Five layers Artificial Neural Network system to design a concrete mix, based on D.O.E. method

Soft computing tools neural network and fuzzy logic can be used for the problems, where no solution algorithm is known. The mix design of concrete can be put under same category of problem. Again, development of required concrete mix, which required large sets of trial, is a very complex problem in itself. The feature of computer aided soft computing tools can be used to obtain perfect relationship between various design parameters of concrete mix (Aggregate/Cement, Water/Cement, Workability, Durability, Strength) and reduces the requirement of large number of trails. A Artificial Neural Network based five layer system has been proposed to design a concrete mix, based on Department of Environmental Engineering (D.O.E.) method. The results obtained from five layers artificial neural network system are evaluated and compared with traditional method of concrete mix design (D.O.E.). The result shows that ANN has strong potential as a feasible tool for estimating the ingredients of concrete to meet the design requirements.