Options
A comparative study of deep learning and Evac4BIM in building evacuation design
Citation Link: https://doi.org/10.15480/882.13518
Publikationstyp
Conference Paper
Date Issued
2024-09-18
Sprache
English
Author(s)
Technische Universität München
Technische Universität München
Technische Universität München
TORE-DOI
Start Page
481
End Page
488
Citation
35. Forum Bauinformatik, fbi 2024: 481-488
Contribution to Conference
Publisher
Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen
Peer Reviewed
true
The integration of pedestrian simulations into the design process of a building is an inevitable step to improve its evacuation performance. This becomes particularly important during the initial design stages, when countless building configurations are explored and evaluated through interdisciplinary discussions. However, conventional simulators typically operate as stand-alone tools, necessitating several manual export and conversion steps and time-consuming runtimes. To address these challenges, recent developments have led to the integration of Building Information Modeling (BIM) with the widely-used pedestrian simulator Pathfinder in an open source tool called Evac4BIM. In this study, we explore the potential for further accelerating the generation and integration of evacuation simulation results through neural networks, trained on a comprehensive, synthetic dataset to enable real-time predictions. Subsequently, we analyze and compare the applicability of Evac4BIM and our deep learning approach in terms of practicality and accuracy.
Subjects
Building information modeling
Deep learning
Evacuation performance
Pedestrian simulation
DDC Class
720: Architecture
624: Civil Engineering, Environmental Engineering
004: Computer Sciences
006: Special computer methods
Publication version
publishedVersion
Loading...
Name
A Comparative Study of Deep Learning and Evac4BIM in Building Evacuation Design.pdf
Type
Main Article
Size
397.93 KB
Format
Adobe PDF