Smoke Detection System Research Articles

Dangerous Smoke Classification Using Mathematical Model of Meaning

Fire accident remains a problem in modern society. This leads great efforts in finding ways to prevent, detect and control it. Conventional fire detection systems are mostly point detectors, which have limitation for early smoke detection, especially in a high-ceiling atrium. A video-based smoke detection system is an interesting alternative approach. It has better area coverage and detecting smoke faster. In this work, a video-based smoke detection system was developed with two main processes, i.e. moving objects segmentation with Gaussian Mixture Models (GMM) and smoke classifications with Mathematical Model of Meaning (MMM). In the MMM model, the interpretation of dangerous smoke is based on the context provided. Then the classification results are compared with conventional smoke detector. The results show that MMM can recognize the dangerous smoke faster than conventional smoke detectors.

Nighttime fire smoke detection system based on machine vision

A real-time machine vision-based nighttime fire smoke detection method that can be incorporated into a surveillance system for early fire alert is proposed in this paper. Nowadays, video surveillance-based early fire smoke detection is crucial to the prevention of large fires and the protection of life and goods. However, many of the known video smoke detection methods require that minimum illumination be provided for the cameras to recognize the existence of fire smoke in a scene. To overcome the nighttime limitations of video smoke detection methods, a laser light is projected into the monitored field of view, and the returning projected light section image is analyzed in order to fire smoke. If the fire smoke appears within the monitoring zone created from the diffusing or scattering projected light path, the camera sensor receives a corresponding signal. The successive processing steps of proposed real-time algorithm are using the spectral, diffusing, and scattering characteristics of the fire smoke regions in the image sequences to register the possible smoke position in a video. Characterization of smoke is carried out by calculating accumulative deviation from the extracted feature vectors, and a classification method using a fuzzy reasoning system is applied to assign a score to the potential fire smoke candidate. Experimental results in a variety of nighttime conditions demonstrate that the proposed fire smoke detection method can successfully and reliably detect fire smoke.

연기 영상의 정적 및 동적 텍스처를 이용한 강인한 연기 검출

Automatic smoke detection systems using a surveillance camera requires a reliable smoke detection method. When an image sequence is captured from smoke spreading over in the air, not only has each smoke image frame a special texture, called static texture, but the difference between two smoke image frames also has a peculiar texture, called dynamic texture. Even though an object has a static texture similar to that of the smoke, its dynamic texture cannot be similar to that of the smoke if its movement differs from the diffraction action of the smoke. This paper presents a reliable smoke detection method using these two textures. The proposed method first detects change regions using accumulated frame difference, and then picks out smoke regions using Haralick features extracted from two textures.

Simulation Study on the Aspirating Smoke Detection System in Large Space Buildings

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.

카메라 영상을 이용한 연기 및 화염의 조기 감지 최신 연구 동향

시대가 발전함에 따라 초고층 건물들이 도처에 세워지고 밀집되어 있다. 이러한 건물에 화재가 발생되면 발화지점 근처로 불이번지면서 대형화재의 위험성이 높아지고 이에 따른 인명 및 재산 피해가 증가한다. 따라서 이런 대형화재를 예방하고 피해를 최소화하기 위해서 화재를 미연에 감지하는 화재감지 기술에 대한 필요성이 높아지고 있다. 화재를 감지하기 위해 열감지기, 연기감지기, 불꽃감지기 등을 사용하는 방법이 있으나 본 논문에서는 감시 카메라에서 들어오는 입력 영상을 분석하여 화염과 연기를 초기에 감지하는 화재감지 시스템의 최근 연구 동향을 알아보고자 한다. 또한 이러한 화염과 연기 감지 알고리즘들을 다양한 형태의 동영상을 이용하여 구현 및 성능을 평가하였다. With the rapid development of technology, skyscrapers are widely spread and they are tightly coupled. If fire occurs in a building, it is easily spread to neighboring buildings, resulting in the large number of victims and property damages. To remove fire disasters, the need for early fire detection techniques is increasing. To detect fire, detecting devices for heat, smoke, and flame have been used widely. However, this paper surveys and presents the latest research which focuses on early smoke and flame detection algorithms and systems with camera's input images. In addition, this paper implements and evaluates the performance of these flame and smoke detection algorithms with several types of movies.

Fire safety of multistorey timber buildings

Fire safety is the main precondition for the use of wood for multistorey timber buildings and is therefore an important criterion for the choice of material for buildings. The Institute of Structural Engineering at ETH Zurich has accomplished several research projects on the fire behaviour of timber structures over the past 15 years. The research projects aimed at supplying basic data and information on the safe use of timber, in particular for multistorey buildings. Further novel fire design concepts and models have been developed based on extensive theoretical studies, element and full-scale testing as well as a large statistical database on fires in timber. The better knowledge in the area of fire design of timber structures from the research projects, combined with technical measures, especially sprinkler and smoke detection systems, as well as well-trained and equipped fire brigades allow the safe use of timber and a wider field of application of timber for buildings. As a result the Swiss fire regulations of 2005 allow the use of timber structures in multistorey medium-rise residential buildings with up to six storeys. Many other countries have also liberalised the use of timber for buildings or introduced fire regulations that allow for the use of timber on the basis of performance. This paper describes the background of the design concept assumed for multistorey medium-rise buildings. It further presents an overview of two novel calculation models for the verification of the separating function of wall-and-floor timber assemblies as well as for the fire resistance of timber connections.

Preventive measures for mitigating fire risks in big box retail facilities

PurposeThe purpose of this paper is to investigate a set of preventive measures required for mitigating fire risks in big box retail facilities.Design/methodology/approachThe paper identifies the potential sources of ignition and fuel in big box retail facilities. It describes the variety of hazardous situations commonly found in such facilities worldwide. The paper then endeavors to discuss the series of fire protection challenges that could be faced during fire emergencies. It also explores the challenges of evacuation and rescue in such mega store facilities.FindingsMega stores, distribution centers and large retail stores are amongst the most challenging occupancies from a fire protection perspective. Fires can occur in big box retail facilities at any time and from a number of causes. These facilities represent a type of occupancy that poses considerable challenges to both fixed fire suppression systems and fire departments in cases of fire emergencies. The paper also describes the responsibilities of building management staff towards their employees and the public. Facility managers should always seek proactive measures to reduce the risk of fire and fire spread in big box retail facilities. These measure include providing sufficient number and capacity of exits; clear exit access; efficient smoke detection systems; voice communication systems; and efficient automatic sprinkler systems.Quality/valueThis paper serves to increase the awareness about fire and its effects in mega store facilities. The paper provides practical value to property directors and facility managers responsible for the daily operations of mega store facilities and for surveyors inspecting such properties.

Vision based smoke detection system using image energy and color information

Smoke detection is a crucial task in many video surveillance applications and could have a great impact to raise the level of safety of urban areas. Many commercial smoke detection sensors exist but most of them cannot be applied in open space or outdoor scenarios. With this aim, the paper presents a smoke detection system that uses a common CCD camera sensor to detect smoke in images and trigger alarms. First, a proper background model is proposed to reliably extract smoke regions and avoid over-segmentation and false positives in outdoor scenarios where many distractors are present, such as moving trees or light reflexes. A novel Bayesian approach is adopted to detect smoke regions in the scene analyzing image energy by means of the Wavelet Transform coefficients and Color Information. A statistical model of image energy is built, using a temporal Gaussian Mixture, to analyze the energy decay that typically occurs when smoke covers the scene then the detection is strengthen evaluating the color blending between a reference smoke color and the input frame. The proposed system is capable of detecting rapidly smoke events both in night and in day conditions with a reduced number of false alarms hence is particularly suitable for monitoring large outdoor scenarios where common sensors would fail. An extensive experimental campaign both on recorded videos and live cameras evaluates the efficacy and efficiency of the system in many real world scenarios, such as outdoor storages and forests.

Specification of Conditions for Error Diagnostics

This paper describes the basic concepts of error diagnostics and an associated rule system whose application helps to identify potential hardware/software locations of errors which caused a failure observed while executing tests of embedded systems. Further on, an overview over the “Avionics Smoke Detection System” is given, where the main algorithms have been applied. The methods, techniques and tools described here rely on the preceding investigations performed with respect to signal flow and the observation of causal chains in distributed test benches during test suite executions. These results have been elaborated in the KATO project within the German aerospace research programme LUFO III.

Automatic fire detection in road traffic tunnels

Fire detection experiments in a road traffic tunnel were performed in the Runehamar test tunnel 5th–8th March 2007. The Runehamar test tunnel is a full profile road traffic tunnel, 1.65 km long, located outside Åndalsnes, Norway. The goal was to examinate smoke and heat detection systems to determinate what kind of principle best suited for detecting a fire in an early stage. The systems were tested during small Heptane pool fires, varying between 0.16 m 2 and 1 m 2, giving heat release rates from 0.2 MW to 2.4 MW accordingly, and one car fire of about 3–5 MW, and with wind conditions varying from 1.1 m s −1 to 1.6 m s −1. The size of the fires, were designed to be in the range from impossible to difficult to detect. The results were conclusive. Earliest detection of a car fire, fire starts inside, was by smoke detection given fixed limits (3000 μg m −3). With open pool fires, or immediate flames, continues fibre optical heat detection systems was faster given the limits 3 °C/4 min.

A fast accumulative motion orientation model based on integral image for video smoke detection

Video smoke detection has many advantages over traditional methods, such as fast response, non-contact, and so on. But most of video smoke detection systems usually have high false alarms. In order to improve the performance of video smoke detection, we propose an accumulative motion model based on the integral image by fast estimating the motion orientation of smoke. But the estimation is not very precise due to block sum. Not very accurate estimation will affect the subsequent decision. To reduce this influence, the accumulation of the orientation over time is performed to compensate results for the inaccuracy of orientation. The model is able to mostly eliminate the disturbance of artificial lights and non-smoke moving objects by using the accumulation of motion. The model together with chrominance detection can correctly detect the existence of smoke. Experimental results show that our algorithm has good robustness for smoke detection.

Case Study - Special Design of Smoke Detection System in a Mental Health Facility in New Zealand

Specialized buildings such as mental health facilities present unique challenges for fire safety design, as occupants typically should not be evacuated, unless directly threatened by the effects of fire. The New Zealand ‘deemed to satisfy’ solutions address this with a mandatory minimum requirement for early warning smoke detection and sprinkler suppression systems in buildings with this occupancy, installed in accordance with New Zealand Standards. However, in some instances, the solutions in the Standards are in conflict with clinical requirements to protect patients from (self-) harm. One example is point-type smoke detectors, which should be installed below the ceiling to be compliant with the Standard, but must be located in a protected recess above the ceiling to meet clinical needs. This case study outlines the performance based design of an aspirated recessed point type smoke detection system in the bedrooms of a secure wing in a mental health facility, operated by one of the largest district health boards in New Zealand. The system was purpose designed to cater for the clinical requirements of the health board. The performance based solution combines the location identification ability of point type analogue addressable detection systems with the unobtrusive installation of aspirating systems. The system consists of fully recessed proprietary analogue addressable point type smoke detectors that are combined with a small aspirating system. The system was successfully tested in comparison with ceiling mounted point type smoke detectors and was accepted by all stakeholders as a specialized engineered solution giving performance equivalent to that of a Standard compliant system.

REAL-TIME FIRE AND SMOKE DETECTION USING CAMERA SEQUENCE IMAGE IN TUNNEL ENVIRONMENT

In this paper, we proposed an image processing technique for automatic real time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurring in the tunnel, it is necessary to have a system to sense and minimize the incident as fast as possible. However it is impossible for human observation of Closed-Circuit Television (CCTV) in tunnel for 24 h. So if the fire and smoke detection system through image processing can warn a fire, it will be very convenient, and it can be possible to minimize damage even when no one is in front of the monitor. The fire and smoke detection is different from forest fire detection as there are elements such as car and tunnel lights and others that are different from the forest environment so an indigenous algorithm has to be developed. The two algorithms proposed in this paper are able to detect the exact position at the earlier stage of incident. In addition, by comparing properties of each algorithm throughout experiment, we have proved the validity and efficiency of proposed algorithm.

Influence of Air Flow Patterns on Smoke Dispersion in Multi-functional Gymnasia

When a fire occurs in an indoor space, the design of the airflow pattern of the HVAC system greatly affects smoke movement. The interactions between smoke and the HVAC system can have an adverse effect of delaying the activation of the smoke detection system and hence increasing the risk from fire. In this paper, smoke movements in several types of indoor gymnasia were studied making use of the Fire Dynamics Simulator 3.1 (FDS) software. The simulation results of the smoke dispersion patterns under a number of HVAC design schemes and fire ignition positions suggest the appropriate locations of fire detectors. This research suggests that fire detectors should be strategically located through systematic simulation investigation of smoke dispersion for the most likely cases and locations of fire.

Fire Performance Of Timber Structures Under Natural Fire Conditions

In recent years the use of wood as a building material has become popular, especially for dwellings. One of the preconditions for its use is adequate fire safety. Technical measures, especially sprinkler and smoke detection systems, well equipped fire brigades and a better knowledge in the area of structural fire design of timber structures allow the use of timber in a wider field of application. Full scale tests on wooden modular hotels were performed under natural fire conditions to look at the efficiency of different fire safety concepts. In a first series the efficiency of technical measures, especially fast response sprinkler systems, was studied. The second series showed the possibility and limits of structural fire safety measures. Special attention was given to the influence of combustible room surfaces on fire growth and fire spread inside and outside the room. The tests enlarged the experimental data for validation of natural fire simulations (temperatures, fire spread etc.) and for verifying the methods for the fire resistance calculation of wood constructions.

An evaluation of actual and simulated smoke properties

Federal regulations require that aircraft cargo compartment smoke detection systems be certified by testing their operation in flight. For safety reasons, only simulated smoke sources are permitted in these certification tests. To provide insight into smoke detection certification in cargo compartments, this research investigates the morphology, transport and optical properties of actual and simulated smoke sources. Experimental data show the morphology of the particulate in smoke from flaming fires is considerably different from simulated smoke. Although the detection of smoldering fires is important as well, only a qualitative assessment and comparison of smoldering sources was possible; therefore, efforts were concentrated on the quantitative comparison of smoke from flaming fires and smoke generators. The particulate for all three different flaming fires was solid with similar morphological properties. Simulated smoke was composed of relatively large liquid droplets, and considerably different size droplets can be produced using a single machine. Transport behavior modeling showed that both the actual and simulated smoke particulates are sufficiently small to follow the overall gas flow. However, actual smoke transport will be buoyancy driven due to the increased temperature, while the simulated smoke temperature is typically low and the release may be momentum driven. The morphology of the actual and simulated smoke were then used to calculate their optical properties. In contrast to the actual smoke from a flaming fire, which is dominated by absorption, all of the extinction for the simulated smoke is due to scattering. This difference could have an impact on detection criteria and hence the alarm time for photoelectic smoke detectors since they alarm based on the scattering properties of the smoke.

Early Warning Fire Detection System Using a Probabilistic Neural Network

The Navy program, Damage Control-Automation for Reduced Manning is focused on enhancing automation of ship functions and damage control systems. A key element to this objective is the improvement of current fire detection systems. As in many applications, it is desired to increase detection sensitivity and,more importantly increase the reliability of the detection system through improved nuisance alarm immunity. Improved reliability is needed, such that fire detection systems can automatically control fire suppression systems. The use of multi-criteria based detection technology continues to offer the most promising means to achieve both improved sensitivity to real fires,and reduced susceptibility to nuisance alarm sources. A multi-criteria early warning fire detection system, has been developed to provide reliable warning of actual fire conditions, in less time, with fewer nuisance alarms,than can be achieved with commercially available smoke detection systems. In this study a four-sensor array and a Probabilistic Neural Network have been used to produce an early warning fire detection system. A prototype early warning fire detector was built and tested in a shipboard environment. The current alarm algorithm resulted in better overall performance than the commercial smoke detectors, by providing both improved nuisance source immunity with generally equivalent or faster response times.

Spot and Aspirated Laser Smoke Detection in Telecommunications Facilities

Full-scale, in-situ comparison tests of spot and aspirated laser detection systems in an active telephone switch center were conducted to compare the response times of spot and aspirated smoke detection systems when exposed to a variety of smoke sources and ventilation conditions. The report documents the performance of multiple systems varying in detector type, detector spacing and detector locations (i.e., mounted on the ceiling versus on return air grills). The work provides data intended to guide system designers in the selection and use of very early warning smoke detection systems.

Multi-criteria fire detection systems using a probabilistic neural network

The Navy program, Damage Control Automation for Reduced Manning (DC-ARM), is focused on enhancing automation of ship functions and damage control systems. A key element to this objective is the improvement of current fire detection systems. As in many applications, it is desired to increase detection sensitivity and, more importantly, increase the reliability of the detection system through improved nuisance alarm immunity. Improved reliability is needed such that fire detection systems can automatically control fire suppression systems. The use of multi-criteria-based detection technology continues to offer the most promising means to achieve both improved sensitivity to real fires and reduced susceptibility to nuisance alarm sources. A multi-signature early warning fire detection system is being developed to provide reliable warning of actual fire conditions in less time with fewer nuisance alarms than can be achieved with commercially available smoke detection systems. In this study, a large database consisting of the responses of 20 sensors to several different types of fires and nuisance sources was generated and analyzed using a variety of multivariate methods. Three data matrices were developed at discrete times corresponding to the different alarm levels of a conventional photoelectric smoke detector. The alarm times represent 0.82%, 1.63% and 11% obscurations per meter. The datasets were organized into three classes representing the sensor responses for baseline (nonfire), fires and nuisance sources. A robust data analysis strategy for use with a sensor array consisting of four to five sensors for early fire detection and nuisance source rejection was developed using a probabilistic neural network (PNN) that was developed at the Naval Research Laboratory for chemical sensor arrays. The analysis algorithms described in this paper evaluate discrete samples and develop classification models that examine individual chemical signatures at discrete points.

Investigation of an approach to fuel identification for non-flaming sources using light-scattering and ionization smoke detector response

Smoke detector performance depends on the detector and smoke characteristics as two decoupled phenomena. In this work, smoke properties on which various smoke detection principles are based were simultaneously measured in an enclosure using existing reference smoke detection systems. The measured smoke properties were scattered light intensity, response of measuring ionization chamber (MIC), obscuration, smoke particle density, and fuel mass loss. Data were collected for conventional fuels such as wood, paper, nylon, wool, polyurethane and PMMA, and also for unconventional fuels such as cooking oil and bread. The fuels were ranked nearly consistently, but in reverse order, based on ionization and light scattering reference detector responses. Discrimination of fuels using a simplified Mie scattering theory was examined. The analysis indicates that the Mie scattering coefficients are fuel-dependent and may be essentially unique to each fuel; however, an overall classification of different fuels using these coefficients may not be practical and requires more precise measurements.