Title:
Five-Layer Fuzzy Inference System to Design a Concrete Mixture, Based on ACI Method
Author(s):
by Sunil Y. Kute and Rajeev S. Kale
Publication:
Materials Journal
Volume:
110
Issue:
6
Appears on pages(s):
629-640
Keywords:
defuzzification; fuzzy inference system; fuzzy logic; linguistic variables; membership function; mixture design
DOI:
10.14359/51686330
Date:
11/1/2013
Abstract:
Soft computing includes fuzzy logic (FL), neural networks, probabilistic reasoning, and genetic algorithms. Today, techniques or a combination of techniques from all these areas are used to design an intelligence system. FL deals with issues such as forming impressions and reasoning on a semantic or linguistic level. The present research work investigates the application of FL to under¬stand the design stipulations, specification of available materials, and to estimate the correct proportioning of ingredients of concrete mixtures to meet the given requirements. In the present work, an attempt has been made to design a five-layer fuzzy inference system (FIS) to estimate the quantity of ingredients of concrete, based on the American Concrete Institute (ACI) method of concrete mixture design. The results obtained from the five-layer FIS are evaluated and compared with a traditional method of concrete mixture design. The results show that FIS has strong potential as a feasible tool for estimating the ingredients of concrete to meet the design requirements.