Preprint
Article

This version is not peer-reviewed.

Responsive Architecture in Practice: BIM/DT/AI/IoT for Dynamic Evacuation—Case Studies

Submitted:

06 February 2026

Posted:

06 February 2026

You are already at the latest version

Abstract
Dynamic fire-safety systems are no longer futuristic; they are a viable alternative to rigid, prescriptive approaches to occupant protection and evacuation. This paper analyses three case studies where Building Information Modelling (BIM), a Digital Twin (DT), Internet-of-Things (IoT) sensor networks, Artificial Intelligence (AI) control algorithms, and dynamic evacuation signage were integrated to support a Dynamic Fire-Safety System (DFS). Secondary research covered a university building in Lille, the Beijing Capital Airport Emergency Center, and a shopping mall in the Taipei 101 high-rise complex. All facilities meet formal requirements, yet a BIM/DT/IoT/AI layer suggests better performance under fire conditions. Methods included a structured literature review, BIM-based fire modelling in Fire Dynamics Simulator (FDS), evacuation simulations, and comparison of static versus dynamic paradigms. The workflow reconstructs fire–evacuation scenarios to assess time-dependent tenability, exit viability, and congestion-driven bottlenecks. In Lille, DFS serves as a computational laboratory for design decisions; in Beijing, as a decision-support core controlling signage in near real time; and in Taipei 101, as an optimisation-driven strategy for multi-storey occupant populations. Across the cases, DFS-oriented solutions are reported to shorten evacuation time and/or increase the probability of successful evacuation relative to static arrangements. Reported benefits depend on clear cue visibility and timely actuation of guidance signals. Implications for Poland are discussed: prescriptive rules should remain a baseline, while complex facilities may adopt performance-based solutions grounded in BIM/DT/IoT/AI, provided equivalence to conventional protection is demonstrated.
Keywords: 
;  ;  ;  ;  ;  ;  ;  ;  
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Prerpints.org logo

Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.

Subscribe

Disclaimer

Terms of Use

Privacy Policy

Privacy Settings

© 2026 MDPI (Basel, Switzerland) unless otherwise stated