Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning : Proof of Concept

Martinsson, John ; Runefors, Marcus LU orcid ; Frantzich, Håkan LU ; Glebe, Dag ; McNamee, Margaret LU and Mogren, Olof (2022) In Fire Technology 58(6). p.3385-3403
Abstract

Fires are a major hazard resulting in high monetary costs, personal suffering, and irreplaceable losses. The consequences of a fire can be mitigated by early detection systems which increase the potential for successful intervention. The number of false alarms in current systems can for some applications be very high, but could be reduced by increasing the reliability of the detection system by using complementary signals from multiple sensors. The current study investigates the novel use of machine learning for fire event detection based on acoustic sensor measurements. Many materials exposed to heat give rise to acoustic emissions during heating, pyrolysis and burning phases. Further, sound is generated by the heat flow associated... (More)

Fires are a major hazard resulting in high monetary costs, personal suffering, and irreplaceable losses. The consequences of a fire can be mitigated by early detection systems which increase the potential for successful intervention. The number of false alarms in current systems can for some applications be very high, but could be reduced by increasing the reliability of the detection system by using complementary signals from multiple sensors. The current study investigates the novel use of machine learning for fire event detection based on acoustic sensor measurements. Many materials exposed to heat give rise to acoustic emissions during heating, pyrolysis and burning phases. Further, sound is generated by the heat flow associated with the flame itself. The acoustic data collected in this study is used to define an acoustic sound event detection task, and the proposed machine learning method is trained to detect the presence of a fire event based on the emitted acoustic signal. The method is able to detect the presence of fire events from the examined material types with an overall F-score of 98.4%. The method has been developed using laboratory scale tests as a proof of concept and needs further development using realistic scenarios in the future.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Acoustic emissions, Artificial intelligence, Deep neural networks, Fire detection, Machine learning, Sound
in
Fire Technology
volume
58
issue
6
pages
19 pages
publisher
Springer
external identifiers
  • scopus:85137843831
ISSN
0015-2684
DOI
10.1007/s10694-022-01307-1
language
English
LU publication?
yes
id
467ec70e-fb64-42a8-97e5-23ac87a9b287
date added to LUP
2022-12-02 15:25:17
date last changed
2023-11-21 16:56:40
@article{467ec70e-fb64-42a8-97e5-23ac87a9b287,
  abstract     = {{<p>Fires are a major hazard resulting in high monetary costs, personal suffering, and irreplaceable losses. The consequences of a fire can be mitigated by early detection systems which increase the potential for successful intervention. The number of false alarms in current systems can for some applications be very high, but could be reduced by increasing the reliability of the detection system by using complementary signals from multiple sensors. The current study investigates the novel use of machine learning for fire event detection based on acoustic sensor measurements. Many materials exposed to heat give rise to acoustic emissions during heating, pyrolysis and burning phases. Further, sound is generated by the heat flow associated with the flame itself. The acoustic data collected in this study is used to define an acoustic sound event detection task, and the proposed machine learning method is trained to detect the presence of a fire event based on the emitted acoustic signal. The method is able to detect the presence of fire events from the examined material types with an overall F-score of 98.4%. The method has been developed using laboratory scale tests as a proof of concept and needs further development using realistic scenarios in the future.</p>}},
  author       = {{Martinsson, John and Runefors, Marcus and Frantzich, Håkan and Glebe, Dag and McNamee, Margaret and Mogren, Olof}},
  issn         = {{0015-2684}},
  keywords     = {{Acoustic emissions; Artificial intelligence; Deep neural networks; Fire detection; Machine learning; Sound}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{3385--3403}},
  publisher    = {{Springer}},
  series       = {{Fire Technology}},
  title        = {{A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning : Proof of Concept}},
  url          = {{http://dx.doi.org/10.1007/s10694-022-01307-1}},
  doi          = {{10.1007/s10694-022-01307-1}},
  volume       = {{58}},
  year         = {{2022}},
}