relation: https://khub.utp.edu.my/scholars/7602/
title: Mix design proportion for strength prediction of rubbercrete using artificial neural network
creator: Awang, A.
creator: Mohammed, B.S.
creator: Mustafa, M.R.
description: Data on the mix design of rubbercrete experiments are available throughout the literature and utilized in this paper to provide a platform for prediction of strength to obtained predetermined mix design. Using artificial neural network (ANN), the strengths of rubbercrete are predicted using literature data with water-cement ratio, percentage of CR, cement, fine aggregates, coarse aggregates and water as inputs. The desired output are identified as the compressive strength, flexural strength, splitting tensile strength and modulus elasticity of rubbercrete. From the result, it is concluded that different data set, different neural network parameters are required. The overall regression plot for the prediction achieved a correlation coefficient, R of 0.99157. With this prediction tool, the neural network can be used as mix design for selection of rubbercrete mix proportions to facilitate the application and utilization of rubbercrete, not only the academic field, but also in the industry. © 2016 Taylor & Francis Group, London.
publisher: CRC Press/Balkema
date: 2016
type: Conference or Workshop Item
type: PeerReviewed
identifier:   Awang, A. and Mohammed, B.S. and Mustafa, M.R.  (2016) Mix design proportion for strength prediction of rubbercrete using artificial neural network.  In: UNSPECIFIED.     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009725360&doi=10.1201%2fb21942-108&partnerID=40&md5=5abe5deefffdb77cf4719cd71a23e8e3
relation: 10.1201/b21942-108
identifier: 10.1201/b21942-108