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

---

Deep learning-based modelling of polyvinyl chloride tube-confined concrete columns under different load eccentricities

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 145, С. 110217 - 110217

Опубликована: Фев. 13, 2025

Язык: Английский

---

Hybrid machine learning models for predicting compressive strength of self-compacting concrete: an integration of ANFIS and Metaheuristic algorithm

Nondestructive Testing And Evaluation, Год журнала: 2025, Номер unknown, С. 1 - 33

Опубликована: Март 25, 2025

Self-compacting concrete (SCC) has become increasingly popular due to its superior workability, segregation resistance, and compressive strength. As the traditional methods for strength prediction are costly time-intensive, this study explores machine learning (ML) techniques as efficient alternatives SCC prediction. Three state-of-the-art hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) models, optimised using Firefly Algorithm (FA), Particle Swarm Optimization (PSO) Genetic (GA). For purpose, a robust dataset of 366 instances 7 input parameters is taken from literature. After data analysis pre-processing, hyperparameters models tuned best-fit model tested on unforeseen data. ANFIS-FF stands out best-performing (RTR2 = 0.945 RTS2 0.9395) in both training testing phases, closely followed by ANFIS-GA. All outperform ANFIS model, outlining significance hybridisation, however, ANFIS-PSO lags behind other two models. The highlights importance integrating with metaheuristic algorithms tackling complex engineering problems like design optimal mix design, minimising material waste ensuring cost-effectiveness. It serves benchmark future research comparing hybridisation starting point ANFIS.

Язык: Английский

---

Optimized machine learning models for predicting the tensile strength of high-performance concrete

Journal of Structural Integrity and Maintenance, Год журнала: 2025, Номер 10(1)

Опубликована: Янв. 2, 2025

Язык: Английский

---

Leveraging ML for predicting UCS of soil stabilised with one-part alkali-activated binder

Proceedings of the Institution of Civil Engineers - Ground Improvement, Год журнала: 2025, Номер unknown, С. 1 - 11

Опубликована: Апрель 16, 2025

The transition to sustainable construction materials has driven interest in alternatives Portland cement. Soil stabilisation with alkali-activated binders is a promising approach, yet its widespread application requires reliable predictive tools for assessing unconfined compressive strength (UCS). This study explores the use of machine learning algorithms predict UCS soil stabilised one-part binder. An experimental data set was compiled train and validate multiple models, including random forests, artificial neural networks, support vector machines. Despite set’s limited size, models demonstrated strong accuracy, forest achieving an R 2 exceeding 0.80. Sensitivity analysis revealed that water content were most influential parameters, aligning established geotechnical principles. These findings highlight potential as tool optimising techniques. By enhancing capabilities, this approach supports more efficient material selection, reducing reliance on extensive laboratory testing. underscores value integrating data-driven methods into engineering advance high-performance treatment solutions.

Язык: Английский

---

Active learning-based regional seismic risk assessment of high-speed railway bridges

Advanced Engineering Informatics, Год журнала: 2025, Номер 66, С. 103470 - 103470

Опубликована: Май 17, 2025

Язык: Английский

---

Effect of multicollinearity in assessing the compaction and strength parameters of lime-treated expansive soil using artificial intelligence techniques

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2024, Номер 8(1)

Опубликована: Ноя. 18, 2024

Язык: Английский

---

Stability of rectangular tunnels in cohesive-frictional soil under surcharge loading using isogeometric analysis and Bayesian neural networks

Advances in Engineering Software, Год журнала: 2024, Номер 201, С. 103861 - 103861

Опубликована: Дек. 30, 2024

Язык: Английский

---

Integrating Multiple Linear Regression Analysis and Machine Learning Models to Predict the Bearing Capacity of Strip Footings on Sandy Clay Slopes

Transportation Infrastructure Geotechnology, Год журнала: 2025, Номер 12(2)

Опубликована: Фев. 1, 2025

Язык: Английский

---

Machine Learning for Defect Condition Rating of Wall Wooden Columns in Ancient Buildings

Case Studies in Construction Materials, Год журнала: 2025, Номер unknown, С. e04458 - e04458

Опубликована: Фев. 1, 2025

Язык: Английский

---