Estimation on compressive strength of recycled aggregate self-compacting concrete using interpretable machine learning-based models DOI

Suhang Yang,

T. Chen, Zhifeng Xu

et al.

Engineering Computations, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 15, 2024

Purpose Recycled aggregate self-compacting concrete (RASCC) has the potential for sustainable resource utilization and been widely applied. Predicting compressive strength (CS) of RASCC is challenging due to its complex composite nature nonlinear behavior. Design/methodology/approach This study comprehensively evaluated commonly used machine learning (ML) techniques, including artificial neural networks (ANN), random trees (RT), bagging forests (RF) predicting CS RASCC. The results indicate that RF ANN models typically have advantages with higher R2 values, lower root mean square error (RMSE), (MSE) absolute (MAE) values. Findings combination ML Shapley additive explanation (SHAP) interpretable algorithms provides physical rationality, allowing engineers adjust proportion based on parameter analysis predict design sensitivity model indicates ANN’s interpretation ability weaker than tree-based (RT, BG RF). regression technology high accuracy, good interpretability great Originality/value

Language: Английский

Predictive models in machine learning for strength and life cycle assessment of concrete structures DOI

A. Dinesh,

B. Rahul Prasad

Automation in Construction, Journal Year: 2024, Volume and Issue: 162, P. 105412 - 105412

Published: April 3, 2024

Language: Английский

Citations

19
Artificial neural network an innovative approach in air pollutant prediction for environmental applications: A review DOI Creative Commons

Vibha Yadav,

Amit Kumar Yadav, Vedant Singh

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102305 - 102305

Published: May 22, 2024

Air pollution in the environment is growing daily as a result of urbanization and population growth, which causes numerous health issues. Information about air quality environmental risks provided by pollutant data crucial for management. The use artificial neural network (ANN) approaches predicting pollutants reviewed this research. These methods are based on several forecast intervals, including hourly, daily, monthly ones. This study shows that ANN techniques contaminants more precisely than traditional methods. It has been discovered input parameters architecture-type algorithms used affect accuracy prediction models. therefore accurate reliable other empirical models because they can handle wide range meteorological parameters. Finally, research gap networks identified. review may inspire researchers to certain extent promote development intelligence prediction.

Language: Английский

Citations

18
Estimating the compressive and tensile strength of basalt fibre reinforced concrete using advanced hybrid machine learning models DOI

Irfan Ullah,

Muhammad Faisal Javed,

Hisham Alabduljabbar

et al.

Structures, Journal Year: 2025, Volume and Issue: 71, P. 108138 - 108138

Published: Jan. 1, 2025

Language: Английский

Citations

2
Polypropylene waste plastic fiber morphology as an influencing factor on the performance and durability of concrete: Experimental investigation, soft-computing modeling, and economic analysis DOI
Razan Alzein,

M. Vinod Kumar,

Ashwin Raut

et al.

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 438, P. 137244 - 137244

Published: July 2, 2024

Language: Английский

Citations

14
A systematic literature review of AI-based prediction methods for self-compacting, geopolymer, and other eco-friendly concrete types: Advancing sustainable concrete DOI

Tariq Ali,

Mohamed Hechmi El Ouni,

Muhammad Zeeshan Qureshi

et al.

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 440, P. 137370 - 137370

Published: July 16, 2024

Language: Английский

Citations

10
Forecasting interfacial bond strength in FRP-reinforced concrete using soft computing techniques DOI
Khalid Saqer Alotaibi, Fadi Almohammed

Construction and Building Materials, Journal Year: 2025, Volume and Issue: 473, P. 140827 - 140827

Published: March 30, 2025

Language: Английский

Citations

1
Interpretable machine learning models for predicting the bond strength between UHPC and normal-strength concrete DOI
Kaihua Liu, Tingrui Wu,

Zhuorong Shi

et al.

Materials Today Communications, Journal Year: 2024, Volume and Issue: 40, P. 110006 - 110006

Published: July 30, 2024

Language: Английский

Citations

8
Machine learning-enabled characterization of concrete mechanical strength through correlation of flexural and torsional resonance frequencies DOI
Bai Li, Majid Samavatian, Vahid Samavatian

et al.

Physica Scripta, Journal Year: 2024, Volume and Issue: 99(7), P. 076002 - 076002

Published: May 21, 2024

Abstract In this study, an assessment of concrete compressive strength was conducted using impulse excitation data-driven machine learning (ML) framework. The model constructed upon a deep neural network and aided by the backpropagation method, ensuring precise training process. contrast to prior research, which mainly focused on mixture components, meaningful relationship between physical parameters—resonant frequencies elastic moduli—and established our ML model. Remarkable performance demonstrated, with root mean square error value 2.8MPa determination factor 0.97. Through Pearson analysis, correlations input features output targets, ranging from −0.29 0.90, were revealed. Notably, strongest found in Young's shear moduli, derived flexural torsional frequencies, highlighting pivotal role dynamic response concrete's mechanical behavior. Furthermore, findings indicated slight prediction deviations cases involving samples high Poisson's ratio. This work illuminates potential for accurate leveraging response, particularly modes, thereby opening avenues research into without direct consideration sample ingredients.

Language: Английский

Citations

6
Mechanical properties, microstructure and GEP-based modeling of basalt fiber reinforced lightweight high-strength concrete containing SCMs DOI
Muhammad Abid,

Ghulam Qadir Waqar,

Jize Mao

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 96, P. 110378 - 110378

Published: Aug. 8, 2024

Language: Английский

Citations

4
Synergistic effects of basalt fiber and volcanic pumice powder in high-strength geopolymer concrete DOI Creative Commons

Mohamed Abdellatief,

Hamed I. Hamouda, Martin Palou

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 27, 2025

This paper explores the synergistic effects of basalt fiber (BF) and volcanic pumice powder (VPP) on physico-mechanical, thermal characteristics, efflorescence, microstructure high-strength geopolymer concrete (HSGC). HSGC mixtures were developed by partially replacing ground granulated blast furnace slag with 0-40% VPP while incorporating BF in range 0-1.5%. The experimental findings demonstrate that increasing content from 0.75 to 1.5% significantly enhances compressive, flexural, splitting tensile strengths, compressive strength up 14.51% at 28 days flexural strengths improving 13.17% 14.46%, respectively. Conversely, higher generally reduces strength, a 40% replacement leading 23% decline 7 days. Moreover, increased levels improved stability, volumes found deteriorate microstructure, thereby accelerating efflorescence process. Particularly, sample containing 10% reduced both crystal area thickness compared other mixtures. A multi-objective optimization approach revealed properties, whereas diminished performance. optimal formulation achieved 59.25 MPa, 7.51 8.64 dry density 2012 kg/m3, 0.69% 17.79% VPP. Macroscopic analyses demonstrated exhibited more compact demonstrating effectiveness response surface methodology identifying ideal mixture parameters for design.

Language: Английский

Citations

0