Prediction of the chloride diffusivity of recycled aggregate concrete using artificial neural network

Jin, Libing; Dong, Tianyun; Fan, Tai; Duan, Jie; Yu, Hongwen; Jiao, Pengfei; Zhang, Weibo

doi:10.1016/j.mtcomm.2022.104137

Cited by 15 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…used the random forest algorithm to predict the compressive strength of basalt fiber reinforced concrete with different fiber contents and lengths and obtained prediction results with high accuracy (R2=0.96, RMSE=6.9). JIN et al (2022) used ANN to predict the durability of recycled coarse aggregate concrete (RAC), which verified the role of ANN in the study of material durability.…”

mentioning

confidence: 65%

Research on anti-impact performance of steel fiber reinforced concrete based on finite element and machine learning

Zhao

Yang

Gao

et al. 2023

Preprint

View full text Add to dashboard Cite

To predict the impact resistance of steel fiber reinforced concrete (SFRC), 50 specimens with different fiber lengths and different fiber contents were loaded using ABAQUS finite element software to obtain data in this paper. Two machine learning (ML) models, backward propagation-artificial neural network (BP-ANN) and support vector machine (SVM), were used to train the data. The results show that in the prediction of the impact resistance of steel fiber reinforced concrete by this model, the deviation of the predicted values from the real values is small, and the two models are well fitted. To further optimize the model, the parameters of the prediction model were adjusted using the whale optimization algorithm (WOA) in this paper, and the accuracy of the optimized model was significantly improved. After optimization, the WOA-BP-ANN and WOA-SVM models have better generalization ability and higher prediction accuracy than the WOA-SVM model.

show abstract

mentioning

confidence: 65%

Research on anti-impact performance of steel fiber reinforced concrete based on finite element and machine learning

Zhao

Yang

Gao

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These models can be deterministic or probabilistic. Some studies have reported on mathematical, analytical, numerical, and empirical service life models of RAC, and some of them have even been based on artificial neural networks [ 144 , 165 , 166 , 167 ].…”

Section: Chloride Ingress-based Service Life Predictionmentioning

confidence: 99%

A Review of Chloride Penetration of Recycled Concrete with Enhancement Treatment and Service Life Prediction

Wang,

Liao,

Zhang

2024

Materials

View full text Add to dashboard Cite

The application of recycled coarse aggregate (RA) in structural concrete can save non-renewable resources and reduce land occupation. Developing comprehensive knowledge of chloride penetration and service life modeling of recycled coarse aggregate concrete (RAC) is a prerequisite for practice. However, compared with the natural aggregate concrete (NAC), the inferior durability performance, especially chloride penetration resistance, of RAC hinders its application in structural concrete. Therefore, many RAC performance enhancement methods have been proposed. This paper presents a holistic review focused on the chloride penetration of RAC with/without enhancement methods and service life prediction. The current RAC performance enhancement methods are introduced. The improvement effect of the corresponding enhancement methods on the chloride penetration resistance of RAC are discussed and analyzed in turn. Based on the reviewed data on the chloride diffusion coefficient, the modification efficiencies of assorted enhancement methods are summarized. With the hope of promoting RAC application in structural concrete, the current literature on chloride-ingress-based service life prediction for RAC is also overviewed. In addition, the typical influencing factors on chloride transport properties are also discussed, i.e., RA quality. It can be concluded that enhancement techniques can effectively improve the chloride penetration resistance of RAC. The old mortar enhancement or removal methods can improve the chloride penetration resistance by 15–30%, depending on the specific treatment measures. The modification efficiency of the modifier material depends on the specific type and content of the incorporated substance, which ranges from approximately 5% to 95%. The estimated service life of RAC structures decreases with the increasing RA replacement ratio. Finally, concluding remarks are provided concerning future research on the chloride transport behavior of RAC.

show abstract

“…This artificial neuron system is efficient in handling various tasks. ANN models consist of interconnected neurons, allowing for complex computations (Bilim et al 2009, Jin et al 2022. In this study, an ANN model was used to forecast data based on experimental data.…”

Section: Measurement Of Mechanical and Physical Propertiesmentioning

confidence: 99%

Development of red mud based sintered artificial aggregates with various industrial wastes

Narendra,

Vasugi

2024

Mater. Res. Express

View full text Add to dashboard Cite

Red mud (RM) has drawn a lot of attention in the search for potential uses in the production of sintered artificial aggregate from industrial waste products. The main objective of the study is to produce an RM-based sintered artificial aggregate (SAA), with several blends (binary, ternary, and quaternary) using various industrial wastes. This study includes assessing the mechanical and physical properties of SAA as well as the sintering parameters in order to determine the appropriate material mix ratio. To achieve these objectives, a comprehensive experimental approach was adopted. A total of 35 different mixtures were formulated by incorporating various industrial wastes as binders and sintering additives. The green pellets were preheated at 105°C for 24 hours, and consecutively sintered at different temperatures, namely 700°C, 900°C, 1100°C, and 1150°C with a duration of 30 minutes. A compressive strength test was performed in order to find the mechanical property of SAA similarly water absorption and bulk density tests were conducted to find the physical properties of SAA. To characterize the SAA, scanning electron microscope analysis (SEM), X-ray diffraction (XRD) and energy dispersive X-ray analysis were conducted, and also data analysis was performed using Artificial Neural Network (ANN) tools, yielding accurate predictions. Successfully best compressive strength low water absorption SAA was produced. The best material weight mix ratio for the production of SAA was identified as (A18) RM: Fly Ash: Waste Glass Powder; 78:10:12. Out of all blends the ternary blend (A18) SAA exhibited impressive properties after 30 minutes of sintering at 1150°C: high compressive strength of 22.92 MPa, water absorption of 4.26%, and bulk density of 1296.12 kg/m³. This was made possible by the high amount of Al2O3, SiO2, in the combination of fly ash, and waste glass powder with RM. SEM and XRD analysis also confirmed that the (A18) SAA achieved the best compressive strength, and low water absorption due to turning the surface and core area into a solid, reduced internal pores and formed quartz, and hematite phases. The findings of this study serve as a foundation for future work and pave the way for the development of sustainable construction materials. 

show abstract

Prediction of the chloride diffusivity of recycled aggregate concrete using artificial neural network

Cited by 15 publications

References 33 publications

Research on anti-impact performance of steel fiber reinforced concrete based on finite element and machine learning

Research on anti-impact performance of steel fiber reinforced concrete based on finite element and machine learning

A Review of Chloride Penetration of Recycled Concrete with Enhancement Treatment and Service Life Prediction

Development of red mud based sintered artificial aggregates with various industrial wastes

Contact Info

Product

Resources

About