Gamaleldin, Mohamed.pdf (40.25 MB)
Improving Fire Safety Systems Based On Internet Of Things And Deep Learning
thesis
posted on 2021-12-21, 16:26 authored by Mohamed GamaleldinStructure fires are one of the main concerns for fire safety systems. The actual fire safety of a
building depends on not only how it is designed and constructed, but also on how it is operated. Computational fluid dynamics software is the current solution to reduce the casualties in
the fire circumstances. However, it consumes hours to provide the results in some cases that
makes it hard to run in real-time. It also does not accept any changes after starting the simulation, which makes it unsuitable for running in the dynamic nature of the fire. On the other
hand, the current evacuation signs are fixed, which might guide occupants and firefighter to
dangerous zones.
In this research, we present a smoke emulator that runs in real-time to reflect what is happening on the ground-truth. This system is achieved using a light-weight smoke emulator engine,
deep learning, and internet of things. The IoT sensors are sending the measurements to correct the emulator from any deviation and reflect events such as fire starting, people movement,
and the door’s status. This emulator helps the firefighter by providing them with a map that
shows the smoke development in the building. They can take a snapshot from the current status of the building and try different virtual evacuation and firefighting plans to pick the best
and safest for them to proceed. The system will also control the exit signs to have adaptive
exit routes that guide occupants away from fire and smoke to minimize the exposure time to
the toxic gases
History
Language
EnglishDegree
- Master of Applied Science
Program
- Electrical and Computer Engineering
Granting Institution
Ryerson UniversityLAC Thesis Type
- Thesis
