Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/27636
Title: Neural network approach to grading maintainability of wet areas in high rise buildings
Authors: TAN SHAN SHAN
Keywords: Maintainability, grading system, artificial neural networks, wet areas, sensitivity analysis
Issue Date: 16-Dec-2003
Source: TAN SHAN SHAN (2003-12-16). Neural network approach to grading maintainability of wet areas in high rise buildings. ScholarBank@NUS Repository.
Abstract: A maintainability grading system using artificial neural networks to enhance decision-making of wet area design was developed. Constructed from 16 influencing parameters of design, material, construction and maintenance, the model was found to be robust with low approximation error of 0.001 and low generalization error of 0.005. Gradings for wet areas in typical office, school and industrial buildings were found to be 92, 87 and 83 respectively. Sensitivity analysis to study the effect of each input parameter and the relationships inherent to the data set identified waterproofing selection, sanitary fitting design and material performance to demonstrate higher influence in affecting wet area maintainability.
URI: http://scholarbank.nus.edu.sg/handle/10635/27636
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Title_Page.pdf45.01 kBAdobe PDF

OPEN

NoneView/Download
ACKNOWLEDGEMENT.pdf56.95 kBAdobe PDF

OPEN

NoneView/Download
Table_of_Contents.pdf94.91 kBAdobe PDF

OPEN

NoneView/Download
Summary.pdf73.15 kBAdobe PDF

OPEN

NoneView/Download
List_of_Tables.pdf78.19 kBAdobe PDF

OPEN

NoneView/Download
List_of_Figures.pdf72.21 kBAdobe PDF

OPEN

NoneView/Download
List_of_Plates.pdf71.98 kBAdobe PDF

OPEN

NoneView/Download
Thesis.pdf4.71 MBAdobe PDF

OPEN

NoneView/Download
Bibliography.pdf155.9 kBAdobe PDF

OPEN

NoneView/Download
Appendices.pdf389.13 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

251
checked on Dec 11, 2017

Download(s)

1,495
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.