scholarly journals Computer Vision Application for Early Stage Smoke Detection on Ships

2016 ◽  
Vol 52 (1) ◽  
pp. 63-80
Author(s):  
Miroslav Bistrović ◽  
Jasmin Čelić ◽  
Domagoj Komorčec

Nowadays, ship’s engine room is fire protected by automatic fire fighting systems, usually controlled from a place located outside the engine room. In order to activate the water mist extinguishing system automatically, at least two different fire detectors have to be activated. One of these detectors is a flame detector that is not hampered by various air flows caused by ventilation or draft and is rapidly activated and the other is smoke detector which is hampered by these flows causing its activation to be delayed. As a consequence, the automatic water mist extinguishing system is also delayed, allowing for fire expansion and its transfer to surrounding rooms. In addition to reliability of the ship’s fire detection system as one of the crucial safety features for the ship, cargo, crew and passengers, using a systematic approach in this research the emphasis is placed on the application of new methods in smoke detection such as the computer image processing and analysis, in order to achieve this goal. This paper describes the research carried out on board ship using the existing marine CCTV systems in early stages of smoke detection inside ship’s engine room, which could be seen as a significant contribution to accelerated suppression of unwanted consequences.


Fire ◽  
2021 ◽  
Vol 4 (4) ◽  
pp. 85
Author(s):  
Ter-Ki Hong ◽  
Seul-Hyun Park

A fire during manned space exploration can cause serious casualties and disrupt the mission if the initial response is delayed. Therefore, measurement technology that can detect fire in the early stage of ignition is important. There have been a number of works that investigate the smoke behaviors in microgravity as the foundation for a reliable method for sensing a fire during spaceflight. For space missions to the outer planets, however, a strategy of detecting smoke as an indicator of fire should be adjusted to cover the fire scenario that can be greatly affected by changes in gravity (microgravity, lunar, Mars, and Earth gravity). Therefore, as a preliminary study on fire detectors of the manned pressurized module, the present study examined the smoke particle behavior and detection characteristics with respect to changes in gravity using numerical analysis. In particular, the effects of the combination of buoyancy and ventilation flow on the smoke particle movement pattern was investigated to further improve the understanding of the fire detection characteristics of the smoke detector, assuming that a fire occurred in different gravity environments inside the pressurized module. To this end, we modeled the internal shape of Destiny and performed a series of numerical analysis using the Fire Dynamics Simulator (FDS). The findings of this study can provide basic data for the design of a fire detection system for manned space exploration modules.



2011 ◽  
Vol 255-260 ◽  
pp. 1404-1408 ◽  
Author(s):  
Zhen Na Zhang ◽  
Hong Bing Chen

The aspirating smoke detection (ASD) system has been widely used in large space buildings. It plays an important role on fire detection at its early stage. In this paper, the model of large space building was established for the simulation study on the response performance of the ASD system. The investigation on the effect of fire location, sampling hole space and pipe length on the responding time, was carried out. The results showed that the responding time of FIRE B (fire close to side wall) is much delayed than that of FIRE A (fire in centre); the increase of sampling hole space and pipe length leads to the delay of the responding time.



Author(s):  
EVA AISAH HW ◽  
ROHMAT TULLOH ◽  
SUGONDO HADIYOSO ◽  
DADAN NUR RAMADAN

ABSTRAKKebakaran rumah seringkali disebabkan oleh kelalaian manusia. Oleh karena itu diperlukan sebuah sistem yang dapat mendeteksi kebakaran secara online realtime. Pada studi ini, dirancang dan diimplementasikan sebuah sistem pendeteksi kebakaran dengan sejumlah sensor untuk mengukur beberapa parameter lingkungan. Sistem ini dilengkapi dengan pengambil keputusan menggunakan metode fuzzy logic. Parameter lingkungan yang diukur mencakup suhu ruangan, asap dan api yang kemudian dapat dimonitor secara real-time melalui web interface menggunakan Internet of Things platform. Pengujian menunjukkan bahwa detektor dapat mendeteksi api dengan jarak hingga 100 cm dengan akurasi mencapai 100%. Pengujian sensor suhu menunjukkan akurasi 98.79%, sementara itu detektor asap memperoleh akurasi 77.81%. Sistem ini mampu mengirimkan data dengan rata-rata delay transmisi 0.62 detik. Sistem usulan ini diharapkan dapat menyediakan pemantauan kondisi suatu ruangan secara real-time.Kata kunci: Kebakaran, Real-Time, Deteksi, Fuzzy, Internet Of Things ABSTRACTHouse fires are often caused by human error. Therefore, we need a system that can detect fires online real-time. In this study, a fire detection system with a number of sensors is designed and implemented to measure several environmental parameters. This system is equipped with a decision maker using the fuzzy logic method. The environmental parameters measured include room temperature, smoke and fire which can then be monitored in real time via a web interface using the Internet of Things platform. Tests show that the detector can detect fires with a distance of up to 100 cm with an accuracy of up to 100%. The temperature sensor test shows an accuracy of 98.79%, while the smoke detector generates an accuracy of 77.81%. This system is capable of sending data with an average transmission delay of 0.62 seconds. This proposed system is expected to provide realtime monitoring of the condition of a room.Keywords: Fire, Real-time, detection, Fuzzy, internet of things



2020 ◽  
Vol 2 (1) ◽  
pp. 50
Author(s):  
Rambo Hilary ◽  
Philemon Rotich ◽  
Anna Geofrey ◽  
Anael Sam

Application of wireless sensor networks (WSN) and Internet of Things (IoT) used to provide real-time monitoring of fire outbreak in markets. The system integrates three subsystems namely; sensing subsystem which uses multiple sensors for detecting fire outbreaks. Data processing subsystem which collects data from the sensing subsystem through Xbee, analyses, and uploads data to the cloud. If values exceed the sensor threshold, an alarm is triggered and notification is sent to stakeholders via mobile application subsystem. The integration between sensing, data processing, and mobile application subsystems pave a new way for the mitigation of fire outbreaks at its early stage.



Author(s):  
Nada Jovičić

The aim of this paper is to analyze possibilities of metal fire detection using various types of fire detectors, and find the most convenient type of detector. Metal fires belong to class D fires, and demand extinguishing agents which work by smothering and heat absorption. On the other hand, it is too risky to use heat generated by fire for early-stage detection due to high heat release rate. Some metals burn with smoke, but during the fire, most of them produce significant ultraviolet and infrared component of radiation which can be used for detection. Therefore, this paper analyzes the possibility of using a flame detector in case of metal fires, as well as sitting and spacing of flame detectors for metal fire detection at its earliest stage.  



2014 ◽  
Vol 613 ◽  
pp. 219-227
Author(s):  
Chao Ching Ho ◽  
Dan Wen Kuo

The performance of a fire sensor has a significant effect on fire detection. Today’s fire alarm systems, such as smoke and heat sensors, however are generally limited to a close proximity to the fire; and cannot provide additional information about fire circumstances. Thus, it is essential to design a suite of low-cost networked sensors that provide the capability of performing distributed measurement and control in real time. In this work, a wireless sensor system was developed for fire detection. The purpose of this paper is to analyze the integration of traditional fire sensors into intelligent fire management systems by using the smart transducer concept. An automated video processing sensor for fire smoke monitoring applications is integrated into an surveillance network as a case study and supported sensor fusion assessment to improve the resistance to nuisance alarms. The proposed sensor system for fire detection was developed to reconcile issues related to proliferation and interoperability, and the architecture can support a smart transducer interface (IEEE 1451). The proposed embedded system for STIM (smart transducer interface module) and NCAP (network capable application processor) will be implemented with DSP. To realize the self-identification of transducers and plug-and-play connections, a transducer electronic data sheet (TEDS) is also stored inside the DSP. The acquired sensor data are pre-processed and applied to discriminate nuisance sources. The IEEE 1451 standard has been integrated into an automatic video-based fire smoke detection system. The proposed architecture has been tested on an experimental setup with the purpose of monitoring fire incidents successfully.



Author(s):  
Milan Blagojević ◽  
Radoje Jevtić ◽  
Dejan Ristić

Abstract Subdividing elements and different structures on the ceiling like beams or similar, significantly affect the location of the smoke detector, because they change the flow of combustion products. From point of view of fire detection system, designers it is very interesting how to arrange and distribute smoke detectors in applications when beams are formed structure like a “honeycomb” The European norm 54-14 is mandatory, but in practice, a main question appears: “Do we have the explanations detailed enough for all of the situations that could occur related to length, width and depth of honeycomb cells”? The main goal of this paper is to show the differences between the rules and the instructions in five standards: EN 54-14, VDE 0833-2, BS 5839-1, NPB 88, NFPA 72, and to find the best solution for various situations in practice.



The video surveillance system has become a important part in the security and protection of cities. The Video surveillance has become an important factor in the cities, since smart monitoring cameras mounted with intelligent video analytics techniques can monitor and pre-alert system by capturing abnormal activity such as fire events. The current world is completely under CCTV for make the various areas secure. The video recorded is unable to find out fire detection at early stage of fire event. After event happened this video sequence is used to find out causes of an event/fire but problem is after event happened system are unable to save loss by that event or accident, so there is need to such system is able to help us in early event detection and pre-alert generation system. Motive behind this proposed work is to invent pre-alert generation system without any hardware as well as sensor. Accuracy of this proposed system may be approx.85-90% or more which is better than existing system.



2020 ◽  
Vol 34 (6) ◽  
pp. 104-113
Author(s):  
Han-Bit Choi ◽  
Euy-Hong Hwang ◽  
Sung-Eun Lee ◽  
Don-Mook Choi

As unwanted fire alarms within the automatic fire detection system increase, fire-fighting power gets wasted. This is recognized as important because it causes a decrease in the evacuation reliability of the occupancy. Therefore, in order to develop measures to reduce unwanted fire alarms, foreign (United States and, United Kingdom) and domestic standards related to unwanted fire alarms were compared and analyzed in the present study. Through the analysis the problems with the standards were identified as uncertainty regarding the detecting space and radius of the smoke detector, the absence of a statistical database (DB) for unwanted fire alarms, the absence of a protocol for managing unwanted fire alarms, and the absence of testing standards for unwanted fire alarms based on scenarios. Consequently, it is proposed that to deal with the problems, it is necessary to ascertain the detecting space and radius of the smoke detector, to propose unwanted fire alarm protection codes for database (DB) system construction, to supplement the fire safety management log by developing related manuals, and to develop unwanted fire alarm testing standards of Korean type based on scenarios.



Sign in / Sign up

Export Citation Format

Share Document