Nonlinear Load-Deflection Analysis of Steel Rebar-Reinforced Concrete Beams: Experimental, Theoretical and Machine Learning Analysis

Buildings, Год журнала: 2025, Номер 15(3), С. 432 - 432

Опубликована: Янв. 29, 2025

The integration of cutting-edge technologies into reinforced concrete (RC) design is reshaping the construction industry, enabling smarter and more sustainable solutions. Among these, machine learning (ML), a subset artificial intelligence (AI), has emerged as transformative tool, offering unprecedented accuracy in prediction optimization. This study investigated flexural behavior steel rebar RC beams, focusing on varying compressive strengths via theoretical, experimental ML analysis. Nine beams with low (SC20), moderate (SC30) high (SC40) strength, measuring 150 × 200 1100 mm, were produced subjected to three-point bending tests. An average error less than 5% was obtained between theoretical calculations experiments ultimate load-carrying capacity beams. By combining ML-powered models, this research bridges gap insights advanced analytical techniques. A groundbreaking aspect work deployment 18 regression models using Python’s PyCaret library predict deflection values an impressive 95%. Notably, K Neighbors Regressor Gradient Boosting demonstrated exceptional performance, providing fast, consistent highly accurate predictions, making them invaluable tool for structural engineers. results revealed distinct failure mechanisms: SC30 SC40 exhibited ductile cracking, while SC20 showed brittle shear cracking sudden collapse.

Язык: Английский

---

Analysis of compressive strength of nanostructure pyrolytic carbon enhanced nanocomposite mortar and forecasting using machine learning models

Matéria (Rio de Janeiro), Год журнала: 2025, Номер 30

Опубликована: Янв. 1, 2025

ABSTRACT Utilization of Nano-structure pyrolytic carbon (NSPC) particles holds significant potential in developing nanocomposites. Consequently, compressive strength is a crucial characteristic which stipulates the efficiency NSPC cementitious composites. Nevertheless, predicting this nanocomposite challenge due to distorted responses and complex structures. The main novelty research predict developed nanocomposite. Therefore, machine learning (ML) model first-time proposed for mortar incorporated with various dosages particles. In addition, bound water determined understand hydration process. This work highlights comprehensive comparison six ML algorithms, such as linear regression, random forest extra trees, gradient boost regressor, extreme boost, LightGBM, prediction accuracy Furthermore, it evaluated through multiple statistical error analysis. Seventeen parameters were considered input variables mortar. According coefficient determination analysis, regressor attained highest R2 value 0.87, while trees achieved values 0.86 0.85, respectively. low mean absolute 3.229 was earned boost. Overall, reliable performed better mapping interplay between strength.

Язык: Английский

---

Machine Learning-Driven Flexural Performance Prediction and Experimental Investigation of Glass Fiber-Reinforced Polymer Bar-Reinforced Concrete Beams

Polymers, Год журнала: 2025, Номер 17(6), С. 713 - 713

Опубликована: Март 7, 2025

This study experimentally examines the flexural performance, crack formation patterns, and failure mechanisms of glass fiber-reinforced polymer (GFRP) bar-reinforced concrete beams with varying compressive strengths (low, moderate, high), addressing a gap in current literature. Furthermore, it employs an innovative machine learning approach to enhance analysis. Nine RC reinforced GFRP bars, having low (CC20), moderate (CC30), high (CC40), each measuring 150 × 200 1100 mm, were fabricated tested under three-point bending conditions. Through integration tests learning-based prediction models, this connects experimental findings advanced analytical approaches. One key innovations is use eighteen ML regression models implemented Python’s PyCaret library, achieving impressive average accuracy 91.5% for beam deflection values. In particular, Ada Boost Regressor Gradient Boosting performed exceptionally well on beams, providing highest number consistent highly accurate predictions, making them very useful tools ultimate load-carrying capacity/deflection predictions. The outcomes identified clear mechanisms: CC20, CC30, CC40 typically developed single, large at midpoint. Although capacity bar improved higher strength, CC20 CC30 displayed more ductile behavior than beams. was determined be approximately 74% that Regardless strength class, absence shear cracks prevention sudden are considered major advantages using reinforcement.

Язык: Английский

---

Interpretable machine learning model for performance characterization of lightweight concrete and composition design

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112266 - 112266

Опубликована: Март 1, 2025

Язык: Английский

---

Investigating horn power and impact of sonication on TiO2@cotton composites with machine learning and computer vision

Measurement, Год журнала: 2025, Номер unknown, С. 117424 - 117424

Опубликована: Март 1, 2025

Язык: Английский

---

Data-driven study on the mechanical properties of strain-hardening cementitious composites using algorithm-enhanced interpretable machine learning models and interactive interface development

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112466 - 112466

Опубликована: Апрель 1, 2025

Язык: Английский

---

The anticipation of compressive strength of geopolymer mortars with tree-based machine learning models: effect of training-testing ratios

Asian Journal of Civil Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 17, 2025

Язык: Английский

---

Development and optimization of geopolymer concrete with compressive strength prediction using particle swarm-optimized extreme gradient boosting

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 113149 - 113149

Опубликована: Апрель 1, 2025

Язык: Английский

---

A methodological study of slump prediction and optimisation of radioprotective serpentine concrete

Construction and Building Materials, Год журнала: 2024, Номер 451, С. 138706 - 138706

Опубликована: Окт. 21, 2024

Язык: Английский

---