Impact of lightweight clay aggregate with slag and biomedical waste ash on self-compacting concrete using machine learning approach DOI Creative Commons
Kennedy C. Onyelowe, Viroon Kamchoom‬, Shadi Hanandeh

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 22, 2025

The self-compacting concrete (SCC) mixes were developed using lightweight expandable clay aggregate (LECA) as a partial substitute for coarse aggregate, ground granulated blast-furnace slag (GGBS) replacement cement, and combusted bio-medical waste ash (BMWA) fine aggregate. substitution levels LECA, GGBS, BMWA set at 10%, 20%, 30% of respectively. M30-grade SCC designed with two different water-to-binder ratios-0.40 0.45-and their compressive strength (CS) was experimentally evaluated. data entries from the above mix designs experiments collected in this research which deals evaluating impact metallurgical slag, on concrete. An extensive literature search used project produced global representative database literature. 384 records divided into training (300 = 80%) validation (84 20%) line requirements more reliable partitioning. Six advanced machine learning methods such Artificial Neural Network (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGB), Random Forest (RF), Adaptive (AdaBoost) to model behavior. All models created "Orange Data Mining" software version 3.36. A combination error metrics, efficiency metrics determination/correlation test performance accuracy. Also, Hoffman Gardener's method evaluate sensitivity analysis variables. At end work, AdaBoost KNN excel predictive accuracy 97.5%, reducing margin ensuring precise SCC. SVR, XGB, RF also exhibit strong (96.5-97%), supporting material selection proportions. demonstrate lowest errors (MAE: 0.65 MPa, RMSE: 0.75 MPa), indicating performance, minimizing overdesign or underperformance risks, optimizing usage. Hoffman/Gardener's GGBS 31% Dens 26% highest is followed by LECA 21% 20%. This enables optimization learning, experimental trials, enhancing efficiency, lowering environmental impact, promoting sustainable construction through effective reuse industrial by-products.

Язык: Английский

Influence of nonlinear thermal radiation and exponential space dependent heat source on hybrid nanofluid stagnation point flow over a shrinking riga surface DOI
Mohammed Zulfeqar Ahmed,

V. Dhanalaxmi,

Thirupathi Thumma

и другие.

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(3)

Опубликована: Фев. 12, 2025

Язык: Английский

Процитировано

1

Evaluating the strength of industrial wastesbased concrete reinforced with steel fiber using advanced machine learning DOI Creative Commons
Kennedy C. Onyelowe, Viroon Kamchoom‬, Ahmed M. Ebid

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 8, 2025

The traditional evaluation of compressive strength through repeated experimental works can be resource-intensive, time-consuming, and environmentally taxing. Leveraging advanced machine learning (ML) offers a faster, cheaper, more sustainable alternative for evaluating optimizing concrete properties, particularly materials incorporating industrial wastes steel fibers. In this research work, total 166 records were collected partitioned into training set (130 = 80%) validation (36 20%) in line with the requirements data partitioning sorting optimal model performance. These entries represented ten (10) components fiber reinforced such as C, W, FAg, CAg, PL, SF, FA, Vf, FbL, FbD, which applied input variables Cs, was target. Advanced techniques to (Cs) "Semi-supervised classifier (Kstar)", "M5 (M5Rules), "Elastic net (ElasticNet), "Correlated Nystrom Views (XNV)", "Decision Table (DT)". All models created using 2024 "Weka Data Mining" software version 3.8.6. Also, accuracies developed evaluated by comparing sum squared error (SSE), mean absolute (MAE), (MSE), root (RMSE), Error (%), Accuracy (%) coefficient determination (R2), correlation (R), willmott index (WI), Nash–Sutcliffe efficiency (NSE), Kling–Gupta (KGE) symmetric percentage (SMAPE) between predicted calculated values output. At end, has been found transformative approach that enhances efficiency, cost-effectiveness, sustainability wastes-based fiber. Among reviewed, Kstar DT emerge most practical achieving precise results. Their adoption significantly reduce environmental impacts promote use by-products construction. sensitivity on produced 36% from 71% 70% 60% 34% 5% 33% 67% 61% 61%. Fiber Volume Fraction (Vf) (67%) high suggests content greatly crack resistance tensile strength. Steel Orientation (61%) indicates importance alignment distributing stresses enhancing structural integrity.

Язык: Английский

Процитировано

1

Towards sustainable construction: estimating compressive strength of waste foundry sand-blended green concrete using a hybrid machine learning approach DOI Creative Commons
Nhat‐Duc Hoang,

Nguyen Quoc-Lam

Deleted Journal, Год журнала: 2025, Номер 2(1)

Опубликована: Март 3, 2025

Язык: Английский

Процитировано

0

Compressive Strength Prediction of Geopolymers Using Stacking Ensemble and Fuzzy Splitting DOI
Sourav Das, Satyabrata Roy,

Srivaishnavi Yaddanapudi

и другие.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0

Numerical computation of heat and mass transport for the higher Reynolds stress tensor modelling of generalised Newtonian fluid in a rotating surface: Milne’s predictor corrector method DOI
T. Salahuddin, Rafaqat Ali, Muhammad Awais

и другие.

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(4)

Опубликована: Фев. 26, 2025

Язык: Английский

Процитировано

0

Thermophoretic particle deposition in a mixed convective bioconvection nanofluid with thermal radiation and chemical reaction over an exponential stretching sheet DOI
Rupa Baithalu, Folarin Oluwaseun, Titilayo M. Agbaje

и другие.

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(4)

Опубликована: Март 9, 2025

Язык: Английский

Процитировано

0

Advancing Hybrid Fiber-Reinforced Concrete: Performance, Crack Resistance Mechanism, and Future Innovations DOI Creative Commons
Zehra Funda Akbulut, Taher A. Tawfik, Piotr Smarzewski

и другие.

Buildings, Год журнала: 2025, Номер 15(8), С. 1247 - 1247

Опубликована: Апрель 10, 2025

This research investigates the effects of steel (ST) and synthetic (SYN) fibers on workability mechanical properties HPFRC. It also analyzes their influence material’s microstructural characteristics. ST improve tensile strength, fracture toughness, post-cracking performance owing to rigidity, interlocking, robust adhesion with matrix. SYN fibers, conversely, mitigate shrinkage-induced micro-cracking, augment ductility, enhance concrete under dynamic stress while exerting negative workability. Hybrid fiber systems, which include offer synergistic advantages by enhancing management at various scales augmenting ductility energy absorption capability. Scanning electron microscopy (SEM) has been crucial in investigating fiber–matrix interactions, elucidating hydration, crack-bridging mechanisms, interfacial bonding. establish thick zones that facilitate effective transfer, whereas reduce micro-crack formation long-term durability. Nonetheless, deficiencies persist, encompassing optimal hybrid configurations, enduring fiber-reinforced (FRC), sustainable substitutes. Future investigations should examine multi-scale reinforcing techniques, intelligent for structural health assessment, alternatives. The standardization testing methodologies cost–benefit analyses is essential promote industrial deployment. review offers a thorough synthesis existing knowledge, emphasizing advancements potential HPFRC high-performance construction applications. findings development new, durable, resilient systems solving current difficulties.

Язык: Английский

Процитировано

0

Impact of lightweight clay aggregate with slag and biomedical waste ash on self-compacting concrete using machine learning approach DOI Creative Commons
Kennedy C. Onyelowe, Viroon Kamchoom‬, Shadi Hanandeh

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 22, 2025

The self-compacting concrete (SCC) mixes were developed using lightweight expandable clay aggregate (LECA) as a partial substitute for coarse aggregate, ground granulated blast-furnace slag (GGBS) replacement cement, and combusted bio-medical waste ash (BMWA) fine aggregate. substitution levels LECA, GGBS, BMWA set at 10%, 20%, 30% of respectively. M30-grade SCC designed with two different water-to-binder ratios-0.40 0.45-and their compressive strength (CS) was experimentally evaluated. data entries from the above mix designs experiments collected in this research which deals evaluating impact metallurgical slag, on concrete. An extensive literature search used project produced global representative database literature. 384 records divided into training (300 = 80%) validation (84 20%) line requirements more reliable partitioning. Six advanced machine learning methods such Artificial Neural Network (ANN), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGB), Random Forest (RF), Adaptive (AdaBoost) to model behavior. All models created "Orange Data Mining" software version 3.36. A combination error metrics, efficiency metrics determination/correlation test performance accuracy. Also, Hoffman Gardener's method evaluate sensitivity analysis variables. At end work, AdaBoost KNN excel predictive accuracy 97.5%, reducing margin ensuring precise SCC. SVR, XGB, RF also exhibit strong (96.5-97%), supporting material selection proportions. demonstrate lowest errors (MAE: 0.65 MPa, RMSE: 0.75 MPa), indicating performance, minimizing overdesign or underperformance risks, optimizing usage. Hoffman/Gardener's GGBS 31% Dens 26% highest is followed by LECA 21% 20%. This enables optimization learning, experimental trials, enhancing efficiency, lowering environmental impact, promoting sustainable construction through effective reuse industrial by-products.

Язык: Английский

Процитировано

0