Issue |
E3S Web Conf.
Volume 627, 2025
VI International Conference on Geotechnology, Mining and Rational Use of Natural Resources (GEOTECH-2025)
|
|
---|---|---|
Article Number | 02016 | |
Number of page(s) | 5 | |
Section | Geoecology and Rational Use of Natural Resources, Environmental Protection | |
DOI | https://doi.org/10.1051/e3sconf/202562702016 | |
Published online | 16 May 2025 |
Approach to prototyping a technical device for fire detection based on the principles of artificial intelligence
1 Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, Russia
2 Tashkent Institute of Irrigation and Agricultural Mechanization Engineers” National Research University, Tashkent, Uzbekistan
* Corresponding author: doronin_as@spbstu.ru
The aim of the study is to justify the developed prototype of a technical device that uses machine learning methods for early detection of fires in order to minimise damage and save human lives. The authors formulated a hypothesis about the expediency of expanding the frequency range within which the fire automation system detects the primary signs of fire in order to increase the efficiency of its operation. To test the hypothesis, a prototype has been developed, based on the typical structure of the existing fleet of fire automation systems, including an additional unit operating on the principles of artificial intelligence. The article describes an additional unit working on the principles of fuzzy logic and convolutional neural networks to analyse the data coming from video cameras and fire detectors in order to determine the fire in the early stages of ignition.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.