Artificial intelligence in the design, optimization, and performance prediction of concrete materials: a comprehensive review DOI Creative Commons
Dayou Luo,

Kejin Wang,

Dongming Wang

и другие.

npj Materials Sustainability, Год журнала: 2025, Номер 3(1)

Опубликована: Май 17, 2025

Язык: Английский

Image-driven prediction system: Automatic extraction of aggregate gradation of pavement core samples integrating deep learning and interactive image processing framework DOI
Han-Cheng Dan, Zheying Huang, Bingjie Lu

и другие.

Construction and Building Materials, Год журнала: 2024, Номер 453, С. 139056 - 139056

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

8
Prediction of maximum dynamic shear modulus of undisturbed marine soils in the eastern coast of China based on machine learning methods DOI
Yiliang Tu, Qianglong Yao,

Ying Zhou

и другие.

Ocean Engineering, Год журнала: 2025, Номер 321, С. 120382 - 120382

Опубликована: Янв. 20, 2025

Язык: Английский

Процитировано

1
A machine learning and game theory-based approach for predicting creep behavior of recycled aggregate concrete DOI Creative Commons

Jinpeng Feng,

Haowei Zhang, Kang Gao

и другие.

Case Studies in Construction Materials, Год журнала: 2022, Номер 17, С. e01653 - e01653

Опубликована: Ноя. 9, 2022

In this paper, the SHapley Additive exPlanation (SHAP) is utilized in conjunction with ensemble machine learning (EML) model to study creep behaviors of recycled aggregate concrete (RAC) for first time. Five typical EML models, such as Random Forest (RF), Adaptive Boost Machine (AdaBoost), Gradient Boosting Decision Tree (GBDT), Extreme (XGBoost), and Light (LGBM) are considered. The proposed method can sort contributions input features interpret prediction results best model. findings show that existing empirical models fib Model Code 2010 JTG 3362-2018 cannot satisfy requirements RAC behavior because impact ratio other factors ignored. Moreover, water-cement loading age two most significant factors. Therefore, has potential provide insight into performance structures help engineers adjust mechanical behaviors.

Язык: Английский

Процитировано

27
Compressive Strength Prediction of Basalt Fiber Reinforced Concrete Based on Interpretive Machine Learning Using SHAP Analysis DOI
Xuewei Wang,

Zhijie Ke,

Wenjun Liu

и другие.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2024, Номер unknown

Опубликована: Авг. 28, 2024

Язык: Английский

Процитировано

6
Intelligent design of limit states for recycled aggregate concrete filled steel tubular columns DOI
Keyu Chen, Shiqi Wang, Ying Wang

и другие.

Structures, Год журнала: 2023, Номер 58, С. 105338 - 105338

Опубликована: Окт. 12, 2023

Язык: Английский

Процитировано

11
Effect of phenyl functional groups on the adsorption behaviour of dodecyl anionic emulsifiers on oxides on the aggregate surface DOI
Lingyun Kong,

Songxiang Zhu,

Yi Peng

и другие.

International Journal of Pavement Engineering, Год журнала: 2024, Номер 25(1)

Опубликована: Янв. 18, 2024

Emulsified asphalt finds extensive application in pavement repair, addressing issues like road ruts and cracks. While the adsorption behaviour of emulsifiers on oxide surfaces (CaCO3 SiO2) aggregates is influenced by presence phenyl functional groups, precise mechanism this influence remains insufficiently understood. This study employs molecular dynamics models macroscopic experiments to investigate involving emulsifiers, sodium ions, water at aggregate interfaces, quantifying role groups from a perspective. The results reveal following: strong electrostatic attraction between alkaline Na+, leading substantial Na+ adsorption. reduce diffusion coefficient, energy, amounts (−34.6%, −16%, −12.5%), while increasing them acidic (+15.9%, + 14.7%, 27.7%). impact hydrogen bond acceptors, TPSA, emulsifier complexity, altering They enhance potential, affecting different surfaces. In summary, ongoing research framework aims fine-tune through use enhancing strength, amount, aggregates. work holds great significance for optimizing structures.

Язык: Английский

Процитировано

4
Interpretable Machine Learning Models for Prediction of UHPC Creep Behavior DOI Creative Commons
Peng Zhu,

Wenshuo Cao,

Lianzhen Zhang

и другие.

Buildings, Год журнала: 2024, Номер 14(7), С. 2080 - 2080

Опубликована: Июль 7, 2024

The creep behavior of Ultra-High-Performance Concrete (UHPC) was investigated by machine learning (ML) and SHapley Additive exPlanations (SHAP). Important features were selected feature importance analysis, including water-to-binder ratio, aggregate-to-cement compressive strength at loading age, elastic modulus duration, steel fiber volume content, curing temperature. Four typical ML models—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting Machine (XGBoost), Light (LGBM)—were studied to predict the UHPC. Via Bayesian optimization 5-fold cross-validation, models tuned achieve high accuracy (R2 = 0.9847, 0.9627, 0.9898, 0.9933 for RF, ANN, XGBoost, LGBM, respectively). contribution different ranked. Additionally, SHAP utilized interpret predictions models, four parameters stood out as most influential coefficient: temperature, ratio. results consistent with theoretical understanding. Finally, UHPC curves three cases plotted based on model developed, prediction more accurate than that fib Model Code 2010.

Язык: Английский

Процитировано

4
Generative artificial intelligence and optimisation framework for concrete mixture design with low cost and embodied carbon dioxide DOI Creative Commons
Khuong Le Nguyen, Minhaz Uddin, Thong M. Pham

и другие.

Construction and Building Materials, Год журнала: 2024, Номер 451, С. 138836 - 138836

Опубликована: Окт. 22, 2024

Язык: Английский

Процитировано

4
In-service performance assessment of fire-corrosion damaged cables of bridges DOI

Jinpeng Feng,

Jinglun Li, Kang Gao

и другие.

Engineering Structures, Год журнала: 2023, Номер 300, С. 117221 - 117221

Опубликована: Ноя. 30, 2023

Язык: Английский

Процитировано

9
Yüksek performanslı betonun basınç dayanımının farklı makine öğrenimi algoritmaları ile tahmin edilmesi DOI Creative Commons
Muhammet Gökhan Altun,

Ahmet Hakan Altun

Journal of Innovative Engineering and Natural Science, Год журнала: 2025, Номер 5(1), С. 347 - 361

Опубликована: Янв. 20, 2025

Betonun basınç dayanımı, beton bileşenlerinin miktarları ve özellikleri, yaşı, ortam koşulları, deneysel koşullar gibi birçok faktörden etkilenmektedir. en önemli özelliği olan dayanımının belirlenmesi amacıyla makine öğrenimi algoritmaları alternatif bir yöntem olarak kullanılmaktadır. Bu çalışmada, yüksek performanslı betonun dayanımını tahmin etmek 1030 satırlık açık veri seti üzerinde altı farklı modeli kullanılmıştır. Ayrıca mevcut setine türetilen yeni öznitelikler ilave edilerek etme süreçlerindeki etkileri incelenmiştir. bağlamda özniteliklerin algoritmaların performansına katkısı değerlendirilmiş hangi iyi sonuçları verdiği analiz edilmiştir. Elde edilen sonuçlara göre doğru yeteneği süre açısından sonucu XGBoost LightGBM göstermiştir. Buna ilaveten, iki öznitelik daha eklenmesi kullanılan algoritmalarının yeteneğini arttırmıştır.

Процитировано

0