Author/Authors :
Paratibha، Aggarwal نويسنده Civil Engineering Department, National Institute of Technology, Kurukshetra- 136118, India. , , Yogesh,، Aggarwal نويسنده Civil Engineering Department, National Institute of Technology, Kurukshetra- 136118, India. , , Kapil، Grover نويسنده Civil Engineering Department, National Institute of Technology, Kurukshetra- 136118, India. , , bhat، subzar ahmad نويسنده Civil Engineering Department, National Institute of Technology, Kurukshetra- 136118, India. ,
Abstract :
Concrete mix design is a process of proportioning of ingredients in right quantities. Although it is based on sound technical principles and heuristics, the entire process is not in the realm of science and precise mathematical calculations. This paper demonstrates the applicability of Artificial Neural Networks (ANN) and Fuzzy Logic Model for approximate proportioning of concrete mixes with Foundry Sand. For ANN, a trained back propagation neural network model and fuzzy set models are developed to learn experimental data to predict 28-day compressive strength and slump flow, containing 43 concrete mixtures. Inputs of the Fuzzy Logic model and ANN model are cement, water, foundry sand, super plasticizer, water cement ratio, sand (designated as fine aggregate) and coarse aggregate. Outputs are 28-day concrete compressive strength and slump flow for different models.
