Study and prediction of photocurrent density with external validation using machine learning models DOI
Nepal Sahu, Chandrashekhar Azad, Uday Kumar

et al.

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 92, P. 1335 - 1355

Published: Nov. 1, 2024

Language: Английский

Carbonation depth assessment in shotcrete with various initial damage degrees and accelerator dosages: Experimental study DOI
Huimin Pan,

Yongxiang Qiu,

Hanqi Jiang

et al.

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 404, P. 133192 - 133192

Published: Sept. 6, 2023

Language: Английский

Citations

7
Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength DOI Open Access

Talita Andrade da Costa Almeida,

Emerson Felipe Félix,

Carlos Manuel Andrade de Sousa

et al.

Materials, Journal Year: 2023, Volume and Issue: 16(24), P. 7683 - 7683

Published: Dec. 17, 2023

The artificial neural networks (ANNs)-based model has been used to predict the compressive strength of concrete, assisting in creating recycled aggregate concrete mixtures and reducing environmental impact construction industry. Thus, present study examines effects training algorithm, topology, activation function on predictive accuracy ANN when determining concrete. An experimental database with 721 samples was defined considering literature. train, validate, test ANN-based models. Altogether, 240 ANNs were trained, by combining three algorithms, two functions, topologies a hidden layer containing 1-40 neurons. single including 28 neurons, trained Levenberg-Marquardt algorithm hyperbolic tangent function, achieved best level accuracy, coefficient determination equal 0.909 mean absolute percentage error 6.81%. Furthermore, results show that it is crucial avoid use overly complex Excessive neurons can lead exceptional performance during but poor ability testing.

Language: Английский

Citations

7
Evaluation of the Performance of Pervious Concrete Inspired by CO2-Curing Technology DOI Creative Commons
Murugan Muthu, Łukasz Sadowski

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(10), P. 4202 - 4202

Published: May 15, 2024

Urban runoff is acidic in nature and mainly consists of heavy metals sediments. In this study, the pervious concrete samples were cured a CO2-rich environment their performance under conditions was evaluated by passing different solutions containing clay particles, metal ions, acid species. The compressive strength these reduced up to 14% when they water instead CO2 environment. Heavy including lead zinc, simulated adsorbed 96% 80% at end experiment, but species could leach calcium ions from cement components during passage. Clay particles trapped flow channels samples, which marginally percolation rate 14%. Concrete carbonation release conditions, zinc removal relatively lower because nonavailability hydroxyl sites interconnected pore structure. weight losses carbonated storage suggesting that curing reduces degradation aggressive chemicals. SEM tomography images revealed degraded microstructure, while XRD results provided data on mineralogical changes. improves gain service life environments.

Language: Английский

Citations

2
PSO-BP model for assessing frost resistance in containment concrete with varying pipe diameters DOI

Du Ting,

Jian Xiao,

Jinghao Chen

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 110908 - 110908

Published: Sept. 1, 2024

Language: Английский

Citations

2
An adaptive weight ensemble approach to forecast influenza activity in an irregular seasonality context DOI Creative Commons
Tim K. Tsang, Qiurui Du, Benjamin J. Cowling

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Oct. 4, 2024

Language: Английский

Citations

2
Methodology for the Prediction of the Thermal Conductivity of Concrete by Using Neural Networks DOI Creative Commons
Ana Carolina Rosa, Youssef Elomari, Alejandro Calderón

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(17), P. 7598 - 7598

Published: Aug. 28, 2024

The energy consumption of buildings presents a significant concern, which has led to demand for materials with better thermal performance. Thermal conductivity (TC), among the most relevant properties, is essential address this demand. This study introduces methodology integrating Multilayer Perceptron (MLP) and Generative Adversarial Network (GAN) predict TC concrete based on its mass composition density. Three scenarios using experimental data from published papers synthetic are compared reveal model’s outstanding performance across training, validation, test datasets. Notably, MLP trained GAN-augmented dataset outperforms one real dataset, demonstrating remarkable consistency between predictions actual values. Achieving an RMSE 0.0244 R2 0.9975, these outcomes can offer precise quantitative information advance energy-efficient materials.

Language: Английский

Citations

1
Integrating machine learning and Monte Carlo Simulation for probabilistic assessment of durability in RC structures affected by carbonation-induced corrosion DOI
Emerson Felipe Félix,

Breno M. Lavinicki,

Tobias L. G. T. Bueno

et al.

Journal of Building Pathology and Rehabilitation, Journal Year: 2024, Volume and Issue: 9(2)

Published: Sept. 19, 2024

Language: Английский

Citations

1
Improving carbonation resistance, strength, and microstructure of concrete through compression casting DOI Creative Commons
Junru Li, Syed Minhaj Saleem Kazmi,

Xun Wang

et al.

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: unknown, P. e03804 - e03804

Published: Sept. 1, 2024

Language: Английский

Citations

1
Construction of hybrid models based on cascade technique using basic machine learning models: An application as photocurrent density predictor of the photoelectrode in PEC cell DOI
Nepal Sahu, Chandrashekhar Azad, Uday Kumar

et al.

Materials Today Communications, Journal Year: 2024, Volume and Issue: 41, P. 110643 - 110643

Published: Oct. 10, 2024

Language: Английский

Citations

1
Coupling Effects of Stress and Carbonation on Concrete Durability: A Review DOI Open Access

Zhixin Liu,

Chaochao Sun,

Jili Qu

et al.

Materials, Journal Year: 2024, Volume and Issue: 17(22), P. 5438 - 5438

Published: Nov. 7, 2024

This review investigates the combined effects of stress and carbonation on durability concrete, an important but under-researched factor affecting infrastructure longevity. Carbonation substantially degrades particularly under tensile, compressive, bending stresses. paper synthesizes recent findings to explore how these states influence progression overall durability, emphasizing data depth, mechanical performance, structural integrity. Key models experimental results are evaluated, revealing significant gaps in current knowledge, including limited insights into long-term impacts stress-carbonation interactions lack standardized testing methods. To address gaps, future research should prioritize refinement prediction complex conditions development high-resilience materials suitable for challenging environments. Ultimately, this aims establish a foundation more accurate predictions concrete service life, thereby supporting advancements material science sustainable construction practices.

Language: Английский

Citations

1