Forecasting the strength of micro/nano silica in cementitious matrix by machine learning approaches

Materials Today Communications, Journal Year: 2023, Volume and Issue: 37, P. 107066 - 107066

Published: Sept. 9, 2023

Language: Английский

---

Sustainable of rice husk ash concrete compressive strength prediction utilizing artificial intelligence techniques

Asian Journal of Civil Engineering, Journal Year: 2023, Volume and Issue: 25(2), P. 1349 - 1364

Published: Aug. 1, 2023

Language: Английский

---

Novel base predictive model of resilient modulus of compacted subgrade soils by using interpretable approaches with graphical user interface

Materials Today Communications, Journal Year: 2024, Volume and Issue: 40, P. 109764 - 109764

Published: July 10, 2024

Language: Английский

---

Innovative machine learning approaches to predict the compressive strength of recycled plastic aggregate self-compacting concrete incorporating different waste ashes

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2024, Volume and Issue: 7(3), P. 2585 - 2604

Published: Jan. 28, 2024

Language: Английский

---

Machine learning assisted prediction of the mechanical properties of carbon nanotube‐incorporated concrete

Structural Concrete, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 17, 2024

Abstract The incorporation of carbon nanotubes (CNTs) in concrete can improve the physical, mechanical, and durability properties. However, interaction CNTs with their effect on mechanical properties remains a challenging issue. Also, determination through experimental testing is time‐consuming, laborious, uneconomical. This study focuses development machine learning (ML) models for prediction concrete. A comprehensive data set 758 CNT‐modified specimens was established compressive strength (CS), split tensile (STS), flexural (FS), modulus elasticity (MOE) values from studies literature. Afterward, predictive were developed using multilinear regression (MLR), support vector (SVM), ensemble methods (EN), tree (RT), Gaussian process (GPR). It found that among ML models, GPR model predicted CS, STS, FS at highest efficiency coefficient ( R 2 ) 0.83, 0.78, 0.93, respectively while performance SVM superior predicting MOE an value 0.91. mean absolute error (MAE) FS, 2.92, 0.26, 0.35, 1.31, which also lesser than other models. training time different demonstrated has lower (~3 s) as compared to indicates it high accuracy‐to‐time cost ratio. Further, most influential parameters CS age, cement, water–cement ratio, nanotubes. one‐way partial dependence analysis showed direct correlation age cement but inverse ratio fine aggregate. graphical user interface provides implication practical applications.

Language: Английский

---

An efficient machine learning approach for predicting concrete chloride resistance using a comprehensive dataset

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Sept. 12, 2023

Abstract By conducting an analysis of chloride migration in concrete, it is possible to enhance the durability concrete structures and mitigate risk corrosion. In addition, utilization machine learning techniques that can effectively forecast coefficient shows potential as a financially viable less complex substitute for labour-intensive experimental evaluations. The existing models predicting resistance encounter two primary challenges: constraints imposed by limited dataset absence certain input variables. These factors collectively contribute decrease overall effectiveness these models. Therefore, this study aims propose advanced approach cleaning, utilizing comprehensive comprising 1073 pre-existing outcomes. proposed model diffusion incorporates various variables, such water content, cement slag fly ash silica fume fine aggregate coarse superplasticizer fresh density, compressive strength, age strength test, test. artificial neural network (ANN) technique also employed processing missing data. current supervised both regression classification tasks. efficacy accurately has been validated. findings indicate XGBoost SVM algorithms exhibit superior performance compared other prediction algorithms, evidenced their high R2 scores 0.94 0.91, respectively. relation demonstrate Random Forest, LightGBM, highest levels accuracy, specifically 0.93, 0.96, 0.97, Furthermore, website developed capable penetration concrete.

Language: Английский

---

Experimental investigation and predictive modeling of compressive strength and electrical resistivity of graphene nanoplatelets modified concrete

Materials Today Communications, Journal Year: 2023, Volume and Issue: 38, P. 107639 - 107639

Published: Nov. 23, 2023

Language: Английский

---

Comparative analysis of cement grade and cement strength as input features for machine learning-based concrete strength prediction

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: 21, P. e03557 - e03557

Published: July 21, 2024

Machine learning (ML) has gained recognition as a valuable tool for predicting concrete properties. This study investigated the influence of input features related to cement strength on performance ML models. Four datasets with various were prepared, and each dataset, grade alternately applied features. models such Random Forest, Extreme Gradient Boosting, Multilayer Perceptron Neural Network utilized predict dataset. The results showed tendency prediction improve when properties used features, extent improvement varying across datasets. Permutation importance analysis indicated that often had greater than grade, positively enhancing performance. Therefore, considering an feature is expected be beneficial constructing more accurate

Language: Английский

---

Machine learning based prediction of compressive and flexural strength of recycled plastic waste aggregate concrete

Structures, Journal Year: 2024, Volume and Issue: 69, P. 107363 - 107363

Published: Sept. 28, 2024

Language: Английский

---

Dynamic and static behaviour of geopolymer concrete for sustainable infrastructure development: Prospects, challenges, and performance review

Composite Structures, Journal Year: 2025, Volume and Issue: unknown, P. 118984 - 118984

Published: Feb. 1, 2025

Language: Английский

---