Innovative AI-driven software for fire safety design: Implementation in vast open structure

Ruchit Parekh 1, * and Charles Smith 2

1 Department of Engineering Management, Hofstra University, New York, USA.
2 Department of Computer Science, Hofstra University, New York, USA.
 
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2024, 12(02), 741–750.
Article DOI: 10.30574/wjaets.2024.12.2.0345
Publication history: 
Received on 05 July 2024; revised on 11 August 2024; accepted on 14 August 2024
 
Abstract: 
Fire modeling plays a crucial role in building fire safety assessments, yet it often incurs significant costs. This research introduces an AI-driven software, the Intelligent Fire Engineering Tool (IFETool), designed to accelerate fire safety evaluations and efficiently determine design constraints. Initially, a comprehensive numerical database focusing on atrium fires was established, accounting for key building and fire-related parameters. A deep learning model was then trained to forecast the progression of tenable smoke visibility, temperature, and CO levels with an impressive accuracy of 97%. The descending tenability profile was subsequently analyzed to estimate the available safe egress time (ASET) and to evaluate the fire safety of atriums with intricate roof designs and slab extensions. This AI tool enables swift assessments of proposed atrium fire engineering designs and offers valuable suggestions for potential improvements. Lastly, operational guidelines for IFETool are provided, catering to common atrium fire safety design tasks.
 
Keywords: 
Smart Building; Fire Engineering; AI Fire Design; Fire Safety; AI Software; Fire AI Design; Fire Design; AI Safety; Fire Engineering
 
Full text article in PDF: