Inductive Classifying Artificial Network for Fly Ash Type Categorization

Nowadays, fly ash is a common ingredient of concrete and may constitute up to 50% by weight of the total binder material. Incorporation of fly ash in Portland-cement concrete is highly desirable due to technological, economic, and environmental benefits. This article demonstrates the use of artificial intelligence neural networks for the classification of data. ICAN stands for Inductive Classifying Artificial Network and is used to conveniently describe Kohonen’s Selforganizing feature map (SOFM) for fly ash type categorization using chemical attributes as inputs. Eight chemical attributes have been considered in classification as these play their role in performance of concrete. The application of ICAN permitted to differentiate three main groups of fly ashes. This is in contrast to ASTM classification of fly ashes into F and C classes based on percentage of Calcium Oxide (CaO) alone. Three one-dimensional ICANs of 16 neurons, 24 neurons and 32 neurons were explored. The overall cla...

• Type: Journal
• Year: 2007
• Where: ENGL
• Authors: M. C. Nataraja, M. A. Jayaram, C. N. Ravikumar
• Keywords: Ash Type Categorization, Concrete, ENGL 2007, Fly Ash