Artificial Neural Network Approach for Grading of Maintainability in Wet Areas of High-Rise Buildings
- 1 March 2004
- journal article
- research article
- Published by Informa UK Limited in Architectural Science Review
- Vol. 47 (1), 27-42
- https://doi.org/10.1080/00038628.2004.9697022
Abstract
A grading system using artificial neural networks to enhance decision-making of wet area design was developed. The model was derived from condition survey of 450 tall buildings and in-depth assessment of a further 120 tall buildings and interviews with the relevant building professionals. The system allows comparison of various alternative designs, materials, construction and maintenance practices, so as to achieve optimum solutions of technical attributes that lead to minimum life cycle maintenance cost.Keywords
This publication has 11 references indexed in Scilit:
- Statistical modelling of artificial neural networks using the multi-layer perceptronStatistics and Computing, 2003
- Factors Affecting Water-Tightness in Wet Areas of High-Rise Residential BuildingsArchitectural Science Review, 2002
- Comparison of Two Maintainability ProgramsJournal of Construction Engineering and Management, 2001
- Prediction and optimization of life-cycle costs in early designBuilding Research & Information, 2000
- A Multiobjective and Stochastic System for Building Maintenance ManagementComputer-Aided Civil and Infrastructure Engineering, 2000
- Priority setting in maintenance management: a modified multi-attribute approach using analytic hierarchy processConstruction Management and Economics, 1998
- Rationalisation of building maintenance by Markov decision models: a pilot case studyJournal of the Operational Research Society, 1998
- Financial management of planned maintenance for housing associationsConstruction Management and Economics, 1997
- Classifying building failure by causeBuilding Research & Information, 1992
- Parallel Distributed ProcessingPublished by MIT Press ,1986