Comparative analysis of the influence of partial replacement of cement with supplementing cementitious materials in sustainable concrete by using machine learning approach DOI Creative Commons
Rishabh Arora, Kaushal Kumar, Saurav Dixit

et al.

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: July 26, 2023

Abstract Cement manufacturing is a major contributor to climate change because of the greenhouse gas carbon dioxide released into atmosphere throughout process. In this paper, cement content concrete has been partially replaced by using two supplementing cementitious materials (SCMs) like Silica Fume and Fly Ash. Characterizations both conducted for their end use utilization in applications. Extensive experimentation ensure effect partial replacement on performance characteristics through compressive strength, flexural split tensile strength concrete. It was observed that waste material ability replace without changing Finding indicating with proper mix design can improve green fume have better response as compared fly ash Accuracy experimental data validated machine learning approach. Experimental results are used train models. Metrics such Mean Absolute Error (MAE), Squared (MSE), Root (RMSE), R 2 Score, Cross Validations evaluate According findings, extreme Gradient Boosting Regression model performs than any other models when it comes predicting validating Split mixtures. achieves an value 0.9811 prediction 0.9818 0.9127 strength. The findings research shed light usefulness regression properties predictions terms accuracy. 10–15% SCMs resulted good agreements characteristics.

Language: Английский

Data Utilization and Partitioning for Machine Learning Applications in Civil Engineering DOI

Ahmed E. Ebid,

Ahmed Farouk Deifalla, Kennedy C. Onyelowe

et al.

Sustainable civil infrastructures, Journal Year: 2024, Volume and Issue: unknown, P. 87 - 100

Published: Jan. 1, 2024

Language: Английский

Citations

18
Estimating the strength of soil stabilized with cement and lime at optimal compaction using ensemble-based multiple machine learning DOI Creative Commons
Kennedy C. Onyelowe, Arif Ali Baig Moghal, Ahmed M. Ebid

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: July 3, 2024

Abstract It has been imperative to study and stabilize cohesive soils for use in the construction of pavement subgrade compacted landfill liners considering their unconfined compressive strength (UCS). As long as natural soil falls below 200 kN/m 2 strength, there is a structural necessity improve its mechanical property be suitable intended purposes. Subgrades landfills are important environmental geotechnics structures needing attention engineering services due role protecting environment from associated hazards. In this research project, comparative suitability assessment best analysis conducted on behavior (UCS) reconstituted with cement lime mechanically stabilized at optimal compaction using multiple ensemble-based machine learning classification symbolic regression techniques. The ML techniques gradient boosting (GB), CN2, naïve bayes (NB), support vector (SVM), stochastic descent (SGD), k-nearest neighbor (K-NN), decision tree (Tree) random forest (RF) artificial neural network (ANN) response surface methodology (RSM) estimate (UCS, MPa) lime. considered inputs were (C), (Li), liquid limit (LL), plasticity index (PI), optimum moisture content (OMC), maximum dry density (MDD). A total 190 mix entries collected experimental exercises partitioned into 74–26% train-test dataset. At end model exercises, it was found that both GB K-NN models showed same excellent accuracy 95%, while SVM, Tree shared level about 90%. RF SGD fair 65–80% finally (NB) badly producing an unacceptable low 13%. ANN RSM also closely matched SVM Tree. Both correlation matrix sensitivity indicated UCS greatly affected by MDD, then consistency limits content, comes third place impact (OMC) almost neglected. This outcome can applied field obtain negligible compactive moisture.

Language: Английский

Citations

10
Machine learning-based hybrid regularization techniques for predicting unconfined compressive strength of soil reinforced with multiple additives DOI
Anish Kumar, Sanjeev Sinha

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2025, Volume and Issue: 8(5)

Published: March 20, 2025

Language: Английский

Citations

1
A comparative study of prediction models for alkali-activated materials to promote quick and economical adaptability in the building sector DOI
Siyab Ul Arifeen, Muhammad Nasir Amin, Waqas Ahmad

et al.

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 407, P. 133485 - 133485

Published: Sept. 28, 2023

Language: Английский

Citations

18
Optimizing and hyper-tuning machine learning models for the water absorption of eggshell and glass-based cementitious composite DOI Creative Commons
Xiqiao Xia

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(1), P. e0296494 - e0296494

Published: Jan. 2, 2024

Cementitious composites' performance degrades in extreme conditions, making it more important to enhance its resilience. To further the adaptability of eco-friendly construction, waste materials are increasingly being repurposed. composites deteriorate both direct and indirect ways due facilitation hostile ion transport by water. The effects using eggshell glass powder as partial substitutes for cement sand mortar on water-absorption capacity were investigated machine learning (ML) modeling techniques such Gene Expression Programming (GEP) Multi (MEP). assess importance inputs, sensitivity analysis interaction research carried out. water absorption property cementitious was precisely estimated generated ML models. It noted that MEP model, with an R2 0.90, GEP 0.88, accurately predicted results. revealed most affected presence powder, sand, powder. model's significance lies fact they offer one-of-a-kind mathematical formulas can be applied prediction features another database. models resulting from this study help scientists engineers rapidly assess, enhance, rationalize mixture proportioning. built theoretically compute made based varied input parameters, cost time savings.

Language: Английский

Citations

7
A 30-Year Review on Nanocomposites: Comprehensive Bibliometric Insights into Microstructural, Electrical, and Mechanical Properties Assisted by Artificial Intelligence DOI Open Access
Fernando Gomes de Souza, Shekhar Bhansali, Kaushik Pal

et al.

Materials, Journal Year: 2024, Volume and Issue: 17(5), P. 1088 - 1088

Published: Feb. 27, 2024

From 1990 to 2024, this study presents a groundbreaking bibliometric and sentiment analysis of nanocomposite literature, distinguishing itself from existing reviews through its unique computational methodology. Developed by our research group, novel approach systematically investigates the evolution nanocomposites, focusing on microstructural characterization, electrical properties, mechanical behaviors. By deploying advanced Boolean search strategies within Scopus database, we achieve meticulous extraction in-depth exploration thematic content, methodological advancement in field. Our uniquely identifies critical trends insights concerning microstructure, attributes, performance. The paper goes beyond traditional textual analytics evaluation, offering new interpretations data highlighting significant collaborative efforts influential studies domain. findings uncover language, shifts, global contributions, providing distinct comprehensive view dynamic research. A component is “State-of-the-Art Gaps Extracted Results Discussions” section, which delves into latest advancements This section details various types their properties introduces applications, especially films. tracing historical progress identifying emerging trends, emphasizes significance collaboration molding Moreover, “Literature Review Guided Artificial Intelligence” showcases an innovative AI-guided research, first Focusing articles 2023, selected based citation frequency, method offers perspective interplay between nanocomposites properties. It highlights composition, structure, functionality systems, integrating recent for overview current knowledge. analysis, with average score 0.638771, reflects positive trend academic discourse increasing recognition potential nanocomposites. another novelty, maps intellectual domain, emphasizing pivotal themes influence crosslinking time attributes. While acknowledging limitations, exemplifies indispensable role tools synthesizing understanding extensive body literature. work not only elucidates prevailing but also contributes insights, enhancing

Language: Английский

Citations

6
Modeling the influence of lime on the unconfined compressive strength of reconstituted graded soil using advanced machine learning approaches for subgrade and liner applications DOI Creative Commons

Xinghuang Guo,

César García,

Alexis Iván Andrade Valle

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(4), P. e0301075 - e0301075

Published: April 2, 2024

In the field of soil mechanics, especially in transportation and environmental geotechnics, use machine learning (ML) techniques has emerged as a powerful tool for predicting understanding compressive strength behavior soils graded ones. This is to overcome sophisticated equipment, laboratory space cost needs utilized multiple experiments on treatment geotechnics systems. present study explores application techniques, namely Genetic Programming (GP), Artificial Neural Networks (ANN), Evolutionary Polynomial Regression (EPR), Response Surface Methodology unconfined (UCS) soil-lime mixtures. was purposes subgrade landfill liner design construction. By utilizing input variables such Gravel, Sand, Silt, Clay, Lime contents (G, S, M, C, L), models forecasted values after 7 28 days curing. The accuracy developed compared, revealing that both ANN EPR achieved similar level UCS days, while GP model performed slightly lower. complexity formula required resulted decreased accuracy. accuracies 85% 82%, with R 2 0.947 0.923, average error 0.15 0.18, respectively, exhibited lower 66.0%. Conversely, RSM produced predicted more than 98% 99%, 7- 28- day curing regimes, respectively. also adequate precision modelling 14% against standard 7%. All factors were found have almost equal importance, except lime content (L), which had an influence. shows importance gradation construction liners. research further demonstrates potential ML reconstituted G-S-M-C provides valuable insights engineering applications exact sustainable designs, performance monitoring rehabilitation constructed civil infrastructure.

Language: Английский

Citations

4
Modeling the compressive strength of concrete at different curing regimes using machine learning DOI Creative Commons
Kennedy C. Onyelowe, Ahmed M. Ebid,

R. Jiménez

et al.

Discover Sustainability, Journal Year: 2025, Volume and Issue: 6(1)

Published: May 1, 2025

Language: Английский

Citations

0
Machine learning-driven sustainable urban design: transforming Singapore's landscape with vertical greenery DOI

Mohammed Yousef Abu Hussein,

Mutasem A. Al-Karablieh,

Safa’ Al-Kfouf

et al.

Asian Journal of Civil Engineering, Journal Year: 2024, Volume and Issue: 25(5), P. 3851 - 3863

Published: April 15, 2024

Language: Английский

Citations

2
Overview of meshfree modeling of the flowability of fresh self-compacting concrete for sustainable structures DOI Creative Commons
Kennedy C. Onyelowe, Denise‐Penelope N. Kontoni, Michael E. Onyia

et al.

E3S Web of Conferences, Journal Year: 2023, Volume and Issue: 436, P. 08008 - 08008

Published: Jan. 1, 2023

The flow of Bingham non-Newtonian incompressible fluids like concrete is associated with the large deformation materials. modeling and simulation these fluids’ behavior by using conventional numerical methods. suffer problem-formulation setbacks due to mesh distortion. In order compensate for mathematical inefficiencies encountered in process, particle-based methods have evolved been applied. Also, use some produces a stretch unreliability Eulerian algorithmic trail, which visits every particle edge allowing revisiting vertices during its operation. This makes model path cumbersome time-consuming. Concrete an important element sustainable infrastructural development, understanding strengthens efficiency handling placement construction activities. this paper, mesh-free method flowability self-compacting (SCC) known as smoothed hydrodynamics (SPH) has reviewed. It derives advantage from Lagrangian trail. explores merits demerits industry propose best practices passing ability, filling dynamic stability flowing fresh (FFC)

Language: Английский

Citations

6