Frost-resistance prediction model for stress-damaged lightweight aggregate concrete based on BPNN: a comparative study DOI Creative Commons
Chun Lin Fu,

Qiushi Zhang

Materials Research Express, Journal Year: 2024, Volume and Issue: 11(8), P. 085513 - 085513

Published: Aug. 1, 2024

Abstract With the depletion of natural resources and requirement higher strength-weight ratio, lightweight aggregate concrete has attracted more attention because its good thermal properties, fire resistance seismic performance. However, exposure to low temperature environments accelerates deterioration concrete, thereby, reduce service life concrete. Even worse, in cold arid regions, often experiences accidental impacts, wind erosion, earthquakes, other disasters during service, these damage significantly impact frost-resistance. Therefore, accurately quantitatively describing predicting frost-resistance under specific disaster conditions is crucial. In this study, take initial degree freeze-thaw cycles as input variables, while relative dynamic elastic modulus (RDEM) an out variable, a frost prediction models for stress-damaged was established based on back propagation neural network (BPNN). The results show that predicted values BPNN model are agreement with experimental values, also compared revised Loland which proposed by another author. Results demonstrate average error between only 1.69%, whereas one 9.13%, indicating can achieve relatively accurate quantitative assessment throughout entire post-disaster lifecycle it broadened idea provided reference

Language: Английский

Development of performance-based models for green concrete using multiple linear regression and artificial neural network DOI

Priyanka Singh,

Abiola Usman Adebanjo, Nasir Shafiq

et al.

International Journal on Interactive Design and Manufacturing (IJIDeM), Journal Year: 2023, Volume and Issue: 18(5), P. 2945 - 2956

Published: June 17, 2023

Language: Английский

Citations

64
Revolutionizing concrete analysis: An in-depth survey of AI-powered insights with image-centric approaches on comprehensive quality control, advanced crack detection and concrete property exploration DOI
Kaustav Sarkar, Amit Shiuly, Krishna Gopal Dhal

et al.

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 411, P. 134212 - 134212

Published: Nov. 25, 2023

Language: Английский

Citations

36
Modified particle packing approach for optimizing waste marble powder as a cement substitute in high-performance concrete DOI
Ahmed Essam,

Sahar A. Mostafa,

Mehran Khan

et al.

Construction and Building Materials, Journal Year: 2023, Volume and Issue: 409, P. 133845 - 133845

Published: Oct. 31, 2023

Language: Английский

Citations

33
Comparative use of different AI methods for the prediction of concrete compressive strength DOI Creative Commons
Mouhamadou Amar

Cleaner Materials, Journal Year: 2025, Volume and Issue: 15, P. 100299 - 100299

Published: Feb. 5, 2025

Language: Английский

Citations

1
Neural Network Prediction and Enhanced Strength Properties of Natural Fibre-Reinforced Quaternary-Blended Composites DOI Creative Commons
Pavithra Chandramouli,

Mohamed Riyaaz Nayum Akthar,

Veerappan Sathish Kumar

et al.

CivilEng, Journal Year: 2024, Volume and Issue: 5(4), P. 827 - 851

Published: Sept. 26, 2024

This research, with its potential to revolutionise the construction industry, aims develop quaternary-blended composites (QBC) by replacing 80% of ordinary Portland cement (OPC) metakaolin, rice husk ash, and wood ash combined discrete hybrid natural fibres at a volume fraction 0.5%. study investigates mechanical properties, including compressive strength, split tensile impact strength QBC various curing ages 7, 28, 56 days. Scanning electron microscopy (SEM) analysis was performed assess microstructural characteristics. research aimed formulate novel quaternary binder that may minimise our reliance on cement. The experimental results indicate mix labelled M4L2 exhibited superior performance, percentage increases approximately 51.03% 29.19%, respectively. Meanwhile, M5L1 demonstrated enhanced energy, increase about 36.40% in SEM observations revealed MC4 contained unhydrated portions larger cracks. In contrast, presence contributed crack resistance, resulting denser matrix improved properties. also employed an artificial neural network (ANN) model predict compressive, tensile, characteristics QBC, predictions aligning closely results. An investigation conducted determine ideal number hidden layers neurons each layer. model’s effectiveness evaluated using statistical metrics such as correlation coefficient (R), determination (R2), root mean square error (RMSE), absolute (MEA), (MAPE). findings suggest developed QBCs can effectively reduce conventional while offering properties suitable for sustainable practices.

Language: Английский

Citations

1
Frost resistance prediction for rubberized concrete based on artificial neural network DOI Creative Commons
Chun Fu, Ming Li

Deleted Journal, Journal Year: 2024, Volume and Issue: 6(12)

Published: Nov. 28, 2024

Using waste rubber to partially replace fine aggregate make concrete can not only reduce black pollution alleviate the dilemma of natural sand resource depletion, but also improve frost resistance concrete, which is undoubtedly a win–win solution. Aim promote application seasonal cold regions, it great significance evaluate and predict its frost-resistance. Different from ordinary existence changes inherent characteristics varying degrees, makes durability more complicated establishment prediction models challenging. In this paper, an artificial neural network (ANN) model was proposed frost-resistance rubberized concrete. water-cement ratio, cement, sand, rate, content number freeze–thaw cycles as input variables relative dynamic elastic modulus output variables, three-layer BP (BPNN) with hidden layer established on basis large experimental data another author. The results show that BPNN has strong ability satisfactory accuracy (R2 = 0.9825, MAPE 1.5609%), opens up new way for

Language: Английский

Citations

1
Design and modeling the compressive strength of high-performance concrete with silica fume: a soft computing approach DOI
Abiola Usman Adebanjo, Nasir Shafiq, Siti Nooriza Abd Razak

et al.

Soft Computing, Journal Year: 2023, Volume and Issue: 28(7-8), P. 6059 - 6083

Published: Nov. 27, 2023

Language: Английский

Citations

3
Deep Learning–and IoT Based Framework for Rock-Fall Early Warning DOI Open Access
Mohammed Abaker, Hatim Dafaalla, Taiseer Abdalla Elfadil Eisa

et al.

Published: June 12, 2023

During the last few years, several approaches have been proposed to improve early warning systems for reducing rock-fall risk. In this regard, paper introduces a Deep learning-and (IoT) based Framework Rock-fall Early Warning, devoted risk with high accuracy. framework, prediction accuracy was augmented by eliminating uncertainties and confusion plaguing model. order achieve accuracy, framework fused model-based deep learning detection Internet of Things. determine framework’s performance, study adopted parameters, namely overall performance measures, on matrix ability reduce The result indicates an increase in model from 86% 98.8%. addition, reduced probability (1.51 ×10-3) (8.57 ×10-9). Our results indicate accuracy; it also provides robust decision-making process delivering lowering probability.

Language: Английский

Citations

2
Lightweight Bi-LSTM method for the prediction of mechanical properties of concrete DOI

Mrinal Anand,

M. Anand,

Minwoong Joe

et al.

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 83(18), P. 54863 - 54884

Published: Dec. 11, 2023

Language: Английский

Citations

2
Design and Modelling the Compressive Strength of High-Performance Concrete with Silica Fume: A Soft Computing Approach DOI Creative Commons
Abiola Usman Adebanjo, Nasir Shafiq, Siti Nooriza Abd Razak

et al.

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

Published: May 4, 2023

Abstract Soft computing methods were used in this research to design and model the compressive strength of high-performance concrete (HPC) with silica fume. Box-Behnken design-based response surface methodology (RSM) was develop 29 HPC mixes a target 80 ± 10 MPa. Cement (450–500 kg/m 3 ), aggregates (1500–1700 fume (SF) (20–45% weight cement) water-binder (w/b) ratio (0.24–0.32) provided as input factors while at 7 28 days analysed responses. Datasets for artificial neural network (ANN) prediction generated from 87 experimental observations test. Performance indicators such p-value, coefficient determination (R 2 mean square error (MSE) assess models. Results demonstrated that RSM worked relatively well projecting p-values < 0.05 R values 0.913 0.892 days, respectively. In addition, performed better detecting synergistic effects variables on On other hand, ANN best generalised relationship between independent dependent considering low MSE 12.32 14.60, high 0.912 0.946 Model equations developed predict silica-based after days. It is considered adopting components both approaches could help process developing consistent supplementary cementitious materials (SCMs).

Language: Английский

Citations

1