«Automation and Informatization of the fuel and energy complex»

Using convolutional neural network for fire detection as part of an automated fire and explosion safety system

UDC: 004.896
DOI: -

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: computer vision, panoramic camera, fire detection, deep learning, 3D model

Annotation:

The authors of the article consider a fire detection system based on the use of a convolutional neural network, a panoramic video surveillance camera and a 3D model of an object as well as the place of this system as part of an automated fire and explosion safety system (AFESS) of a technological facility. The system, based on the images from a panoramic video surveillance camera, uses a neural network with YOLOv5 architecture to detect fires and a 3D model to determine their exact location. In terms of its functions, the system is part of the AFESS in the category of automated fire and explosion protection system (AFEPS) and is at the level of an automated fire detection system (AFDS). AFDS technical solutions, such as the use of temperature, smoke and flame sensors, gas analyzers as well as visual detection methods based on thermal imagers and camera images are overviewed. Specific functions of the system as part of the AFEPS are defined: automatic early detection of fires; determination of the exact location of the ignition source and its transmission to the fire service; presentation of photo and video materials from the fire site for subsequent analysis of the situation as well as video images of what is happening at the fire site in real time. An algorithm for the interaction of this system with AFEPS in the event of a fire is proposed. The possibility of using the system in combination with other AFDS means, such as smoke detectors and gas analyzers, is also considered. It is shown that the use of the considered system as part of the AFEPS allows expanding the capabilities of the AFDS, especially for large objects located outdoors.

Bibliography:

1. Topol'skiy N.G., Teterin I.M., Gudkov A.S. Osnovy sozdaniya avtomatizirovannykh sistem pozharnoy bezopasnosti ob"ektov: ucheb. posobie. – M.: Akad. Gos. protivopozhar. sluzhby MChS Rossii, 2006. – 60 s.
2. Opredelenie sostava programm v spetsial'nom programmnom obespechenii avtomatizirovannykh sistem pozharovzryvobezopasnosti ob"ektov / N.G. Topol'skiy, A.V. Kryuchkov, D.S. Grachev, K.A. Mikhaylov // Pozharovzryvobezopasnost'. – 2018. – T. 27, № 7–8. – S. 67–73. – DOI: 10.18322/pvb.2018.27.7-8.67-73
3. Yilmaz G., Karlik S.E. A distributed optical fiber sensor for temperature detection in power cables // Sensors and Actuators A: Physical. – 2006. – Vol. 125, Issue 2. – P. 148–155. – DOI: 10.1016/j.sna.2005.06.024
4. A Durable, Flexible, Large-Area, Flame-Retardant, Early Fire Warning Sensor with Built-In Patterned Electrodes / Khan Fawad, Wang Shanchi, Ma Zhewen [et al.] // Small Methods. – 2021. – Vol. 5, Issue 4. – Article No. 2001040. – DOI: 10.1002/smtd.202001040
5. Barrett R. CO Fire Detection: A Useful Technique? Report on a Test Programme and Discusses the Issues Involved in the Use of CO Fire Detectors // Fire Safety Engineer. – 2000. – Vol. 7. – P. 20–25.
6. A survey on gas sensing technology / Liu Xiao, Cheng Sitian, Liu Hong [et al.] // Sensors. – 2012. – Vol. 12, No. 7. – P. 9635–9665. – DOI: 10.3390/s120709635
7. Design of Fire and Gas Detection System for a Process Plant: A Review / A. Prashanth Kumar Reddy, E. Sathwik Reddy, T.N.S.S. Bhaskar [et al.] // Advances in Industrial Safety. – Singapore: Springer, 2020. – P. 271–280. – DOI: 10.1007/978-981-15-6852-7_24
8. Jackson M.A., Robins I. Gas sensing for fire detection: Measurements of CO, CO2, H2, O2, and smoke density in European standard fire tests // Fire Safety J. – 1994. – Vol. 22, Issue 2. – P. 181–205. – DOI: 10.1016/0379-7112(94)90072-8
9. Bogue R. Sensors for fire detection // Sensor Review. – 2013. – Vol. 33, Issue 2. – P. 99–103. – DOI: 10.1108/02602281311299635
10. Investigation of Multi-Sensor Algorithms for Fire Detection / J.A. Milke, M.E. Hulcher, C.L. Worrell [et al.] // Fire Technology. – 2003. – Vol. 39. – P. 363–382. – DOI: 10.1023/A:1025378100781
11. Qualey J.R. Fire Test Comparisons of Smoke Detector Response Times // Fire Technology. – 2000. – Vol. 36. – P. 89–108. – DOI: 10.1023/A:1015498224060
12. Conforti F. Multi-sensor, multi-criteria detectors are better // Proceedings AUBE. – 1999. – P. 247–249.
13. Xu Lijun, Yan Yong. A New Flame Monitor with Triple Photovoltaic Cells // Proceedings of 2005 IEEE Instrumentation and Measurement Technology Conf., Ottawa, ON, Canada, May 16–19, 2005. – IEEE, 2005. – P. 2253–2257. – DOI: 10.1109/IMTC.2005.1604577
14. PbS Colloidal Quantum Dot Visible-Blind Photodetector for Early Indoor Fire Detection / A. de Iacovo, C. Venettacci, L. Colace [et al.] // IEEE Sensors J. – 2017. – Vol. 17, Issue 14. – P. 4454–4459. – DOI: 10.1109/JSEN.2017.2710301
15. Fire Detection Using Computer Vision / T. Zaman, M. Hasan, S. Ahmed, S. Ashfaq // 2018 IEEE 61st Int. Midwest Symposium on Circuits and Systems (MWSCAS), Windsor, ON, Canada, Aug. 05–08, 2018. – P. 356–359. – DOI: 10.1109/MWSCAS.2018.8623842
16. Qi Xiaojun, Ebert J. A computer vision-based method for fire detection in color videos // Int. J. of Imaging. – 2009. – Vol. 2, Issue S09. – P. 22–34.
17. Evsikov A.A., Samarin I.V. Obnaruzhenie ochagov vozgoraniya na tekhnologicheskikh ob"ektakh s ispol'zovaniem svertochnoy neyronnoy seti // Pozharovzryvobezopasnost'. – 2023. – T. 32, № 5. – S. 40–48. – DOI: 10.22227/0869-7493.2023.32.05.40-48
18. YOLOv5 by Ultralytics / G. Jocher, A. Chaurasia, A. Stoken [et al.]. – Version 7.0. – 2020. – URL: https://github.com/ultralytics/yolov5
19. Evsikov A.A., Samarin I.V. Raspoznavanie vozgoraniy na panoramnom izobrazhenii s ispol'zovaniem svertochnoy neyronnoy seti // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 12(605). – S. 5–10. – DOI: 10.33285/2782-604X-2023-12(605)-5-10
20. Evsikov A.A., Samarin I.V. Obnaruzhenie i opredelenie tochnogo mestopolozheniya ochaga vozgoraniya s ispol'zovaniem svertochnoy neyronnoy seti, panoramnogo izobrazheniya i 3D-modeli ob"ekta nablyudeniya // Pozharovzryvobezopasnost'. – 2024. – T. 33, № 4. – S. 13–21. – DOI: 10.22227/0869-7493.2024.33.04.13-21