use to be environmentally favorable by preserving natural resources and limiting waste reduction. However, the use of RAC has not been effectively integrated in the industry due to limited research overlying the critical areas of its creep and shrinkage behavior. Hence, this study aims to investigate the natural aggregate concrete creep and shrinkage prediction models and perform recycled concrete aggregate (RCA) replacement level and water absorption modifications to illustrate the presence and behavior of RAC. Comparative analysis was undertaken by establishing comprehensive conventional concrete and RAC experimental databases and investigating several creep and shrinkage prediction models including, ACI 209R‐92, Bazant–Baweja B3, CEB MC 90, GL 2000, MC 2010, and JSCE 2010. The Bazant–Baweja B3 model was found to present the most optimal results by evaluating each conventional model against the RAC databases and performing regression analysis. Hence, the Bazant–Baweja B3 natural aggregate concrete models for creep and shrinkage were then effectively modified to illustrate the presence of RCA replacement level and water absorption. The adjusted models were verified with a set of experimental databases which successfully presented favourable results with coefficient of correlation factors increased from an average of 0.76 to 0.9.

show abstract

“…Machine Learning (ML) methods are currently used to predict structures’ damage states [ 6 , 7 ]. For example, Cardellicchio et al proposed a methodology to interpret defect detection results using Class Activation Maps and Explainable Artificial Intelligence techniques applied to Reinforced Concrete (RC) bridges in Southern Italy [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Rapid Post-Earthquake Damage Detection of RC Resisting-Moment Frame Buildings

Alcantara

Saito

2023

Sensors

View full text Add to dashboard Cite

This study proposes a methodology to predict the damage condition of Reinforced Concrete (RC) resisting-moment frame buildings using Machine Learning (ML) methods. Structural members of six hundred RC buildings with varying stories and spans in X and Y directions were designed using the virtual work method. Sixty thousand time-history analyses using ten spectrum-matched earthquake records and ten scaling factors were carried out to cover the structures’ elastic and inelastic behavior. The buildings and earthquake records were split randomly into training data and testing data to predict the damage condition of new ones. In order to reduce bias, the random selection of buildings and earthquake records was carried out several times, and the mean and standard deviation of the accuracy were obtained. Moreover, 27 Intensity Measures (IM) based on acceleration, velocity, or displacement from the ground and roof sensor responses were used to capture the building’s behavior features. The ML methods used IMs, the number of stories, and the number of spans in X and Y directions as input data and the maximum inter-story drift ratio as output data. Finally, seven Machine Learning (ML) methods were trained to predict the damage condition of buildings, finding the best set of training buildings, IMs, and ML methods for the highest prediction accuracy.

show abstract

Prediction of ultimate condition of FRP-confined recycled aggregate concrete using a hybrid boosting model enriched with tabular generative adversarial networks

Cited by 41 publications

References 70 publications

A comprehensive quantitative bottom-up analysis of fiber-reinforced recycled-aggregate concrete behavior

A comprehensive quantitative bottom-up analysis of fiber-reinforced recycled-aggregate concrete behavior

Development of creep and shrinkage prediction models for recycled aggregate concrete

Machine Learning-Based Rapid Post-Earthquake Damage Detection of RC Resisting-Moment Frame Buildings

Contact Info

Product

Resources

About