Prediction of concrete and FRC properties at high temperature using machine and deep learning: A review of recent advances and future perspectives

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 83, P. 108369 - 108369

Published: Dec. 29, 2023

Language: Английский

---

Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 408, P. 133752 - 133752

Published: Oct. 14, 2023

Language: Английский

---

Integrated behavioural analysis of FRP-confined circular columns using FEM and machine learning

Composites Part C Open Access, Journal Year: 2024, Volume and Issue: 13, P. 100444 - 100444

Published: Feb. 12, 2024

This study investigates the structural behaviour of double-skin columns, introducing novel – double filled tubular (DSDFT) which utilize dual steel tubes and concrete to enhance load-carrying capacity ductility beyond conventional hollow (DSHT) employing a combination finite element model (FEM) machine learning (ML) techniques. A total 48 columns (DSHT+DSDFT) were created examine impact various parameters, such as tube configurations, thickness fibre-reinforced polymer (FRP) layer, type FRP material, diameter, on columns. The results validated against experimental findings ensure their accuracy. Key highlight advantages DSDFT configuration. Compared DSHT exhibited remarkable 19.54% 101.21% increase in capacity, demonstrating improved load-bearing capabilities. Thicker layers enhanced up 15%, however at expense reduced axial strain. It is also observed that glass wrapping displayed 25% superior ultimate strain than aramid wrapping. Four different ML models examined predict with long short-term memory bidirectional LSTM emerging choices exhibiting exceptional predictive interdisciplinary approach offers valuable insights into designing optimizing confined column systems. sheds light both double-tube single-tube propelling advancements engineering practices for new constructions retrofitting. Further, it lays out blueprint maximizing performance under compression.

Language: Английский

---

Investigation of optimized machine learning models with PSO for forecasting the shear capacity of steel fiber-reinforced SCC beams with/out stirrups

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 83, P. 108455 - 108455

Published: Jan. 3, 2024

Language: Английский

---

Systems driven intelligent decision support methods for ship collision and grounding prevention: Present status, possible solutions, and challenges

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: unknown, P. 110489 - 110489

Published: Sept. 1, 2024

Language: Английский

---

Efficient Removal of Greenhouse Gases: Machine Learning-Assisted Exploration of Metal–Organic Framework Space

ACS Nano, Journal Year: 2024, Volume and Issue: unknown

Published: July 1, 2024

Global warming is a crisis that humanity must face together. With greenhouse gases (GHGs) as the main factor causing global warming, adoption of relevant processes to eliminate them essential. advantages high specific surface area, large pore volume, and tunable synthesis, metal–organic frameworks (MOFs) have attracted much attention in GHG storage, adsorption, separation, catalysis. However, pool MOFs expands rapidly with new syntheses discoveries, finding suitable MOF for particular application highly challenging. In this regard, high-throughput computational screening considered most effective research method number materials discover high-performance target MOFs. Typically, generates voluminous multidimensional data, which well suited machine learning (ML) training improve efficiency explore relationships between data depth. This Review summarizes general process common methods using ML screen field removal. It also addresses challenges faced by exploring space potential directions future development screening. aims enhance understanding integration various fields broaden ideas

Language: Английский

---

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

Structural Concrete, Journal Year: 2024, Volume and Issue: unknown

Published: June 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.

Language: Английский

---

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

Frontiers of Structural and Civil Engineering, Journal Year: 2024, Volume and Issue: 18(8), P. 1169 - 1194

Published: July 26, 2024

Language: Английский

---

Machine learning-driven web-post buckling resistance prediction for high-strength steel beams with elliptically-based web openings

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101749 - 101749

Published: Jan. 7, 2024

The use of periodical elliptically-based web (EBW) openings in high strength steel (HSS) beams has been increasingly popular recent years mainly because the strength-to-weight ratio and reduction floor height as a result allowing different utility services to pass through openings. However, these sections are susceptible web-post buckling (WPB) failure mode therefore it is imperative that an accurate design tool made available for prediction capacity. Therefore, present paper aims implement power various machine learning (ML) methods WPB capacity HSS with assess performance existing analytical model. For this purpose, numerical model developed validated aim conducting total 10,764 finite element models, considering S460, S690 S960 grades. This data employed train validate ML algorithms including Artificial Neural Networks (ANN), Support Vector Machine Regression (SVR) Gene Expression Programming (GEP). Finally, proposes new models resistance prediction. results discussed detail, they compared method. proposed based on predictions shown be powerful, reliable efficient tools

Language: Английский

---

Predicting fatigue slip and fatigue life of FRP rebar-concrete bonds using tree-based and theory-informed learning models

International Journal of Fatigue, Journal Year: 2025, Volume and Issue: 193, P. 108816 - 108816

Published: Jan. 12, 2025

Language: Английский

---