Modelling the Rheological Properties of Fly Ash Incorporated Superplasticized Cement Paste at Different Temperature Using Multilayer Perceptrons in Tensorflow

Robert, Rogin C.; Kuriakose, Nelvin Mani; Gopikrishnan, K; Sathyan, Dhanya; Rajesh, C. B.

doi:10.1007/978-3-030-55115-5_58

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was reported that both yield stress and plastic viscosity could be predicted precisely using the RKS model with the limited amount of training data. Modelling using different techniques, and study of cement paste's flow properties was carried out by so many scholars (Robert et al 2021 [15], Dhanya et al 2020 [16], Jayasree and Gettu 2002 [17]). The research done by Uysal et al (2011) [5] used artificial neural networks to forecast the core compressive strength of self-compacting concrete (SCC) mixtures with mineral additives.…”

Section: Introductionmentioning

confidence: 99%

Modelling the Yield Stress of Fly-Ash Added Superplasticized Cement Paste at Different Temperatures Using Artificial Neural Network

Chandrasekar

Nourin

Gupta

et al. 2022

MSF

Self Cite

View full text Add to dashboard Cite

Rheology is the science that concerns the flow of liquids, and the distortion of solids under an applied force. The study of the rheology of concrete determines the properties of fresh concrete. The rheological parameters are affected by temperature, stress conditions and several other factors. The main intention of this research is to model the rheological parameters of the fly ash incorporated cement with various types of superplasticizers exposed under different temperatures using an Artificial Neural Network. Test data were generated by performing rheological tests on cement paste at three distinct temperatures (15, 27, 35°C). Mixes were prepared using OPC, fly ash (15, 25, 35%) and superplasticizers of four different families. By conducting experiments, 252 data have been generated by modifying the combination of fly-ash, superplasticizer, and test temperature. Among the 252 data, 80% has been utilized for training and 20% is utilized for predicting the model’s accuracy. The input layer of the model consists of test temperature, the amount of fly ash replaced, cement and water content, and four different groups of superplasticizers. The cement paste’s yield stress was the output parameter of the model. The model generated data has been compared with the experimentally generated data to determine the accuracy of the model.Keywords: Rheology, Fly Ash, Superplasticizer, Temperature, ANN

show abstract