Advancing waste-based construction materials through carbon dioxide curing: A comprehensive review DOI Creative Commons
Marsail Al Salaheen, Wesam Salah Alaloul, Khalid Mhmoud Alzubi

et al.

Results in Engineering, Journal Year: 2023, Volume and Issue: 20, P. 101591 - 101591

Published: Nov. 21, 2023

With an emphasis on solid waste-based construction materials, this study seeks to provide in-depth analysis of current advancements in CO2 curing processes for building materials. 715 publications were extracted from the Web Science and Scopus databases reviewed following systematic review guidelines integrated with bibliometric approach. The recent operational environmental benefits obtain characteristics optimal materials discussed. findings demonstrated that early-age densifies microstructure lowering porosity enhancing mechanical properties, impermeability, durability. Additionally, carbonation has potential enhance performance ash-based concretes as well physical recycled aggregates, hence promoting waste reutilization sector. Also, conducted studies revealed pre- post-curing conditions are critical chamber configuration. Moreover, exposure time, pressure concentration, all directly influenced material sequestration. More investigations related improving long-term products still required methods increasing rate.

Language: Английский

A review of physics-based machine learning in civil engineering DOI Creative Commons
Shashank Reddy Vadyala, Sai Nethra Betgeri, John C. Matthews

et al.

Results in Engineering, Journal Year: 2021, Volume and Issue: 13, P. 100316 - 100316

Published: Dec. 29, 2021

The recent development of machine learning (ML) and Deep Learning (DL) increases the opportunities in all sectors. ML is a significant tool that can be applied across many disciplines, but its direct application to civil engineering problems challenging. for applications are simulated lab often fail real-world tests. This usually attributed data mismatch between used train test model it encounters real world, phenomenon known as shift. However, physics-based integrates data, partial differential equations (PDEs), mathematical models solve shift problems. Physics-based trained supervised tasks while respecting any given laws physics described by general nonlinear equations. ML, which takes center stage science plays an important role fluid dynamics, quantum mechanics, computational resources, storage. paper reviews history engineering.

Language: Английский

Citations

152
Compressive strength prediction of basalt fiber reinforced concrete via random forest algorithm DOI
Li Hong, Jiajian Lin,

Xiaobao Lei

et al.

Materials Today Communications, Journal Year: 2022, Volume and Issue: 30, P. 103117 - 103117

Published: Jan. 14, 2022

Language: Английский

Citations

112
Artificial intelligence algorithms for prediction and sensitivity analysis of mechanical properties of recycled aggregate concrete: A review DOI Creative Commons
Tien-Dung Nguyen, Rachid Cherif, Pierre-Yves Mahieux

et al.

Journal of Building Engineering, Journal Year: 2023, Volume and Issue: 66, P. 105929 - 105929

Published: Jan. 20, 2023

Using recycled aggregates generated from demolition waste for concrete production is a promissory option to reduce the environmental footprint of built environment. However, predicting hardened performance aggregate one main barriers its intensive deployment in construction sector. Since traditional empirical approaches are less reliable new formulations, artificial intelligence have been widely developed recent years towards this aim. In paper, we conducted an extensive literature review on (AI) methods that predict mechanical concretes and perform sensitivity analysis. The primary methodologies algorithms found thoroughly described, examined, discussed study concerning their applicability, accuracy, computational requirements. Furthermore, benefits drawbacks various highlighted. AI demonstrated success variety prediction applications with high accuracy. Although these robust predictive tools estimating concrete's mixture composition properties, highly dependent data structure hyperparameter selection. This could help engineers researchers make better decisions about using properties and/or optimise formulations concrete.

Language: Английский

Citations

57
A systematic review on automated human emotion recognition using electroencephalogram signals and artificial intelligence DOI Creative Commons
Raveendrababu Vempati, Lakhan Dev Sharma

Results in Engineering, Journal Year: 2023, Volume and Issue: 18, P. 101027 - 101027

Published: March 17, 2023

Language: Английский

Citations

46
Forecasting the strength of graphene nanoparticles-reinforced cementitious composites using ensemble learning algorithms DOI Creative Commons
Majid Khan, Roz‐Ud‐Din Nassar,

Waqar Anwar

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 21, P. 101837 - 101837

Published: Feb. 6, 2024

Contemporary infrastructure requires structural elements with enhanced mechanical strength and durability. Integrating nanomaterials into concrete is a promising solution to improve However, the intricacies of such nanoscale cementitious composites are highly complex. Traditional regression models encounter limitations in capturing these intricate compositions provide accurate reliable estimations. This study focuses on developing robust prediction for compressive (CS) graphene nanoparticle-reinforced (GrNCC) through machine learning (ML) algorithms. Three ML models, bagging regressor (BR), decision tree (DT), AdaBoost (AR), were employed predict CS based comprehensive dataset 172 experimental values. Seven input parameters, including graphite nanoparticle (GrN) diameter, water-to-cement ratio (wc), GrN content (GC), ultrasonication (US), sand (SC), curing age (CA), thickness (GT), considered. The trained 70 % data, remaining 30 data was used testing models. Statistical metrics as mean absolute error (MAE), root square (RMSE) correlation coefficient (R) assess predictive accuracy DT AR demonstrated exceptional accuracy, yielding high coefficients 0.983 0.979 training, 0.873 0.822 testing, respectively. Shapley Additive exPlanation (SHAP) analysis highlighted influential role positively impacting CS, while an increased (w/c) negatively affected CS. showcases efficacy techniques accurately predicting nanoparticle-modified concrete, offering swift cost-effective approach assessing nanomaterial impact reducing reliance time-consuming expensive experiments.

Language: Английский

Citations

28
New generation neurocomputing learning coupled with a hybrid neuro-fuzzy model for quantifying water quality index variable: A case study from Saudi Arabia DOI
Mohammad Saood Manzar, Mohammed Benaafi, Romulus Costache

et al.

Ecological Informatics, Journal Year: 2022, Volume and Issue: 70, P. 101696 - 101696

Published: May 31, 2022

Language: Английский

Citations

47
Towards sustainable construction: Machine learning based predictive models for strength and durability characteristics of blended cement concrete DOI
Majid Khan, Muhammad Faisal Javed

Materials Today Communications, Journal Year: 2023, Volume and Issue: 37, P. 107428 - 107428

Published: Oct. 26, 2023

Language: Английский

Citations

41
Optimizing durability assessment: Machine learning models for depth of wear of environmentally-friendly concrete DOI Creative Commons
Majid Khan, Roz‐Ud‐Din Nassar, Asad U. Khan

et al.

Results in Engineering, Journal Year: 2023, Volume and Issue: 20, P. 101625 - 101625

Published: Nov. 28, 2023

The use of fly ash in cementitious composites has gained popularity. Assessing this property requires expensive and destructive laboratory tests utilizing specialized equipment like the rotating-cutter method. Therefore, there is a need for alternative methods to predict depth wear (DW) such more efficiently cost-effectively. Accordingly, objective research utilize machine learning (ML) approaches, including one individual algorithm (Decision Tree) two ensemble algorithms (AdaBoost Regressor Bagging Regressor) estimate fly-ash-based concrete. A collection 216 experimental records was obtained from existing literature. efficiency models examined with multiple statistical indexes. bagging regressor (BR) model provided superior estimation performance correlation coefficient (R) 0.999 compared AdaBoost (R = 0.965) decision tree 0.962). models, notably BR, accurate predictions an 87.8 % lower mean absolute error (MAE) 85 root square (RMSE) model. In addition, BR exhibited lowest index (ρ) values 0.016 training 0.012 validation. SHapley Additive exPlanation (SHAP) revealed that time testing age are most dominant controlling features significantly contribute wear. conclusion, ML techniques SHAP interpretation DW concrete reduces reliance on lab tests, making durability assessment practical cost-effective.

Language: Английский

Citations

36
Fractionation of dyes/salts using loose nanofiltration membranes: Insight from machine learning prediction DOI
Nadeem Baig, Jamilu Usman, Sani I. Abba

et al.

Journal of Cleaner Production, Journal Year: 2023, Volume and Issue: 418, P. 138193 - 138193

Published: July 22, 2023

Language: Английский

Citations

33
Prediction of the cross-sectional capacity of cold-formed CHS using numerical modelling and machine learning DOI Creative Commons
Musab Rabi, Felipe Piana Vendramell Ferreira, Ikram Abarkan

et al.

Results in Engineering, Journal Year: 2023, Volume and Issue: 17, P. 100902 - 100902

Published: Jan. 19, 2023

The use of circular hollow sections (CHS) have seen a large increase in usage recent years mainly because the distinctive mechanical properties and unique aesthetic appearance. focus this paper is behaviour cold-rolled CHS beam-columns made from normal high strength steel, aiming to propose design formula for predicting ultimate cross-sectional load carrying capacity, employing machine learning. A finite element model developed validated conduct an extensive parametric study with total 3410 numerical models covering wide range most influential parameters. ANN then trained using data obtained as well 13 test results compiled various research available literature, accordingly new proposed. comprehensive comparison rules given EC3 presented assess performance model. According analysis study, proposed ANN-based shown be efficient powerful tool predict resistance level accuracy least computational costs.

Language: Английский

Citations

29