Photoelectric Smoke Detectors Research Articles

Embedded Spatial–Temporal Convolutional Neural Network Based on Scattered Light Signals for Fire and Interferential Aerosol Classification

Photoelectric smoke detectors are the most cost-effective devices for very early warning fire alarms. However, due to the different light intensity response values of different kinds of fire smoke and interference from interferential aerosols, they have a high false-alarm rate, which limits their popularity in Chinese homes. To address these issues, an embedded spatial–temporal convolutional neural network (EST-CNN) model is proposed for real fire smoke identification and aerosol (fire smoke and interferential aerosols) classification. The EST-CNN consists of three modules, including information fusion, scattering feature extraction, and aerosol classification. Moreover, a two-dimensional spatial–temporal scattering (2D-TS) matrix is designed to fuse the scattered light intensities in different channels and adjacent time slices, which is the output of the information fusion module and the input for the scattering feature extraction module. The EST-CNN is trained and tested with experimental data measured on an established fire test platform using the developed dual-wavelength dual-angle photoelectric smoke detector. The optimal network parameters were selected through extensive experiments, resulting in an average classification accuracy of 98.96% for different aerosols, with only 67 kB network parameters. The experimental results demonstrate the feasibility of installing the designed EST-CNN model directly in existing commercial photoelectric smoke detectors to realize aerosol classification.

Development of a Photoelectric Smoke Detector with a Built-in Function to Prevent False Alarms Owing to Humidity

In this study, a photoelectric smoke detector with a built-in function was developed to prevent false alarms owing to humidity. Smoke-detector sensitivity characteristics were analyzed through room-scale false alarm experiments and by generating humidity conditions measured using a type approval sensitivity tester. The results showed that when humidity was generated, more light scattering occurred as the humidity flowed into the detector chamber along with the smoke, increasing the smoke concentration of the smoke detector. It was found that smoke concentrations increased at a relative humidity of 85 %RH or higher. The findings confirm that false alarms occur owing to high concentrations of humidity in the summer. False alarms that occur owing to high concentrations of water vapor in summer can be prevented by detecting fires using a humidity + smoke concentration fire-detection algorithm that has been quantified through experiments.

Study on the Smoke and CO Alarm Concentrations to Develop a Smoke & CO Combination Detector

In this study, we studied smoke and CO alarm concentrations to develop a combination detector for both smoke and CO. The derivation of smoke and CO alarm concentrations involved examining CO concentrations by smoke concentration using a sensitivity tester, typically employed for the type approval of photoelectric smoke detectors. Fire alarm and false alarm tests were performed to analyze smoke and CO concentrations further. In the fire alarm test conducted with polyurethane foam, generating black smoke with a reduced light scattering effect in the smoke chamber, no fire alarm was triggered, although the fire alarm concentration of the existing photoelectric smoke detector of sensitivity type 2 was set at 15 %/m. The measured smoke concentration reached only up to 10.2 %/m. Conversely, in the false alarm test with sliced pork belly and mackerel, false alarms occurred as the smoke concentration exceeded 15 %/m. The determined smoke and CO alarm concentrations for the combination detectors were established at 7.5 %/m for smoke (continuously for 10 s) and 15 ppm for CO (continuously for 10 s). Applying these concentrations in subsequent tests revealed an improved performance. In the polyurethane foam fire, where the existing smoke detector failed to operate, a fire alarm was issued at 328 s with the newly derived concentrations. For smoldering wood, the combination detector issued a fire alarm 305 s faster than the existing smoke detector. Furthermore, in the false alarm test with hamburger patty, sliced pork belly, and mackerel, the adaptability of false alarms was enhanced.

Computational design of a smoke detector with high sensitivity considering three-dimensional flow characteristics

Early fire detection is essential for preventing catastrophic events, and fire detectors play a critical role in ensuring fire safety. Among the various types of fire detectors, photoelectric smoke detectors are widely used because of their ability to detect smoke at an early stage. The present study investigates the effects of changes in flow directions and inlet size on the smoke detection ability of a photoelectric smoke detector by conducting computational fluid dynamics (CFD) simulations. The results indicated that when the flow direction changes, the components in the optical chamber may hinder the smoke inflow and increase the detector activation time. Moreover, the smoke inlet size was found to affect the carbon monoxide concentration inside the chamber. The velocity magnitude distributions confirmed the correlation between the smoke velocity in the labyrinth structures entering the optical chamber and the detection ability of the smoke detector. These findings suggested that when optimizing the performance of a smoke detector, flow direction, inlet size, and amount of smoke introduced into the optical chamber should be considered. The current study suggested the modified design of the smoke detector to have superior detection ability in both directions compared to the base case in terms of activation time.

Response Characteristics of Smoke Detection for Reduction of Unwanted Fire Alarms in Studio-Type Apartments

Photoelectric smoke detectors (SDs) often emit false alarms in studio-type apartments, where fire prevention is crucial. This study investigates the response characteristics of conventional and analog smoke detection factors to reduce false positives in studio-type apartments. A mock-up was tested based on relevant domestic laws, standards, statistical data, and experimental cases. A simulation of a cooking scenario involving burned food items was conducted, and optical density, particulate matter (PM), and carbon monoxide levels were measured and compared with actual smoke detection at six different locations. The measured values of conventional smoke detectors (CSDs) and analog smoke detectors (ASDs) at these locations were used to derive the activation time of CSDs and ASDs for the entire mock-up space. The results showed that the CSD activated at 7.42 min, while the ASD activated at 11.57 min. PM10.0, CO, and CO2 showed similar activation time trends. The PM10.0, CO, and CO2 concentrations at the time of SD activation were estimated. The findings suggest that a sensor with a consistent coefficient of variation, such as PM10.0 and CO, should be recommended.

Preliminary Study for Smoke Color Classification of Combustibles Using the Distribution of Light Scattering by Smoke Particles

Photoelectric smoke detectors are used for early detection of building fires, and sensitivity adjustment is generally performed using white smoke generated by the burning of filter paper. Therefore, when black smoke of the same concentration is introduced, the detector is often not activated. To address this problem, differences in the distribution of light scattered by smoke of various colors were analyzed. A light-scattering chamber with a light-receiving unit for various scattering angles was constructed to measure the scattered light generated inside the chamber of the smoke detector. The light scattering distribution was measured for smoke generated from three combustibles—filter paper (white smoke), kerosene (black smoke), and polyurethane (gray-black smoke)—and three analysis criteria were applied. By identifying a section where the measured values were concentrated for a specific analysis criterion and scattering angle, it was confirmed that some combustibles can be distinguished. Specifically, criterion III, a probabilistic section, was presented to determine which combustible smoke particles were close by applying the proposed section in a complex manner. A preliminary study was conducted to evaluate a methodology for the color classification of smoke particles flowing into a smoke detector chamber; this can be utilized as a foundation for determining optical properties.

Statistical Characteristics of Scattering Ratio Based on Three Optical Wavelengths for Smoke Particles

Photoelectric smoke detectors, which operate by reacting to the scattering of light caused by particles entering the light path, are widely used and extremely sensitive. Owing to higher standards imposed by Underwriters Laboratories, researchers have begun analyzing the properties of smoke particles. In particular, several wavelengths are used to classify particles by their scattering reactivity. The performances of actual smoke detectors are limited by their hardware and price. Therefore, properties that can distinguish particle types in these limited conditions must be determined. In addition, algorithms for extracting valid data intervals from unstable scattering data must be developed. In this study, scattering intensity ratios for three wavelengths are derived via simulations of light scattering by particles. An upper cumulative sum is defined for the three wavelengths, and an index for the start of particle inflow is extracted. In addition, valid intervals are extracted based on the scattering intensity ratios and the moving variance of adjacent wavelengths, and the properties of each particle are defined using the extracted indexes. For verification, a data acquisition device that can obtain data using the three selected wavelengths (470, 525, and 850 nm) from two sensors is designed. Five types of fire sources and non-fire alarm sources are selected and used in a test chamber designed to generate particle data. After applying the algorithm, the data in the valid data intervals can be used to derive a sample mean scattering intensity ratio that is more constant than that of the overall data or the data processed using the CUSUM index. In addition, the fire sources have a higher sample mean scattering intensity ratio than water vapor, which is a non-fire alarm source. The scattering intensity ratios for smoke particles can be extracted in real time via a comparison with experimental results obtained from the selected sensors.

Detection of smoke from infrared image frames in the aircraft cargoes

The existing equipment of civil aircraft cargo fire detection mainly uses photoelectric smoke detectors, which has a high false alarm rate. According to Federal Aviation Agency’s statistics, the false alarm rate is as high as 99%. Since, in the cargo of civil aircraft, visible image processing technology cannot be used to detect smoke in the event of a fire due to the closed dark environment, a novel smoke detection method using infrared image processing technology is presented. Experiments were conducted under different environment pressures in the full-size cargo of civil aircraft. The results show that the proposed method can effectively detect smoke at the early stage of fire which is applicable for fire detection in civil aircraft cargoes.

Evaluation of Empirical Evidence Against Zone Models for Smoke Detector Activation Prediction

A series of experiments were conducted in a large room to generate data to assess the accuracy of computer fire model predictions of detector activation time. A comparison between experimental measurements and zone model predictions of the detector activation in the Consolidated Fire and Smoke Transport model (CFAST) version 7.4.3 were made. The experimental room was 11.0 m by 7.3 m by 3.7 m high with a single opening 2.44 m high and 1.83 m wide centered in a short wall. Two ceiling configurations were examined, a flat ceiling and a flat ceiling with two 0.30 m wide and 0.30 m deep solid beams. The fire source was a gaseous fuel burner fed with different mixtures of propane and propene that produced soot yields ranging from 0.010 gsoot/gfuel to 0.072 gsoot/gfuel and a fuel flow ramp time that ranged from 30 s to 1800 s. The heat release rate profile reached a nominal maximum value of 30 kW. The activations of two different models of photoelectric smoke detectors and a single ionization smoke detector, each with a range of alarm set points and installed at various locations on the ceiling, were recorded. Predictions of the various smoke detector activation times were made in CFAST with the temperature approximation method, and a fixed smoke detector concentration method for photoelectric detector activations. Predictions with the smoke detection method were better than the temperature approximation method over the range of fire scenarios examined. Predictions of smooth ceiling experiments were generally better than the beamed ceiling experiments.

Study of Effectiveness of CO and Smoke Alarm in Smoldering Fire

Introduction One of the main causes of home fires in Japan is smoking in bed, and carbon monoxide poisoning and suffocation account for a high proportion of cause of death in bedding fires [1]. In this study, using a full-scale building model, a smoldering fire initiated with a lighted cigarette placed still on cotton bedding was reproduced. The COHb concentration (blood COHb concentration) inhaled into a human body and the density and concentration behavior of smoke and CO alarms were compared by monitoring the change in the CO concentrations while smoldering fire. Early detection of fires and effects on a human body were discussed based on the data and the effectiveness of a smoke and CO alarm placed on an indoor wall was examined. Experimental In this study, single function CO gas sensor modules and smoke and CO alarms equipped with photoelectric smoke detectors and electrochemical CO sensors were arranged in a full-scale building model, as shown in Figure 1. Smoldering fire was caused in cotton bedding using a cigarette as a source of fire, and the COHb concentration of an expiratory position and the smoke densities and the CO concentrations of smoke and CO alarms placed on walls were examined. The laboratory was W2.12 ×D2.58 × H2.42 m and a set of cotton bedding was arranged. The source of the fire was set almost at the center of the laboratory and the CO sensor modules were arranged at the pillow, in the bedding, and on the upper part of the bedding (L1-300～L5-400), and on the lower part of the ceiling (L1-2120～L5-2120). Also, smoke and CO alarms (A1～A4) were placed 300 mm off the ceiling on the four walls of the laboratory. The CO concentration outputs and smoke density outputs at each measuring point were collected per 5 seconds using data loggers. After the lighted cigarette (MEVIUS SUPER LIGHTS) was placed still, each measured data was being continuously monitored. Also, based on the CO concentration data from the CO sensor modules surrounding the bedding, the COHb concentration accumulated in a human body was calculated. Result and Conclusions Each CO concentration data from the CO sensor modules placed 400 mm above the lower part of the mattress, in the bedding, and at the expiratory position were extracted as representative data (Fig.2). The CO concentration right above the fire point started rising 50 seconds after the cigarette was placed still, sharply surged to a high concentration level over 1000 ppm at 440 seconds. The CO concentration under the coverlet also suddenly surged a bid later than the one right above the source of the fire, exceeding 1000 ppm at 350 seconds. For the CO concentration at position near the pillow as expiratory position, the rise of CO concentration was confirmed 380 seconds after the cigarette was placed still and the concentration exceeded 1000 ppm at 1240 seconds. Figure 3 shows it is sufficiently possible to detect CO on the wall’s position since it was found in the comparison of the data of the CO sensor module near the ceiling and the smoke and CO alarms on the laboratory walls that the trends of CO concentration were similar in terms of the ways of rising and the concentration values. In this experiment, assuming a respiratory position of a sleeping person, the COHb concentration accumulated through breathing based on the CO concentrations of the upper part of the bedding (L2-300～L5-400) and the CO concentrations and smoke densities of the alarms placed on the walls were compared. Here, the smoke and CO alarms were set to at 10%/m for smoke and 100ppm for CO. Figure 4 shows the relationship between the CO concentration and smoke density values of A2 which responded last among the alarms placed on the walls and the COHb concentrations of the pillow position was related to these data. It was found that the CO alarm detected 280 seconds faster than the smoke alarm. The COHb concentration at the pillow position in the case of this extremely dangerous situation was calculated and it was found that the concentration was 15.1% when the smoke alarm went off. From the results above, it has been confirmed that the CO detection function of a CO and smoke alarm placed on a wall enables people to evacuate well in advance and the alarm is effective in early detection of fire.

Study of Effectiveness of CO and Smoke Alarm in Smoldering Fire

Study of Effectiveness of CO and Smoke Alarm in Smoldering Fire

Reliability Assessment of Photoelectric Smoke Detector, Ionization Smoke Detector and a Fire Alarm Control Panel with Both Detectors AS Notification Device

Notification device like smoke detectors are critical and important part of a Fire Alarm Control Panel (FACP). Popularly used smoke alarms in commercial establishments in India are photoelectric smoke alarms (PESD) and ionization smoke alarms (ISD). In this study reliability assessments of PESD with Integrated Circuit (IC) – MC145010 and ISD with IC – MC145017 have been carried out on the basis of reliabilities of their respective electronic components. The cases considered are: (I) Failure rates of all components are equal and constant over time (II) Failure rates of all components are equal and follow Weibull distribution and (III) Failure rates of all components are different. To determine failure rates of 9 volt battery of both detectors additional assumptions taken are, (a) battery life is 10 years with constant failure rate, (b) battery life follows Weibull distribution. In this paper the reliability and failure rate of two types of smoke alarms have been calculated based on failure rates of their electronic parts like resistors, capacitors, Integrated Circuits etc. These failure rates have been subsequently used for reliability assessment of a non-addressable FACP containing four PESDs and four ISDs as notification device. A comparison of failure rates was also performed on the basis of two quality factors of electronic components – military specific and lower than military specific. Mean Time To Failure (MTTF) of PESD and ISD have been calculated in all the cases. Subsequently, MTTF values obtained in case III were used to approximate failure rates for case I case II.

Fire detection with infrared images using cascaded neural network

The existing equipment of civil aircraft cargo fire detection mainly uses photoelectric smoke detectors, which has a high false alarm rate. According to Federal Aviation Agency’s (FAA) statistics, the false alarm rate is as high as 99%.1In the cargo of civil aircraft, the traditional photoelectric detection technology cannot effectively distinguish interference particles from smoke particles. Since the video smoke detection technology has proven to be reliable in many large scenarios, a deep learning method of image processing for fire detection is proposed. The proposed convolutional neural network is constructed of front end network and back end network cascaded with the capsule network and the circularity computation for the dynamic infrared fire image texture extraction. In order to accurately identify whether there is a fire in the area and give the kind of burning substances, a series of fuels are selected, such as n-heptane, cyclohexane, and carton for combustion reaction, and infrared camera is used to take infrared images of all fuel combustion. Experimental results show that the proposed method can effectively detect fire at the early stage of fire which is applicable for fire detection in civil aircraft cargoes.

Influence of high altitude on the burning behaviour of typical combustibles and the related responses of smoke detectors in compartments.

The effect of altitude on typical combustible burning and related smoke detector response signals was investigated by comparison experiments at altitudes of 40 m and 3650 m based on EN54 standard tests. Point-type light scattering photoelectric smoke detectors and ionization smoke detectors were used for four kinds of EN54 fire tests, including two kinds of smouldering fires with wood (test fire no. 2 in EN54 standard or TF2) and cotton (TF3), and two kinds of flaming fires with polyurethane (TF4) and n-heptane (TF5). First, the influence of altitude or ambient pressure on mass loss for smouldering combustion (TF2 or TF3) was insignificant, while a significant decrease in the mass burning rate was found for flaming tests (TF4 and TF5) as reported in our previous studies. Second, for photoelectric smoke detectors in flaming fire tests, the effect of altitude was similar to that of the burning rate, whereas for the ionization smoke detectors, the response signal at high altitudes was shown to be ‘enhanced’ by the detection principle of the ionization chamber, leading to an even larger value than at normal altitude for smouldering conditions. Third, to provide a reference for smoke detector design in high-altitude areas, the differences between signal speed in rising and peak values at two locations are discussed. Also, relationship between ion chamber signals and smoke optical densities are presented by utilization of an ionization smoke detector and smoke concentration meter. Moreover, a hierarchical diagram is illustrated to provide a better understanding of the effects of altitude on combustible burning behaviour and the mechanisms of detector response.

Informal settlement fires in South Africa: Fire engineering overview and full-scale tests on “shacks”

This paper discusses fires in informal settlements (otherwise known as slums, ghettos, shantytowns, etc.), which are regularly ravaged by fire in South Africa. Initially an overview of the problem is presented, highlighting the factors that contribute to the frequent, large conflagrations that occur. Details have been based on research conducted in Cape Town, South Africa, although the research is applicable to settlements worldwide. Data from recent fires where up to 4500 people were left homeless is included, highlighting aspects regarding fire spread and fire dynamics. Thereafter, preliminary results from a pilot study are presented where full-scale burn tests have been carried out on informal settlement dwellings, or “shacks”. Results from (a) a smoldering fire test, (b) 25kg/m2 wood fire load test and (c) a ‘representative’ shack fire test are presented. For flaming fires it is shown that flashover in these small dwellings can occur in as little as one minute (depending on the fuel source), which is consistent with observations from professional firefighters in the field. Photoelectric smoke detectors, ionization, and rate-of-rise heat detectors were included during fire tests, to evaluate their performance in such confined spaces, as these are currently being either used or being considered for use in settlements. Activation times are reported for the different tests conducted.

Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detection System

Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detection System

Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detection System

Evaluation on Performance of Photoelectric Smoke Detectors in the Zone Detection System

분진 및 풍속에 따른 광전식연기감지기 챔버의 응답특성에 관한 연구

본 논문은 분진 및 풍속에 따른 연기감지기 챔버의 응답특성에 관한 연구이다. 연기감지기가 실내에 적용됨으로 인해 화재의 조기감지 측면에서는 나아졌으나, 실내에서 발생되는 다양한 생활먼지 및 환경적인 요건 등에 의해 발생될 수 있는 부작동 및 오작동에 대한 연구는 미비한 편이다. 이에 본 연구에서는 다양한 분진 및 풍속에 따른 연기감지기의 실내적응성을 연구하기 위해 연기챔버의 형태 및 구조가 다른 4종류의 광전식연기감지기를 실험대상으로 하고, 플라이애시, 활석가루 그리고 섬유분진(흑채가루)을 실험시료로 하여 분진시험을 진행하였다. 또한 연기챔버 내의 오염도에 따른 응답특성을 관찰하기 위해 추가적으로 분진시험 풍속을 0.25 m/s, 0.5 m/s, 1.0 m/s로 설정하여 인가하였다. 실험결과 플라이애시 및 활석가루, 섬유분진의 경우 분진시험 기준풍속조건인 0.25 m/s에서는 분진인가 후 작동시험 및 부작동시험에서 모두 적합한 것으로 나타났다. 반면, 가혹풍속조건인 0.5 m/s 및 1.0 m/s에서는 플라이애시 및 활석가루의 경우 부작동시험에서 비화재보인 오작동이 나타났고, 섬유분진의 경우 작동시험에서 정상적으로 작동되지 않아 부작동이 발생하는 것으로 확인되었다. The present article discusses the response characteristics of smoke detector chamber due to dust and wind velocity. Although situations have improved in terms of early sensing of fires as the smoke detectors are applied indoors, studies tend to place insufficient focus on the side effects and malfunction that can be caused by diversified life dust produced indoors and environmental requirements, etc. Therefore, in the present study, 4 types of photoelectric smoke detectors with different forms and structures of smoke chamber were selected as the experimental objects, and dust test was conducted with fly ash, talcum powder and fiber dust as experiment samples to study indoor applicability of the smoke detectors in terms of their response to diversified dust and wind velocity. Also, to observe response characteristics due to pollution level inside the smoke chamber, wind velocity for dust test were set additionally at 0.25 m/s, 0.5 m/s, and 1.0 m/s. Based to the experimental results, fly ash, talcum powder, and fiber dust (black hair powder) were found to be suitable at the dust test reference wind velocity conditions of 0.25 m/s for both operation test and non-operation test after dust application. On the other hand, under the harsh wind velocity conditions of 0.5 m/s and 1.0 m/s, malfunction of unwanted alarm was observed in non-operation tests in the case of fly ash and talcum powder, and non-operation was confirmed to occur in the case of fiber dust as the alarm failed to operate normally in operation tests.

아날로그 광전식 연기감지기 비화재보 개선에 대한 연구

아날로그 광전식 연기감지기 비화재보 개선에 대한 연구

Performance measurement of a smoke extraction system for buildings in full-scale hot smoke test

Abstract The current inspection method for a smoke extraction system in Taiwan measures whether the air flow of the smoke vent conforms to the design value. However, this method is inapplicable to natural smoke extraction systems. As the plugholing effect is disregarded, adequate air flow cannot ensure that the system will exhaust smoke effectively during a fire. Hence, a full-scale hot smoke test for smoke extraction systems is necessary. Some international test criteria are formulated using visible smoke and alcoholic fuel which is pollution-free after combustion. The effectiveness is judged only by visually observing the smoke’s flow direction, which is indeed unscientific. This study used a string of vertical smoke layer measuring instruments composed of several approved photoelectric smoke detectors, as well as a light attenuation measuring device composed of illuminance meters to conduct tests on the effect of makeup air. The results proved that the former one uses different height induction times to judge the position of the smoke layer effectively, while the latter one uses the light attenuation rate to distinguish the smoke density instantly and accurately. The obtained experimental data were consistent with the onsite smoke distribution. The two sets of equipment designed in this study can be used for full-scale hot smoke tests to obtain performance data for a smoke extraction system.