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

Yang, Guangchao; Yang, Ran; Zhang, Jian

doi:10.3390/buildings13112783

Cited by 2 publications

(1 citation statement)

References 33 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Projects that were "frozen" during the pandemic are being resumed, and new ones emerge that require serious material resources [1]. The use of costeffective building materials, widely used in various construction infrastructure facilities, including vibrocentrifuged concrete, is coming to the fore [2,3].…”

Section: Introductionmentioning

confidence: 99%

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods

Beskopylny,

Stel’makh,

Shcherban’

et al. 2024

Buildings

View full text Add to dashboard Cite

The determination of mechanical properties for different building materials is a highly relevant and practical field of application for machine learning (ML) techniques within the construction sector. When working with vibrocentrifuged concrete products and structures, it is crucial to consider factors related to the impact of aggressive environments. Artificial intelligence methods can enhance the prediction of vibrocentrifuged concrete properties through the use of specialized machine learning algorithms for materials’ strength determination. The aim of this article is to establish and evaluate machine learning algorithms, specifically Linear Regression (LR), Support Vector Regression (SVR), Random Forest (RF), CatBoost (CB), for the prediction of compressive strength in vibrocentrifuged concrete under diverse aggressive operational conditions. This is achieved by utilizing a comprehensive database of experimental values obtained in laboratory settings. The following metrics were used to analyze the accuracy of the constructed regression models: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root-Mean-Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The average MAPE in the range from 2% (RF, CB) to 7% (LR, SVR) allowed us to draw conclusions about the possibility of using “smart” algorithms in the development of compositions and quality control of vibrocentrifuged concrete, which ultimately entails the improvement and acceleration of the construction and building materials manufacture. The best model, CatBoost, showed MAE = 0.89, MSE = 4.37, RMSE = 2.09, MAPE = 2% and R2 = 0.94.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods

Beskopylny,

Stel’makh,

Shcherban’

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

Concrete Breaking Strength Prediction Using Machine Learning

Dr. R. Premsudha,

Dr. S. Kapilan,

G. Viswanathan

et al. 2024

IJARSCT

View full text Add to dashboard Cite

When it comes to estimating, classifying, and forecasting material strength based on changing material parameters, machine learning (ML) techniques have shown to be dependable methodologies. It is found that choosing the right machine learning technique depends on the characteristics of the problem and the available data. Therefore, fifteen different machine learning techniques were used to a specific dataset of concrete compressive strength in order to assess the accuracy of ML models to predict concrete compressive strength. Due to its excellent performance while dealing with continuous target variables and nonlinear interactions among the features and the target, the Support Vector Regressor (SVR) had the greatest prediction accuracy (88.18%) of all the ML methods employed. To guarantee the structural integrity of building projects, it is essential to predict the breaking strength of concrete. The goal of this project is to create a machine learning model that can forecast concrete's breaking strength depending on the mix's composition and curing circumstances. A dataset was created that included details regarding concrete samples, such as mix ratios, curing temperatures, curing times, and breaking strengths. recise estimation of concrete's compressive strength is crucial for the advancement and construction. A bibliometric analysis of the pertinent literature published in was conducted in order to comprehend the state of research in the field of concrete compressive strength prediction. The previous ten years have seen the first research in this sector. The database consisted of 31,35 journal articles published between 2012 and 2021 in the Web of Science core database. The knowledge map was created using Cite Space 6.1R2, a visualisation tool, to analyse the field at a macro level in terms of hotspot distribution, spatial and temporal distribution, and evolutionary trends, respectively. Next, we become specific and separate the prediction techniques for concrete compressive strength into two groups

show abstract

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

Cited by 2 publications

References 33 publications

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods

Concrete Breaking Strength Prediction Using Machine Learning

Contact Info

Product

Resources

About