A comparative analysis of tree-based machine learning algorithms for predicting the mechanical properties of fibre-reinforced GGBS geopolymer concrete

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2024, Volume and Issue: 7(3), P. 2555 - 2583

Published: Jan. 28, 2024

Language: Английский

---

Exploratory literature review and scientometric analysis of artificial intelligence applied to geopolymeric materials

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 145, P. 110210 - 110210

Published: Feb. 20, 2025

Language: Английский

---

AutoGluon-enabled machine learning models for predicting recycled aggregate concrete’s compressive strength

Australian Journal of Structural Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 15

Published: March 2, 2025

Language: Английский

---

Behavior of geomaterial composite using sugar cane bagasse ash under compressive and flexural loading

Frontiers in Materials, Journal Year: 2023, Volume and Issue: 10

Published: March 2, 2023

The sugar industry produces a huge quantity of cane bagasse ash in India. Dumping massive quantities waste non-eco-friendly manner is key concern for developing nations. main focus this study the development sustainable geomaterial composite with higher strength capabilities (compressive and flexural). To develop composite, sugarcane (SA), glass fiber (GF), blast furnace slag (BF) are used. Ash generated from burning known as bagasse. check suitability secondary use civil engineering to minimize risk environment growth, sequence compressive flexural tests was performed on materials prepared using (SA) reinforced by (GF) combination cement (CEM). effects mix ratios (0.2%–1.2%), weight (10%), binding (10%–20%), water (55%) regarding strength, density, tangent modulus, stress–strain pattern, load–deflection curve were studied. According findings, achieved maximum 1055.5 kPa ranged 120 kPa, 217 80.1 at different ratio percentages. value initial modulus cube specimens between 96 636 MPa. For compression 20% cement, density decreased 1320.1 1265 kg/m 3 , 1318 1259.6 . With limitation lower percentages C/SA, specimen cannot sustain its shape even after curing period. In comparing previous research present experimental work, it observed that material proposed here lightweight can be utilised filler substance weak compressible soils improve their load-bearing capacity.

Language: Английский

---

Machine Learning Models for Ecofriendly Optimum Design of Reinforced Concrete Columns

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(7), P. 4117 - 4117

Published: March 23, 2023

CO2 emission is one of the biggest environmental problems and contributes to global warming. The climatic changes due damage nature triggering a climate crisis globally. To prevent possible crisis, this research proposes an engineering design solution reduce emissions. This optimization-machine learning pipeline set models trained for prediction variables ecofriendly concrete column. In research, harmony search algorithm was used as optimization algorithm, different regression were predictive models. Multioutput applied predict such section width, height, reinforcement area. results indicated that random forest performed better than all other machine algorithms have also achieved high accuracy.

Language: Английский

---

Effect of Graphene Oxide on the Mechanical Properties and Durability of High-Strength Lightweight Concrete Containing Shale Ceramsite

Materials, Journal Year: 2023, Volume and Issue: 16(7), P. 2756 - 2756

Published: March 30, 2023

An effective pathway to achieve the sustainable development of resources and environmental protection is utilize shale ceramsite (SC), which processed from spoil produce high-strength lightweight concrete (HSLWC). Furthermore, urgent demand for better performance HSLWC has stimulated active research on graphene oxide (GO) in strengthening mechanical properties durability. This study was an effort investigate effect different contents GO manufactured SC. For this purpose, six mixtures containing range 0-0.08% (by weight cement) were systematically designed test (compressive strength, flexural splitting tensile strength), durability (chloride penetration resistance, freezing-thawing sulfate attack resistance), microstructure. The experimental results showed that optimum amount 0.05% can maximize compressive strength by 20.1%, 34.3%, 24.2%, respectively, exhibited excellent chloride resistance. Note when addition relatively high, improvement as attenuated instead. Therefore, based comprehensive analysis microstructure, optimal level best considered be 0.05%. These findings provide a new method use SC engineering.

Language: Английский

---

Machine Learning Modeling Integrating Experimental Analysis for Predicting Compressive Strength of Concrete Containing Different Industrial Byproducts

Advances in Civil Engineering, Journal Year: 2024, Volume and Issue: 2024, P. 1 - 11

Published: March 1, 2024

This study aimed to develop accurate models for estimating the compressive strength (CS) of concrete using a combination experimental testing and different machine learning (ML) approaches: baseline regression models, boosting model, bagging tree-based ensemble average voting (VR). The research utilized an extensive dataset with 14 input variables, including cement, limestone powder, fly ash, granulated glass blast furnace slag, silica fume, rice husk marble brick coarse aggregate, fine recycled water, superplasticizer, voids in mineral aggregate. To evaluate performance each ML five metrics were used: mean absolute error (MAE), squared (MSE), root (RMSE), coefficient determination (R2-score), relative (RRMSE). comparative analysis revealed that VR model exhibited highest effectiveness, displaying strong correlation between actual estimated outcomes. boosting, bagging, achieved impressive R2-scores range 86.69%–92.43%, MAE ranging from 3.87 4.87, MSE 21.74 38.37, RMSE 4.66 RRMSE 8% 11%. Particularly, outperformed all other R2-score (92.43%) lowest rate. developed demonstrated excellent generalization prediction capabilities, providing valuable tools practitioners, researchers, designers efficiently CS concrete. By mitigating environmental vulnerabilities associated impacts, this can significantly contribute enhancing quality sustainability construction practices.

Language: Английский

---

Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC)

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: 49(10), P. 14351 - 14365

Published: May 3, 2024

Abstract Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization fundamental for daily-basis engineering practice. Nonetheless, experimental measurements of PCC’s properties (i.e., Poisson’s Ratio - v -, Elastic Modulus E Compressive Strength -ComS-, and Tensile -TenS-) consume considerable amounts time financial resources. Therefore, development high-precision indirect methods fundamental. Accordingly, this research proposes a computational model based on deep neural networks (DNNs) to simultaneously predict , ComS, TenS. For purpose, Long-Term Pavement Performance database was employed as data source. In regard, mix design parameters PCC are adopted input variables. The performance DNN evaluated with 1:1 lines, goodness-of-fit parameters, Shapley additive explanations assessments, running analysis. results demonstrated that proposed exhibited an exactitude higher than 99.8%, forecasting errors close zero (0). Consequently, machine learning-based designed in investigation helpful tool estimating when laboratory tests not attainable. Thus, main novelty study creating robust determine TenS by solely considering parameters. Likewise, central contribution state-of-the-art achieved present effort public launch developed through open-access GitHub repository, which can be utilized engineers, designers, agencies, other stakeholders.

Language: Английский

---

Data-Driven, Physics-Based, or Both: Fatigue Prediction of Structural Adhesive Joints by Artificial Intelligence

Applied Mechanics, Journal Year: 2023, Volume and Issue: 4(1), P. 334 - 355

Published: March 8, 2023

Here, a comparative investigation of data-driven, physics-based, and hybrid models for the fatigue lifetime prediction structural adhesive joints in terms complexity implementation, sensitivity to data size, accuracy is presented. Four data-driven (DDM) are constructed using extremely randomized trees (ERT), eXtreme gradient boosting (XGB), LightGBM (LGBM) histogram-based (HGB). The physics-based model (PBM) relies on Findley’s critical plane approach. Two (HM) were developed by combining approaches obtained from invariant stresses (HM-I) stress (HM-F). A dataset 979 points four adhesives employed. To assess split into three train/test ratios, namely 70%/30%, 50%/50%, 30%/70%. Results revealed that DDMs more accurate, but sensitive size compared PBM. Among different regressors, LGBM presented best performance generalization power. HMs increased predictions, whilst reducing size. HM-I demonstrated datasets sources can be utilized improve predictions (especially with small datasets). Finally, showed highest an improved

Language: Английский

---

Performance Characterization and Composition Design Using Machine Learning and Optimal Technology for Slag–Desulfurization Gypsum-Based Alkali-Activated Materials

Materials, Journal Year: 2024, Volume and Issue: 17(14), P. 3540 - 3540

Published: July 17, 2024

Fly ash–slag-based alkali-activated materials have excellent mechanical performance and a low carbon footprint, they emerged as promising alternative to Portland cement. Therefore, replacing traditional cement with slag–desulfurization gypsum-based will help make better use of the waste, protect environment, improve materials’ performance. In order understand it thus in engineering, needs be characterized for compositional design. This study developed novel framework characterization composition design by combining Categorical Gradient Boosting (CatBoost), simplicial homology global optimization (SHGO), laboratory tests. The CatBoost model was evaluated discussed based on SHapley Additive exPlanations (SHAPs) partial dependence plot (PDP). Through proposed framework, optimal maximum flexural strength compressive at 1, 3, 7 days is Ca(OH)2: 3.1%, fly ash: 2.6%, DG: 0.53%, alkali: 4.3%, modulus: 1.18, W/G: 0.49. Compared material obtained from experiment, actual increased 26.67%, 6.45%, 9.64%, 41.89%, 9.77%, 7.18%, respectively. addition, results tests are very close predictions which shows that characterizes well test data. provides reasonable, scientific, helpful way characterize determine civil materials.

Language: Английский

---