RETRACTED: Experimental investigation and comparative machine-learning prediction of strength behavior of optimized recycled rubber concrete

Jalal, Mostafa; Grasley, Zachary; Gurganus, Charles; Bullard, Jeffrey W.

doi:10.1016/j.conbuildmat.2020.119478

Cited by 44 publications

(10 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks (ANN), fuzzy logic, genetic algorithms (GA), and genetic programming (GP) use AI techniques built on natural tools. These methods have been used to resolve the problems of the pre-mix design of rubberized concrete and waste foundry sand concrete by training of the available data collected from the literature [ 41 , 42 ]. The configuration detection capabilities of the AI methods (support vector regression or ANN) lead to the generalization of complicated patterns.…”

Section: Supervised Machine Learning Algorithmsmentioning

confidence: 99%

Application of Gene Expression Programming (GEP) for the Prediction of Compressive Strength of Geopolymer Concrete

et al. 2021

View full text Add to dashboard Cite

For the production of geopolymer concrete (GPC), fly-ash (FA) like waste material has been effectively utilized by various researchers. In this paper, the soft computing techniques known as gene expression programming (GEP) are executed to deliver an empirical equation to estimate the compressive strength of GPC made by employing FA. To build a model, a consistent, extensive and reliable data base is compiled through a detailed review of the published research. The compiled data set is comprised of 298 experimental results. The utmost dominant parameters are counted as explanatory variables, in other words, the extra water added as percent FA (), the percentage of plasticizer (), the initial curing temperature (), the age of the specimen (), the curing duration (), the fine aggregate to total aggregate ratio (), the percentage of total aggregate by volume (), the percent SiO2 solids to water ratio () in sodium silicate (Na2SiO3) solution, the NaOH solution molarity (), the activator or alkali to FA ratio (), the sodium oxide (Na2O) to water ratio () for preparing Na2SiO3 solution, and the Na2SiO3 to NaOH ratio (). A GEP empirical equation is proposed to estimate the of GPC made with FA. The accuracy, generalization, and prediction capability of the proposed model was evaluated by performing parametric analysis, applying statistical checks, and then compared with non-linear and linear regression equations.

show abstract

Section: Supervised Machine Learning Algorithmsmentioning

confidence: 99%

Application of Gene Expression Programming (GEP) for the Prediction of Compressive Strength of Geopolymer Concrete

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Accordingly, in recent years, numerous mathematical predictions and optimisation models have been developed within the research community, including artificial neural networks (ANNs) [ 25 , 26 , 27 ], metaheuristic algorithms [ 28 , 29 ], genetic expression programming (GEP) [ 30 , 31 , 32 , 33 ], adaptive neuro-fuzzy inference systems (ANFIS) [ 34 , 35 , 36 ], and response surface methodology (RSM) [ 37 , 38 , 39 ]. Among them, RSM is one of the best statistical techniques used for data optimization [ 40 ].…”

Section: Introductionmentioning

confidence: 99%

Optimisation of GBFS, Fly Ash, and Nano-Silica Contents in Alkali-Activated Mortars

et al. 2021

View full text Add to dashboard Cite

Although free-cement-based alkali-activated paste, mortar, and concrete have been recognised as sustainable and environmental-friendly materials, a considerable amount of effort is still being channeled to ascertain the best binary or ternary binders that would satisfy the requirements of strength and durability as well as environmental aspects. In this study, the mechanical properties of alkali-activated mortar (AAM) made with binary binders, involving fly ash (FA) and granulated blast-furnace slag (GBFS) as well as bottle glass waste nano-silica powder (BGWNP), were opti-mised using both experimentally and optimisation modelling through three scenarios. In the first scenario, the addition of BGWNP varied from 5% to 20%, while FA and GBFS were kept constant (30:70). In the second and third scenarios, BGWNP (5–20%) was added as the partial replacement of FA and GBFS, separately. The results show that the combination of binary binders (FA and GBFS) and BGWNP increased AAM’s strength compared to that of the control mixture for all scenarios. In addition, the findings also demonstrated that the replacement of FA by BGWNP was the most significant, while the effect of GBFS replacement by BGWNP was less significant. In particular, the highest improvement in compressive strength was recorded when FA, GBFS, and BGWNP were 61.6%, 30%, and 8.4%, respectively. Furthermore, the results of ANOVA (p values < 0.0001 and high F-values) as well as several statistical validation methods (R > 0.9, RAE < 0.1, RSE < 0.013, and RRSE < 0.116) confirmed that all the models were robust, reliable, and significant. Similarly, the data variation was found to be less than 5%, and the difference between the predicted R2 and adj. R2 was very small (<0.2), thus confirming that the proposed non-linear quadratic equations had the capability to predict for further observation. In conclusion, the use of BGWNP in AAM could act as a beneficial and sustainable strategy, not only to address environmental issues (e.g., landfill) but to also enhance strength properties.

show abstract

“…MLR-Multiple linear regression [3][4][5][6][7][8][9][10][11][12][13] SVM-Support vector machine [2,6,[13][14][15][16][17][18] ANFIS-Adaptive neuro-fuzzy inference system [5,10,11,[18][19][20] FL-Fuzzy logic [2,21,22] RF-Random forest [2,17,23] DT-Decision tree [2,15,23] GP-genetic programming [18,24,25] M5PMT-M5P Model tree [9,26,27] Salp swarm algorithm [27,28] CART-Classification and regression tree [12] Artificial neural networks are computational structures that are trained to learn patterns from examples. The development of ANNs is inspired by the human brain, a biological neural network functioning based on communication between neurons.…”

Section: Prediction Methods Referencementioning

confidence: 99%

Application of Artificial Neural Networks for Prediction of Mechanical Properties of CNT/CNF Reinforced Concrete

Kekez

Kubica

2021

Materials

View full text Add to dashboard Cite

Prominence of concrete is characterized by its high mechanical properties and durability, combined with multifunctionality and aesthetic appeal. Development of alternative eco-friendly or multipurpose materials has conditioned improvements in concrete mix design to optimize concrete production speed and price, as well as carbon footprint. Artificial neural networks represent a new and efficient tool in achieving optimal concrete mixtures according to its intended function. This paper addresses concrete mix design and the application of artificial neural networks (ANNs) for self-sensing concrete. The authors review concrete mix design methods and the development of ANNs for prediction of properties for various types of concrete. Furthermore, the authors present developments and applications of ANNs for prediction of compressive strength and flexural strength of carbon nanotubes/carbon nanofibers (CNT/CNF) reinforced concrete using experimental results for the learning process. The goal is to bring the ANN approach closer to a variety of concrete researchers and possibly propose the implementation of ANNs in the civil engineering practice.

show abstract

RETRACTED: Experimental investigation and comparative machine-learning prediction of strength behavior of optimized recycled rubber concrete

Cited by 44 publications

References 68 publications

Application of Gene Expression Programming (GEP) for the Prediction of Compressive Strength of Geopolymer Concrete

Application of Gene Expression Programming (GEP) for the Prediction of Compressive Strength of Geopolymer Concrete

Optimisation of GBFS, Fly Ash, and Nano-Silica Contents in Alkali-Activated Mortars

Application of Artificial Neural Networks for Prediction of Mechanical Properties of CNT/CNF Reinforced Concrete

Contact Info

Product

Resources

About