Strength Prediction of High Early Strength Concrete by Artificial Intelligence
Panga Narasimha Reddy1, Javed Ahmed Naqash2

1Panga Narasimha Reddy, Research Scholar, Department of Civil Engineering, National Institute of Technology, Srinagar (Jammu and Kashmir), India.
2Dr. Javed Ahmed Naqash, Associate Professor, Civil Engineering, National Institute of Technology, Srinagar (Jammu and Kashmir), India.

Manuscript received on 18 February 2019 | Revised Manuscript received on 27 February 2019 | Manuscript published on 28 February 2019 | PP: 330-334 | Volume-8 Issue-3, February 2019 | Retrieval Number: C5913028319/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The evaluation of the combined effect of alccofine, chemical admixture and curing age to compressive strength prediction of High early strength concrete (HESC) in view of its increasing application in construction industries, is a novelty. Concrete is generally a mixture of different materials and it is a difficult task to predict the strength of HESC. However, it seems that a soft computing could save time and money. In this study, fuzzy logic (FL) and artificial neural network (ANN) models were developed to predict the strength of High Early Strength Concrete. This research paper presents the effect on strength of the concrete with alccofine (i.e. 25%) as a constant replacement of cement for all concrete mixes and several non-chloride hardening accelerator ratios (0-1.8) for different water to binder contents (i.e. 0.38, 0.4 and 0.45). The compressive strength was evaluated at 3, 7 and 28 days resulting in a total of 36 data sets that were used in FL and ANN. The results of the measured compressive strength were compared to values predicted from FL and ANNs. The results showed that ANN can be used successfully to strength prediction of high early strength concrete wherein the ANN model performed better than the FL model. The extrapolation capacity of FL and ANN was satisfactory.
Keywords: High Early Strength Concrete, Artificial Neural Network, Fuzzy Logic, Compressive Strength, Non-Chloride Hardening Accelerator, Prediction

Scope of the Article: Fuzzy Logic