Numerical and machine learning modeling of GFRP confined concrete-steel hollow elliptical columns

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 12, 2024

This article investigates the behavior of hybrid FRP Concrete-Steel columns with an elliptical cross section. The investigation was carried out by gathering information through literature and conducting a parametric study, which resulted in 116 data points. Moreover, multiple machine learning predictive models were developed to accurately estimate confined ultimate strain load concrete at rupture tube. Decision Tree (DT), Random Forest (RF), Adaptive Boosting (ADAB), Categorical (CATB), eXtreme Gradient (XGB) techniques utilized for proposed models. Finally, these visually quantitatively verified evaluated. It concluded that CATB XGB are standout models, offering high accuracy strong generalization capabilities. model is slightly superior due its consistently lower error rates during testing, indicating it best this dataset when considering both robustness against overfitting.

Язык: Английский

---

Nonlinear finite element and machine learning modeling of tubed reinforced concrete columns under eccentric axial compression loading

Alexandria Engineering Journal, Год журнала: 2024, Номер 92, С. 380 - 416

Опубликована: Март 2, 2024

There is still insufficient data on the behavior of tubed-reinforced concrete columns (TRCCs) under eccentric compression. Thus, this research work comprehensively examines compression TRCCs using nonlinear finite element modeling and machine learning (ML). To do this, numerical simulation parametric analysis based existing investigations were conducted. In addition to 22 specimens with limited test variables, additional 188 developed cover a wide range parameters, including load eccentricity, transverse reinforcement spacing, columns' slenderness ratio, yield strength steel, outer steel tube diameter. Additionally, six ML models created estimate ultimate results. The results indicated that increasing diameter, reducing spacing enhanced load-carrying capacity columns. Gaussian process regression model demonstrated superior performance metrics in comparison other models, highest R2 values (0.998613 training 0.99823 testing stages) lowest root mean square error (0.007213 0.008471 stages). save money, time, resources compared laboratory testing, an online-based prediction program finally presented predict load.

Язык: Английский

---

Prediction of compressive strength of high-volume fly ash self-compacting concrete with silica fume using machine learning techniques

Construction and Building Materials, Год журнала: 2024, Номер 438, С. 136933 - 136933

Опубликована: Июнь 15, 2024

Язык: Английский

---

Modelling the mechanical properties of concrete produced with polycarbonate waste ash by machine learning

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Май 21, 2024

Abstract India’s cement industry is the second largest in world, generating 6.9% of global output. Polycarbonate waste ash a major problem India and around globe. Approximately 370,000 tons scientific are generated annually from fitness care facilities India. helps reduce environmental burden associated with disposal decreases need for new raw materials. The primary variable this study quantity polycarbonate (5, 10, 15, 20 25% weight cement), partial replacement cement, water-cement ratio aggregates. mechanical properties, such as compressive strength, split tensile strength flexural test results, mixtures were superior at 7, 14 28 days compared to those control mix. water absorption rate less than that standard concrete. Compared conventional concrete, concrete undergo minimal loss under acid curing conditions. utilized construction pollution improve economy. This further simulated characteristics made using least absolute shrinkage selection operator regression decision trees. Cement, waste, slump, absorption, main components considered input variables. suggested tree model was successful unparalleled predictive accuracy across important metrics. Its outstanding ability (R 2 = 0.879403), 0.91197), 0.853683) confirmed method preferred choice these predictions.

Язык: Английский

---

Prediction of mechanical properties of high‐performance concrete and ultrahigh‐performance concrete using soft computing techniques: A critical review

Structural Concrete, Год журнала: 2024, Номер unknown

Опубликована: Май 23, 2024

Abstract A cement‐based material that meets the general goals of mechanical properties, workability, and durability as well ever‐increasing demands environmental sustainability is produced by varying type quantity individual constituents in high‐performance concrete (HPC) ultrahigh‐performance (UHPC). Expensive time‐consuming laboratory experiments can be used to estimate properties mixtures elements. As an alternative, these attributes approximated means predictive models created through application artificial intelligence (AI) methodologies. AI approaches are among most effective ways solve engineering problems due their capacity for pattern recognition knowledge processing. Machine learning (ML) deep (DL) a subfield gaining popularity across many scientific domains result its benefits over statistical experimental models. These include, but not limited to, better accuracy, faster performance, greater responsiveness complex environments, lower economic costs. In order assess critical features literature, comprehensive review ML DL applications HPC UHPC was conducted this study. This paper offers thorough explanation fundamental terms ideas algorithms frequently predict UHPC. Engineers researchers working with construction materials will find useful helping them choose accurate appropriate methods needs.

Язык: Английский

---

Machine learning and nonlinear finite element analysis of fiber‐reinforced polymer‐confined concrete‐steel double‐skin tubular columns under axial compression

Structural Concrete, Год журнала: 2024, Номер unknown

Опубликована: Июнь 21, 2024

Abstract Fiber‐reinforced polymer (FRP)‐confined double‐skin tubular columns (DSTCs) are an innovative type of hybrid that consist outer tube made FRP, inner circular steel tube, and a concrete core sandwiched between them. Available literature focuses on hollow DSTCs with limited research tubes filled concrete. Overall, have many applications, highlighting the importance studying effects filling strength composite system. To address this gap, finite element models (FEMs) both traditional machine learning (ML) techniques were used to develop accurate for predicting load‐bearing capacity confined ultimate strain under axial loads. A comprehensive database 60 experimental tests 45 FEMs simulations was analyzed, five parameters selected as input variables ML‐based models. New like gradient boosting (GB), random forest (RF), convolutional neural networks, long short‐term memory compared established algorithms multiple linear regression, support vector regression (SVR), empirical mode decomposition (EMD)‐SVR. Regression error characteristics curve, Shapley Additive Explanation analysis, statistical metrics assess performance these using containing 105 test results cover range variables. While EMD‐SVR GB perform well strain, suggested EMD‐SVR, GB, RF show superior predictive accuracy load. be more precise, load prediction, obtain values 0.99, 0.989, 0.960, respectively. The at 0.690 However, design engineers by “black‐box” nature ML. In order solve this, study presents open‐source GUI based which gives ability precisely estimate various conditions, enabling them make well‐informed decisions about mix proportion.

Язык: Английский

---

Proposed numerical and machine learning models for fiber-reinforced polymer concrete-steel hollow and solid elliptical columns

Frontiers of Structural and Civil Engineering, Год журнала: 2024, Номер 18(8), С. 1169 - 1194

Опубликована: Июль 26, 2024

Язык: Английский

---

Analyzing the influence of manufactured sand and fly ash on concrete strength through experimental and machine learning methods

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 10, 2025

Язык: Английский

---

Compressive strength prediction models for concrete containing nano materials and exposed to elevated temperatures

Results in Engineering, Год журнала: 2025, Номер unknown, С. 103975 - 103975

Опубликована: Янв. 1, 2025

Язык: Английский

---

Machine learning for the prediction of the axial load‐carrying capacity of FRP reinforced hollow concrete column

Structural Concrete, Год журнала: 2025, Номер unknown

Опубликована: Март 4, 2025

Abstract Fiber reinforced polymer (FRP) has emerged as a significant advancement in construction, with design provisions outlined by codes such GB/T 30022‐2013, CSA S806‐12 (R2017), and ACI 440:2015. While the use of FRP bars alternatives to conventional reinforcement columns been extensively studied, their application hollow concrete (HCCs) remains underexplored. This study investigates behavior FRP‐reinforced HCCs using advanced machine learning (ML) models, focusing on prediction two critical outputs: first peak load (Y1) failure (Y2), based eight input parameters. Models evaluated include extreme gradient boosting (XGB), light (LGB), categorical (CGB). A rigorous comparative analysis demonstrated that all models achieved high predictive accuracy, deviations within ±10% actual results, validating reliability. Among CGB exhibited superior generalization robustness, emerging most reliable predictor for HCC behavior. To enhance practicality, user‐friendly graphical user interface was developed allow engineers parameters instantly obtain predictions Y1 Y2. not only advances understanding but also bridges gap between computational real‐world applications, contributing robust tool structural engineering design.

Язык: Английский

---