Fire Detection Time Research Articles

Study on the Response Characteristics of Smoke Detectors Based on the ISO 7240-7 Smoldering Cotton Fire

In this study, a smoldering cotton fire test was conducted in accordance with ISO 7240-7 to analyze the smoke/aerosols and combustion products that occur during a cotton fire that are crucial flammable components of multi-unit dwellings. The results of the smoldering cotton fire experiment comparing ODM and ASD based on the concentration standard of 15 %/m, which are the operating concentrations of the fire detection of type-2 smoke detectors, indicated a delay of approximately 2∼4 min in the ASD fire detection time. In addition, in the case of the smoldering fire, the CO concentrations appeared to be 37 ppm and 62 ppm at the ASD<sub>1,2</sub> fire detector operating concentrations, resulting in high concentrations of combustion gas. Furthermore, in the case of a smoldering fire rather than a flame fire, despite a large amount of smoke/aerosol and gas owing to incomplete combustion because of the lack of buoyancy, it did not flow into the smoke detector chamber and was not distributed on the ceiling; this required a long time to detect the fire. Accordingly, smoke detector operation tests for various smoke/aerosols must be conducted in Korea to meet the international standards of firefighting technology.

Implementasi NodeMCU dan Blynk Dalam Sistem Pendeteksi Kebakaran Berbasis IoT

Fires can cause material losses and human lives. Therefore, an effective fire early detection system is needed to prevent greater losses. In this research, ESP8266 is used as a microcontroller to connect fire detection sensors such as KY-026 Fire Sensor and MQ-2 Smoke Sensor. This early fire detection system is also equipped with a buzzer as an alarm and NodeMCU as a platform to connect the system to the Internet network and Blynk as a medium to provide real-time fire notifications to users. Tests were conducted by comparing the response time and accuracy of fire detection at different distances. The test results show that the fire early detection system built has an average response time of 2 seconds and a detection accuracy rate of 95%.

Reduction of response time of fire detection and containment systems in compartments

Bench tests were performed on promising sensors used in fire safety systems in compartments. Activation delay times of fire sensors and systems were analyzed during the thermal decomposition and suppression of burning construction and interior design materials typical of compartments: wood, particle board, fiberboard, linoleum, cardboard, different types of wallpaper, paper and plastic. The thermal decomposition and ignition characteristics were identified using commercially available fire detectors of different types and designs (thermal, smoke and flame detectors), contact and non-contact temperature measurement instruments, a gas detection system and video recording equipment. Devices with the highest efficiency in terms of response time and detection reliability were determined that are necessary and sufficient to identify the thermal decomposition of construction and interior design materials at an early stage of fire. When generalizing the experimental data, mathematical equations were derived to predict the integral characteristics of the processes under study. Promising methods of reducing the response time of fire sensors and systems in general were determined. Guidelines were proposed on upgrading the existing systems of fire prevention in buildings and developing new automatic ones to significantly accelerate the detection of fires in buildings and optimize their containment and suppression.

Machine learning driven smart fire safety design of false ceiling and emergency response

In modern buildings, false ceilings are widely used for building services systems and aesthetic purposes, but they also pose challenges in terms of fire safety. A fire accident typically results from the failure of multiple safety measures or components. In many fire accidents, fire and smoke reached the false ceiling and kept spreading in the interstitial space without any detection. This study first generates a numerical database of false ceiling fire scenarios by varying the room dimensions, false-ceiling leakage area, fire size and locations. Then, a smart model based on machine learning to predict the fire smoke motion below and above the false ceiling is developed. The trained model is capable to predict the activation time of fire detectors and sprinklers for any given false ceiling design and fire scenario. This methodology enables a designer to generate multiple fire scenarios and determine the available safe egress time (ASET) for performance-based fire engineering designs especially in terms of fire detection time. In case of a real fire, with the data feed from the fire sensor network, the trained machine learning model can further predict the critical building fire events with the false ceiling, such as multi-compartment fires, smoke in the evacuation path, and structural failures. This work proposes a smart framework for improving the building fire safety design of false ceilings and the sensor-driven fire forecast to support firefighting.It enhances the emergency response processes by enabling dynamic risk assessment through prediction of critical events.

Full-scale experimental study on evacuation behavior characteristics of underwater road tunnel with evacuation stairs under blocked conditions

In recent decades, with the rapid development of the economy and tunnel construction technology, an increasing number of underwater road tunnels have been constructed in China. Underwater road tunnels play a crucial role in transportation hubs that connect cities and regions. Underwater tunnels have strong closures, which makes evacuation and rescue difficult. Therefore, personnel evacuation in emergencies, such as fires, has become a critical problem that needs to be solved. A full-scale evacuation experiment in an underwater shield tunnel with 188 participants was conducted to explore the characteristics of personnel evacuation behavior under the blocked condition of an underwater shield tunnel in the case of fire. The time of fire detection and personnel response, alighting time of passengers from vehicles, opening time of the stair-cover plate, evacuation capacity of stairs, and relationship between the evacuation speed and age and gender of participants were obtained. The experimental results showed that the driver’s actions had a strong demonstrative effect, and the improvement of the driver’s efficiency in handling emergencies could promote the evacuation process. The average alighting time per bus passenger was 1.41 ± 0.53 s, and proper personnel guidance, good road conditions, and increased tunnel familiarity reduced it. The average evacuation capacity of the stairs was 33.3 ± 4.1 person/min. When the proportion of older adults increased from 0 % to 10.64 %, the evacuation capacity of stairs decreased by approximately 8.5 %. The evacuation capacity of stairs can be significantly improved through reasonable organization and evacuation guidance. However, as the number of people gathered at the stair entrance gradually increased, the “bottleneck” effect became significant, and the evacuation capacity was primarily controlled by its structure at this time. The average evacuation speed for male and female was the same in good road conditions, about 1.39 m/s, but decreased significantly in blocked conditions, to 0.72 m/s and 0.48 m/s, respectively. Further, it decreased to 1.27 m/s and 1.23 m/s, respectively, in the secure channel, which may be related to the psychological state of relaxation and slackening and the increase in road pavement roughness.

Влияние высоты помещения на расчётное время обнаружения пожара

Introduction. Within the framework of this article, a quantitative and qualitative assessment of the influence of the height of the room on the estimated time of fire detection was carried out. Purpose. Assessment of the effect of the room height on the estimated fire detection time. Methods. Using the Fire Dynamics Simulator software system used to simulate the fire process, numerical experiments were carried out to study the fire detection time, which is considered in this article as an interval from the moment of fire start to reaching the values of optical density of smoke, at which point smoke fire detectors are triggered. Results and their discussion. As a result of numerical modeling of fire in rooms of different heights, data on the change in the optical density of smoke in the initial stage of fire are established. Based on the information received, the estimated time of fire detection by automatic fire alarm was determined according to the algorithms of triggering A and B at different values of permissible sensitivity for point smoke fire detectors, taking into account the height of the room. The results of numerical experiments can be used for expert assessment of the design time of fire detection as a "technical" component of the evacuation start time taken into account when determining the individual fire risk and conditions for safe evacuation of people. Conclusions. It was found that the height of the room has a slight impact on the estimated fire detection time. However, this effect is manifested in the case of the operation of point smoke detectors at the upper threshold of permissible sensitivity. To take into account the time of fire detection as part of the evacuation start time, further study of this issue is required with comparison of modeling results with the results of field experiments. Keywords: optical density of smoke; fire alarm; evacuation start time; fire detection time.

Development of early fire detection model for buildings using computer vision-based CCTV

A fire in a building directly affects the lives of its occupants. Therefore, a safer environmental system that can minimize the damage caused by a fire occurring indoors needs to be developed. Recent studies on computer vision-based rapid fire detection methods aim to overcome the limitations of general fire detectors and prevent false alarms using advanced deep learning technology. However, studies considering the development of a video fire detection model for indoor usage and its implementation in an actual test room are lacking. We developed a computer vision-based early fire detection model (EFDM) using an indoor closed-circuit television (CCTV) surveillance. The proposed EFDM derives the fire detection time through actual fire tests. The possibility and necessity of using fire detectors indoors is confirmed by comparing the results with the fire detection times of a general fire detector. The developed model achieves a recall, precision, and mAP0.5 performance of 0.97, 0.91, and 0.96, respectively. The fire recorded in the indoor fire video test dataset was detected within 8 s. The possibility of fire detection from three combustibles according to Underwriters Laboratories (UL) 268 B is confirmed via experimentation. A difference of up to 307 s is observed when the fire detection times of the EFDM and general fire detectors are compared. The useable range is confirmed by detecting a fire within 1 s of the maximum visible range of the CCTV. The proposed method can help contribute to the reduction of unfortunate property damages or casualties caused by a fire.

Effect of computational grid cell size and heterogeneity of computing area for estimated fire detection time

Introduction . In Russia, based on the provisions of the current regulatory documents, the time for the start of evacuation for a room in which a fire broke out is determined depending on the area of the room. According to some authors, the time of the start of the evacuation of people is a combination of “technical”, which includes the time of detection of a fire, and “psychophysical”, determined by the behavioral and organizational characteristics of the people who make it up. The fire detection time is currently not taken into account. Purpose . Evaluation of the influence of the size of the cells of the computational grid and the inhomogeneity of the computational domain on the estimated time of fire detection. Aims. 1. Establish the qualitative nature of the influence of the size of the cells of the computational grid and the inhomogeneity of the computational domain on the estimated time of fire detection. 2. Offer recommendations for determining the estimated time of fire detection. Methods . For research, computer simulation methods were used using the Fire Dynamics Simulator software package. Results and discussion . The use of grids with different cell sizes can significantly reduce the number of cells in the computational domain and, as a result, the computation time. However, this leads to rather contradictory results. The minimum time values are reduced by almost 3–4 times compared to a homogeneous computational grid, and the maximum time increases by 2 times. Conclusions . 1. The size of the cells of the computational grid and the inhomogeneity of the computational domain have a significant impact on the time of fire detection. 2. A sufficiently large spread in the values of the estimated fire detection time may indicate an unreliable estimate of the total time for the start of evacuation and incorrect conclusions about the safe evacuation of people and/or the probability of evacuation of people. 3. For a correct estimate of the evacuation start time, taken into account the estimated fire detection time, it is recommended to use homogeneous computational grids with cell sizes not exceeding 0.25 m.

Fire Sense

Abstract: The significance of putting out a fire as soon as possible can serve to warn others about the perils of disaster and death. Common sensor fire detection systems are limited, especially in a vast location, requiring a long time to detect a fire, and are unable to work in an open environment. This study developed a fire sense approach based on visual sensitivity and colourful variables such as colour, earth filling, light, backdrop, and fire detection time to assess the likelihood of a fire. The degree of error of fire detection was calculated in this study’s test. Keywords: Fire Detection, HSV, Time Frame Selection, Alert System, Fire Alarm

An improved theoretical model for the maximum smoke temperature rise in a tunnel based on equivalent fire source

The maximum smoke temperature rise underneath tunnel ceiling is of great importance for the assessment of heat exposure, estimation of fire detection time and possibility analysis of fire spread. Previous studies mainly focused on the scenario with a single fire source, but the existence of two fire sources is common due to the increase traffic volume. The maximum smoke temperature rise induced by two fire sources is studied through theoretical analysis in this study. A virtual equivalent fire source is proposed, which is mainly affected by the total fire heat release rate (HRR) of two fires, longitudinal ventilation velocity, effective tunnel height and separating distance between two fires. The HRR of the equivalent fire source decreases with a longer separating distance, which indicates that the influences of the downstream fire on the maximum ceiling temperature weakens gradually as the separating distance increases. An improved model on the maximum ceiling smoke temperature rise caused by two fire sources was developed, and the predictions based on the revised model agree well with the experimental data.

Влияние расстояния от плоскости горения очага пожара до уровня установки пожарных извещателей на расчётное время обнаружения пожара

Introduction. The analysis of existing methods for determining the estimated time of fire detection by means of fire automatics allows us to conclude that it is advisable to use a more differentiated approach. Within the framework of this article, the assumption about the influence of the distance from the burning plane of the fire seat to the level of installation of fire detectors (to the sensitive elements of point smoke fire detectors) on the estimated time of fire detection was carried out. In particular, such an effect can be observed during a fire involving the burning of furniture, shelving, etc., i.e. in cases where the above distance is potentially shortened. Goals and objectives. The aim of the work is to study the influence of the distance from the burning plane of the fire seat to the level of installation of fire detectors (to the sensitive elements of point smoke detectors) on the estimated time of fire detection. Research methods. To assess the influence of the distance from the burning plane of the fire seat to the level of installation of fire detectors (to the sensitive elements of point smoke fire detectors) on the estimated time of fire detection, computer simulation methods were used using the Fire Dynamics Simulator software package. Results and its discussion. The results of modeling the dynamics of the optical density of smoke in a room at various distances from the burning plane of the fire seat to the level of installation of fire detectors (to the sensitive elements of point smoke fire detectors) are presented. The distance varied in the range from 0.25 to 2.75 m. Conclusions. It has been established that the distance from the burning plane of the fire source to the level of installation of fire detectors (to the sensitive elements of point smoke detectors) does not have a significant effect on the estimated time of fire detection. The difference in the values of the estimated fire detection time for different values of the distance from the burning plane of the fire source to the level of installation of fire detectors and the value obtained on the basis of the existing method for determining the time of the start of evacuation may indicate an unreliable assessment of the total time of the start of evacuation and incorrect conclusions about safe evacuation people and/or the likelihood of people evacuating. To correctly take into account the time of the beginning of the evacuation, further study of this issue and comparison of its "technical" component, obtained by calculation methods, with the results of field experiments is required. Keywords: fire safety, fire protection, fire detection time, fire alarm, evacuation probability, smoke optical density, evacuation time, evacuation start time, fire risk.

An Energy-Efficient Wireless Power Transmission-Based Forest Fire Detection System

Compared with the traditional techniques of forest fires detection, wireless sensor network (WSN) is a very promising green technology in detecting efficiently the wildfires. However, the power constraint of sensor nodes is one of the main design limitations of WSNs, which leads to limited operation time of nodes and late fire detection. In the past years, wireless power transfer (WPT) technology has been known as a proper solution to prolong the operation time of sensor nodes. In WPT-based mechanisms, wireless mobile chargers (WMC) are utilized to recharge the batteries of sensor nodes wirelessly. Likewise, the energy of WMC is provided using energy-harvesting or energy-scavenging techniques with employing huge, and expensive devices. However, the high price of energy-harvesting devices hinders the use of this technology in large and dense networks, as such networks require multiple WMCs to improve the quality of service to the sensor nodes. To solve this problem, multiple power banks can be employed instead of utilizing WMCs. Furthermore, the long waiting time of critical sensor nodes located outside the charging range of the energy transmitters is another limitation of the previous works. However, the sensor nodes are equipped with radio frequency (RF) technology, which allows them to exchange energy wirelessly. Consequently, critical sensor nodes located outside the charging range of the WMC can easily receive energy from neighboring nodes. Therefore, in this paper, an energy-efficient and cost-effective wireless power transmission (ECWPT) scheme is presented to improve the network lifetime and performance in forest fire detection-based systems. Simulation results exhibit that ECWPT scheme achieves improved network performance in terms of computational time (12.6%); network throughput (60.7%); data delivery ratio (20.9%); and network overhead (35%) as compared to previous related schemes. In conclusion, the proposed scheme significantly improves network energy efficiency for WSN.

A Fast Video Fire Detection of Irregular Burning Feature in Fire-Flame Using in Indoor Fire Sensing Robots

Indoor fire sensing robot could become the best choice to detect irregularity feature in the complex situation with help of nascent visual technologies. This paper works on improvement computational time and accuracy of video fire detection (VFD) using on those robots. The profile of flame is first identified by flame luminance and chrominance using the proposed VFD network. A more efficient layer aggregation connection is designed to improve detection accuracy. The proposed feature pyramid layer combining ghost convolution and cross-connection improves the feature extraction ability. Improvements in re-parameterized blocks with residual connections increase inference speed. The irrigation feature of fast burning fire flame in the incipient, growth, full-developed and decay stages are fully detected with analysis of the proposed visualized Heat Release Rate (vHRR) with spark, flicker, and other dynamic disturbances involved. Compared with high-performance methods, the average detection accuracy of this method on public datasets and self-built datasets is improved by 3.5% and 2.3%. Five indoor representative scenarios illustrate that our method achieves a good balance between the detection accuracy and speed of flame trends. In the future, the model could be deployed in lightweight, fast-moving indoor sensor robots for fire detection in hazardous environments.

Research on Application of the Feature Transfer Method Based on Fast R-CNN in Smoke Image Recognition

Most of the existing smoke detection methods are based on manual operation, which is difficult to meet the needs of fire monitoring. To further improve the accuracy of smoke detection, an automatic feature extraction and classification method based on fast regional convolution neural network (fast R–CNN) was introduced in the study. This method uses a selective search algorithm to obtain the candidate images of the sample images. The preselected area coordinates and the sample image of visual task are used as network learning. During the training process, we use the feature migration method to avoid the lack of smoke data or limited data sources. Finally, a target detection model is obtained, which is strongly related to a specified visual task, and it has well-trained weight parameters. Experimental results show that this method not only improves the detection accuracy but also effectively reduces the false alarm rate. It can not only meet the real time and accuracy of fire detection but also realize effective fire detection. Compared with similar fire detection algorithms, the improved algorithm proposed in this paper has better robustness to fire detection and has better performance in accuracy and speed.

Operational algorithm for a heat detector used in motor vehicles

In most cases, fixed temperature heat detectors are used to detect fire in vehicles. The response parameter of such detectors is constant. The time of fire detection by a fire detector, as well as the probability of its false operation, are affected by heat flux from an internal combustion engine. This paper reports the development and investigation of an operational algorithm of the fixed-dynamic heat detectors with variable response parameters. Depending on the temperature influence exerted by engine operation modes, a given algorithm automatically changes a value of the minimal static response temperature of a detector, as well as value of the rate of rise in the temperature of its response. The experimental results showed that in the initial period of engine operation, the temperature change rate in the engine compartment fluctuates and is the largest. It can exceed 290 °С/min. However, regardless of the type of vehicle and the type of engine, when the temperature reaches technological, the temperature change rate would vary within small limits, approximately 30÷50 °С/min. The study results from the Simulink software package (USA) in the MATLAB programming environment (USA) confirm the effectiveness of the programmed operational algorithm of a thermal fire detector. The developed algorithm of a fire detector's operation makes it possible to detect the fire at an early stage and reduce the cases of the device's false response. The fire detector responded to both the maximal and dynamic components. As regards the maximal component, the proposed detector is triggered about 2.3 times faster than the classic maximal thermal fire detector. Detection of fire at an early stage makes it possible to quickly use the fire extinguishing system

Multi-Sensor Data Fusion Algorithm for Indoor Fire Early Warning Based on BP Neural Network

Fire early warning is an important way to deal with the faster burning rate of modern home fires and ensure the safety of the residents’ lives and property. To improve real-time fire alarm performance, this paper proposes an indoor fire early warning algorithm based on a back propagation neural network. The early warning algorithm fuses the data of temperature, smoke concentration and carbon monoxide, which are collected by sensors, and outputs the probability of fire occurrence. In this study, non-uniform sampling and trend extraction were used to enhance the ability to distinguish fire signals and environmental interference. Data from six sets of standard test fire scenarios and six sets of no-fire scenarios were used to test the algorithm proposed in this paper. The test results show that the proposed algorithm can correctly alarm six standard test fires from these 12 scenarios, and the fire detection time is shortened by 32%.

Real-Time Fire Detection Algorithm Based on Support Vector Machine with Dynamic Time Warping Kernel Function

In recent years, the development of fire detectors has attracted the attention of researchers for the purpose of protecting human lives and properties from catastrophic fire disasters. However, monitoring fires is challenging due to several unique characteristics of fire sensor signals, such as the existence of temporal dependency and diverse signal patterns for different fire types, including flaming, heating, and smoldering fires. In this study, we propose a new approach for fire detection based on machine learning and optimization techniques, to monitor various types of fire by utilizing information obtained via multichannel fire sensor signals. The contribution of this study is to improve an existing fire detector by developing a new fire monitoring framework to identify fire based on support vector machine with dynamic time warping kernel function (SVM-DTWK), which considers the temporal dynamics existing in the sensor signals of different fire types. In addition, multichannel sensor signals are further considered by the SVM-DTWK with a multi-modeling framework that constructs multiple classifiers for each sensor type and effectively utilizes sensor information that is critical for the detection of fires without prior knowledge of the fire type. Using real-life fire data, the proposed approach is compared with existing fire monitoring methods and achieves superior performance in terms of both fire detection time and false alarm rate.

EQUATIONS FOR THE OPERATING TEMPERATURE OF THERMOSENSITIVE ELEMENTS OF FIRE DETECTORS EMBEDDED IN A CONCRETE BLOCK

Statement of the problem. Solving the problem of giving the properties of a building structure to detect fires outside buildings is one of the ways to prevent the transition of fire from one building to another. Embedding of fire automation equipment in construction products should be carried out after making the appropriate calculations. The absence of an expression for determining the temperature of the heat-sensitive element of a fire detector inside a concrete block requires detailed calculations. At the same time, it is necessary to study the influence of the distance to the object of a possible fire, the size of the heat-sensitive element, and the heat flow on the time of fire detection by a construction product included in the smart home system.Results. As part of the temperature measurement of heat-sensitive elements of fire detectors inside the concrete block, empirical data were obtained. This information allows us to describe the radiant heat exchange at an early stage of a fire. This is typical of open burning outdoors. Conclusions. Approximate equations are obtained for determining the temperature and response time of a fire detector inside a concrete block at the initial stage of a fire, depending on the distance to the fire object (radiation source), heat flow, and the size of the thermosensitive element. These values can be determined with sufficient accuracy.

Numerical investigation on fire accident and evacuation in a urban tunnel for different traffic conditions

A fire outbreak in a urban tunnel with congested traffic may pose a great danger to all tunnel users. The main threat to human life in an urban tunnel fire is thick toxic smoke quickly filling large parts of the tunnel. It hinders evacuation and may even lead to lethal intoxication. Due to the potentially rapid development of the fire, people trapped will need to evacuate on their own. Thus, tunnel safety systems must support their self-rescue efforts. In this paper, several scenarios of fire accidents in a real urban tunnel are numerically investigated. The scenarios differed in road traffic state, fire power and fire detection time. To make them realistic the entire sequence of events during a tunnel fire was numerically modeled. First, the formation of congestion is examined using VISSIM software, then fire development is simulated by Fire Dynamic Simulator and finally, the evacuation process is modeled by PATHFINDER software. All data needed to build these numerical models correspond to real conditions of the selected urban tunnel under the Martwa Wisła river in Gdansk (Poland). The outcomes of the work suggest the number of threatened people may be very large even under common circumstances. In the worst case over a half of people trapped inside may come into contact, at least temporarily, with factors threatening health or live.

Field modeling of the fire dynamics as an answer to the question about the fire alarm performance

Introduction. The performance of a fire alarm needs to be analyzed to answer the question about its compliance with fire safety requirements. This type of research is frequently performed in the course of a forensic fire investigation. Therefore, it is necessary to identify conditions of fire escalation and safe evacuation of people to assess the fire alarm performance.Purposes and objectives. The purpose of this work is the numerical study of the impact, produced by mathematical models of combustion, characteristics of fire loads and locations of fire beds, on fire alarm performance. Methods. Fire dynamics was field modeled to achieve the goal of this research. The analysis of flame propagation was performed with regard for various fire bed locations to simulate the fire alarm operation.Results and discussion. The fulfillment of safe evacuation conditions for cases of irregular arrangement of smoke detectors was analyzed to develop and test the algorithm for the calculation of the evacuation start time. It is shown that the estimated time of fire detection depends on combustion models employed (their average or complex level), the size of the computational grid, fire load specifications and the location of the fire bed.Conclusions. It is shown that the results of the field modeling of fire propagation and detection time are influenced by combustion models used, fire load specifications and the location of the fire bed in relation to smoke detectors. If the fire alarm fails to perform its functions and, consequently, safe evacuation conditions are not fulfilled, it is necessary either to improve the combustion model or to compare the modeling results obtained for actual and standard smoke detector location patterns.