Application of artificial neural network to building compartment design for fire safety

Authors:
Eric Wai Ming Lee;Po Chi Lau;Kitty Kit Yan Yuen
Affiliations:
Fire Safety and Disaster Prevention Research Group, Department of Building and, Construction, City University of Hong Kong, Kowloon Tong, Hong Kong (SAR), People of Republic of China;Asian Institute of Intelligent Buildings, c/o Department of Building and Construction, City University of Hong Kong, Kowloon Tong, Hong Kong (SAR), People of Republic of China;Fire Safety and Disaster Prevention Research Group, Department of Building and, Construction, City University of Hong Kong, Kowloon Tong, Hong Kong (SAR), People of Republic of China
Venue:
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
Year:
2006

Citing 4
Cited 1

Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Bayesian neural networks for classification: how useful is the evidence framework

Neural Networks
Metamodeling using extended radial basis functions: a comparative approach

Engineering with Computers
A hybrid neural network model for noisy data regression

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Computational fluid dynamics (CFD) techniques are currently widely adopted to simulate the behaviour of fire but it requires extensive computer storage and lengthy computational time. Using CFD in the course of building design optimization is theoretically feasible but requires lengthy computational time. This paper proposes the application of an artificial neural network (ANN) approach as a quick alternative to CFD models. A novel ANN model that is denoted as GRNNFA has been developed specifically for fire studies. As the available training samples may not be sufficient to describe system behaviour, especially for fire data, additional knowledge of the system is acquired from a human expert. The expert intervention network training is developed to remedy the established system response surface. A genetic algorithm is applied to evaluate the close optimum set of the design parameters.