Sustainable foam glass property prediction using machine learning: A comprehensive comparison of predictive methods and techniques

Results in Engineering, Год журнала: 2025, Номер unknown, С. 104089 - 104089

Опубликована: Янв. 1, 2025

Язык: Английский

---

Identification of Wind Load Exerted on the Jacket Wind Turbines from Optimally Placed Strain Gauges Using C-Optimal Design and Mathematical Model Reduction

Journal of Marine Science and Engineering, Год журнала: 2024, Номер 12(4), С. 563 - 563

Опубликована: Март 27, 2024

Wind turbine towers experience complex dynamic loads during actual operation, and these are difficult to accurately predict in advance, which may lead inaccurate structural fatigue strength assessment the design phase, thereby posing safety risks wind tower. However, online monitoring of has become possible with development load identification technology. Therefore, an method for exerted on was developed this study estimate using strain, can be used loads. The tower were simplified into six equivalent concentrated forces topside tower, initial mathematical model established based theory frequency domain, many candidate sensor locations directions considered. Then, expressed as a linear system equations. A numerical example verify accuracy stability identification, results indicate that combined Moore–Penrose inverse algorithm provide stable accurate reconstruction results. uses too sensors, is not conducive engineering applications. D-optimal C-optimal methods reduce dimension determine location direction strain gauges. adopts direct optimisation search strategy, while indirect strategy. four examples show dimensionality reduction leads high accuracy, provides more robust Moreover, damage calculated closely approximates derived from finite element simulation load, relative error within 6%. offers pragmatic solution acquisition

Язык: Английский

---

Ensemble machine learning models for predicting concrete compressive strength incorporating various sand types

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(4)

Опубликована: Март 14, 2025

Язык: Английский

---

ANN‐based analysis of the effect of SCM on recycled aggregate concrete

Structural Concrete, Год журнала: 2024, Номер unknown

Опубликована: Июль 7, 2024

Abstract Rising environmental awareness has prompted in‐depth studies on how the concrete industry affects environment. Using recycled aggregates (RCAs) and supplementary cementitious materials (SCMs) in manufacturing provides advantages for sustainability. However, broader chemical composition of SCMs inferior qualities RCAs compared with natural (NAs) often lead to a decrease mechanical strength. The difficulty lies foreseeing inclusion will affect compressive artificial neural network (ANN) approach presented herein can precisely forecast aggregate (RAC) strength, even when incorporates SCMs. analysis employing connection weight (CWA) determines input variables influence Results indicate silica fume contributes most followed by cement content, modulus, fine dosage, coarse aggregate. Additionally, amount water utilized, water/cement ratio, presence RCA are all detrimental adverse effect materials' alumina modulus be attributed increased demand during their reaction. Performance metrics final ANN model testing data subset include R 2 = 0.94, RMSE 3.11, utilizing 834 observations after outlier treatment training validation purposes. In summary, ANN‐based demonstrates its efficacy predicting strength incorporating RCAs, shedding light influential factors performance.

Язык: Английский

---

Integrating PCA and XGBoost for Predicting UACLC of Steel-Reinforced Concrete-Filled Square Steel Tubular Columns at Elevated Temperatures

Case Studies in Construction Materials, Год журнала: 2025, Номер unknown, С. e04456 - e04456

Опубликована: Фев. 1, 2025

Язык: Английский

---

A Systematic Review on Utilizing Artificial Intelligence in Lateral Resisting Systems of Buildings

Archives of Computational Methods in Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 27, 2025

Язык: Английский

---

Optimizing sustainable blended concrete mixes using deep learning and multi-objective optimization

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

Опубликована: Май 10, 2025

Язык: Английский

---

Predictive modeling of shear strength in fiber-reinforced cementitious matrix-strengthened RC beams using machine learning

Asian Journal of Civil Engineering, Год журнала: 2024, Номер 25(4), С. 3251 - 3261

Опубликована: Фев. 5, 2024

Язык: Английский

---

Concrete aging factor prediction using machine learning

Materials Today Communications, Год журнала: 2024, Номер 40, С. 109527 - 109527

Опубликована: Июнь 13, 2024

Язык: Английский

---

Enhancing the mechanical properties’ performances coconut fiber and CDW composite in paver block: multiple AI techniques with a Performance analysis

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

Опубликована: Дек. 30, 2024

The present research incorporates five AI methods to enhance and forecast the characteristics of building envelopes. In this study, Response Surface Methodology (RSM), Support Vector Machine (SVM), Gradient Boosting (GB), Artificial Neural Networks (ANN), Random Forest (RF) machine learning method for optimization predicting mechanical properties natural fiber addition incorporated with construction demolition waste (CDW) as replacement Fine Aggregate in Paver blocks. factors considered were cement content, fine aggregate, CDW, coconut fibre, while resulting measure was machinal paver Furthermore, techniques precision extensively evaluated. outcomes from both training testing phases demonstrated strong predictive power RSM, SVM, GB, ANN, RF a criterion used Root Mean square error (RMSE), (MSE), Absolute Error (MAE) correlation coefficient (R). Moreover, results that GB ANN provide enhanced performance comparison SVM determining factors.

Язык: Английский

---