eprintid: 248
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/00/02/48
datestamp: 2023-11-09 15:15:53
lastmod: 2023-11-09 15:15:53
status_changed: 2023-11-09 15:13:38
type: article
metadata_visibility: show
creators_name: Noorzaei, J.
creators_name: Hakim, S.J.S.
creators_name: Jaafar, M.S.
creators_name: Abang Ali, A.A.
creators_name: Thanoon, W.A.M.
title: An optimal architecture of artificial neural network for predicting compressive strength of concrete
ispublished: pub
keywords: Coarse aggregate; Data points; Feasible tools; Superplasticiser, Architecture; Backpropagation; Compressive strength; Mean square error; Neural networks; Plasticizers; Silica, Concretes
note: cited By 15
abstract: This research work focuses on development and application of Artificial Neural Networks (ANNs) for prediction of compressive strength of concrete after 28 days. To predict the compressive strength of concrete, six input parameters namely, cement, water, silica fume, superplasticiser, fine aggregate and coarse aggregate were identified. A detailed study was carried out and it is shown that, the performance of the 6-12-6-1 architecture was the best amongst all possible architecture. The Mean Square Error (MSE) for the training set was 5.33 for the 400 training data points, 6.13 for the 100 validation data points and 6.02  for the 139 testing data points. The results of the present investigation indicate that ANNs have strong potential as a feasible tool for predicting the compressive strength of concrete.
date: 2007
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-35648977118&partnerID=40&md5=94c3af6959c6264cb3217f1aa4060a0b
full_text_status: none
publication: Indian Concrete Journal
volume: 81
number: 8
pagerange: 17-24
refereed: TRUE
issn: 00194565
citation:   Noorzaei, J. and Hakim, S.J.S. and Jaafar, M.S. and Abang Ali, A.A. and Thanoon, W.A.M.  (2007) An optimal architecture of artificial neural network for predicting compressive strength of concrete.  Indian Concrete Journal, 81 (8).  pp. 17-24.  ISSN 00194565