Explainable Tuned Machine Learning Models for Assessing the Impact of Corrosion on Bond Strength in Concrete DOI Creative Commons

Maryam Bypour,

Alireza Mahmoudian,

Mohammad Yekrangnia

et al.

Cleaner Engineering and Technology, Journal Year: 2024, Volume and Issue: 23, P. 100834 - 100834

Published: Nov. 12, 2024

Language: Английский

Machine Learning-Driven Optimization for Predicting Compressive Strength in Fly Ash Geopolymer Concrete DOI Creative Commons

Maryam Bypour,

Mohammad Yekrangnia, Mahdi Kioumarsi

et al.

Cleaner Engineering and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100899 - 100899

Published: Jan. 1, 2025

Language: Английский

Citations

1
A novel machine learning-based approach to determine the reduction factor for punching shear strength capacity of voided concrete slabs DOI Creative Commons

Alireza Mahmoudian,

Mussa Mahmoudi, Mohammad Yekrangnia

et al.

Deleted Journal, Journal Year: 2025, Volume and Issue: 2(1)

Published: Feb. 27, 2025

Language: Английский

Citations

1
Explainable Boosting Machine Learning for Predicting Bond Strength of FRP Rebars in Ultra High-Performance Concrete DOI Creative Commons

Alireza Mahmoudian,

Maryam Bypour,

Mahdi Kioumarsi

et al.

Computation, Journal Year: 2024, Volume and Issue: 12(10), P. 202 - 202

Published: Oct. 9, 2024

Aiming at evaluating the bond strength of fiber-reinforced polymer (FRP) rebars in ultra-high-performance concrete (UHPC), boosting machine learning (ML) models have been developed using datasets collected from previous experiments. The considered variables this study are rebar type and diameter, elastic modulus tensile rebars, compressive cover, embedment length, test method. dataset contains two methods: pullout tests beam tests. Four types rebar, including carbon (CFRP), glass (GFRP), basalt, steel were considered. ML applied include AdaBoost, CatBoost, Gradient Boosting, XGBoost, Hist Boosting. After hyperparameter tuning, these demonstrated significant improvements predictive accuracy, with XGBoost achieving highest R2 score 0.95 lowest Root Mean Square Error (RMSE) 2.21. Shapley values analysis revealed that strength, modulus, length most critical factors influencing strength. findings offer valuable insights for applying predicting FRP-reinforced UHPC, providing a practical tool structural engineering.

Language: Английский

Citations

5
Interpretable machine learning models for predicting flexural bond strength between FRP/steel bars and concrete DOI Creative Commons
Mohsen Ebrahimzadeh,

Alireza Mahmoudian,

Nima Tajik

et al.

Structures, Journal Year: 2025, Volume and Issue: 74, P. 108587 - 108587

Published: March 4, 2025

Language: Английский

Citations

0
Explainable Tuned Machine Learning Models for Assessing the Impact of Corrosion on Bond Strength in Concrete DOI Creative Commons

Maryam Bypour,

Alireza Mahmoudian,

Mohammad Yekrangnia

et al.

Cleaner Engineering and Technology, Journal Year: 2024, Volume and Issue: 23, P. 100834 - 100834

Published: Nov. 12, 2024

Language: Английский

Citations

3