Artificial Neural Network for Evaluating the Strength of Self- Compacting Self-Curing Concrete

Author(s): A Mohanraj, V Senthilkumar and N Karthiga Shenbagam
Paper category: Proceedings
Book title: Proceedings of the 71st RILEM Annual Week & ICACMS 2017,Chennai,India, 3rd -8th September 2017
Editor(s): Manu Santhanam
Ravindra Gettu
Radhakrishna G. Pillai
Sunitha K. Nayar
ISBN: 978-2-35158-196-4
ISBN: 978-2-35158-190-2 (Set)
e-ISBN: 978-2-35158-191-9:
Publisher: Published by RILEM Publications S.A.R.L.
Publication year: 2017
Pages: 42-51
Total Pages: 10
Language : English

Abstract: This research work focuses on Artificial Neural Networks (ANNs) for evaluating optimum
percentage of internal curing agent (ICA), super absorbent polymer (SAP) in self compacting
concrete (SCC) at 28 days. To evaluate the optimum percentage of SAP in SCC, the input
parameters such as weight of cement, fine aggregate, coarse aggregate, fly ash, super-
plasticizer (SP) and viscosity modifying agent (VMA) and SAP are identified. A detailed
research was carried out having a single hidden layer with six nodes for detremining the
strength of the concrete. A total of 240 different data sets of SCC were collected from the
ready-mix factory. Training data sets comprises 80 data entries and the remaining data entries
are divided between the testing and validation data set. The performance of best possible
architecture was identified. An attempt was also made to determine the compressive strength
of self compacting self curing concrete (SCSCC) using the determined optimum percentage
of chemical admixtures. A concrete mix of M40 grade was proportioned. The strength
obtained using ANN was experimentally analysed and the same strength seems to be
achieved in 28 days of self-curing. Also, the workability properties of SCSCC using SAP as
ICA satisfy the guidelines specified by EFNARC.

Online publication : 2017
Publication type : full_text
Public price (Euros) : 0.00