Smart Fire Detector utilizing IoT-based Zigbee Sensor

<pre>There are several differences between the two types of alarm systems, conventional systems and addressable systems. It is important to carefully determine the introduction of a fire alarm system according to the installation environment. Talking about the main difference relates to how the connected device communicates with the main control panel by sending a signal. Cost is another factor that can be a determinant of your chosen fire alarm system. In this paper, we proposed smart addressable fire detection system. In the proposed system, <span>IoT</span> was used and the network was constructed using <span>ZigBee</span> module. In the configured network, it consists of a local server and a control server. The local server controls the addressing sensor and sends the information obtained from the sensor to the control server. The control server receives data transmitted from the local server and enables quick fire action. In the actual implementation, the local server used the Lycra controller and <span>ZigBee</span> module. In addition, the control server used the Raspberry Pi and <span>ZigBee</span> modules and connected to the Ethernet so that the administrator could monitor or control the local server.</pre>

TEMPERATURE ERROR WHEN DETERMINING THE TIME PARAMETER OF A FIRE DETECTOR WITH A THERMORESISTIVE SENSITIVE ELEMENT

For fire detectors with a thermoresistive sensing element, a mathematical description of the reaction to the thermal action of an electric current pulse flowing through such a sensing element and having the shape of a right triangle is obtained. The mathematical description is constructed using the Laplace integral transformation and is shown to be a superposition of two Heaviside functions. The parameters of these functions are determined by the transmission coefficient and time constant of the thermoresistive sensitive element of the fire detector and the amplitude and duration of the electric current pulse. It is shown that the ratio of the output signals of the thermoresistive sensitive element of the fire detector at two a priori given moments of time can be used to determine the time parameter of the fire detector. The values ​​of a priori set moments of time, in which the temperature of the thermoresistive sensitive element of the fire detector is determined, are selected under the condition of simplicity of technical implementation. If there is a change in ambient temperature, it leads to a temperature error as a function of the time parameter of the fire detector. For such an error, a mathematical description is obtained in the general case, as well as for the case when the thermal influence on the thermoresistive sensitive element of the fire detector is due to the flow of an electric current pulse in the form of a right triangle. It is shown that the value of the temperature error has a minimum at the values ​​of the ratio of the output signals of the thermoresistive sensitive element of the fire detector at two a priori time points belonging to the range The value of this error does not exceed 4.9% with variations in ambient temperature, the value of which does not exceed 2.0%.

EVALUATION OF THE IMPLEMENTATION OF ACTIVE FIRE PROTECTION SYSTEM AT ERNALDI BAHAR SUMATERA SELATAN

Introduction: The hospital is a place that is quite prone to fire hazards. Ernaldi Bahar has various characteristics of activities that have the potential to cause fires such as medical and administrative activities that use electrical installations as well as the use of intensive fire sources in kitchens, laundry or generator rooms as well as the presence of relatively high burning materials sourced from various medicines, chemicals, LPG gas cylinders and oxygen. The purpose of the research is to evaluate the implementation of active fire protection system at Ernaldi Bahar. Methods: This study uses qualitative methods with observational approaches, interviews and document studies. Result: The results showed that the active fire protection system at Ernaldi Bahar Hospital is well categorized with a percentage of 69% value with the results of fire alarm analysis based on Kepmen PU No.10 Year 2000, NFPA 72 and SNI 03-3985-2000 (81%), fire detector analysis based on NFPA 2000 and SNI 03-3985-2000 (100%), apar analysis based on NFPA 10 (89%), building hydrant analysis based on Permen PU No.26 Year 2008 and SNI 03-1745-2000 (73%), analysis of page hydrants based on Permen PU No.26 Year 2008 and SNI 03-1745-2000 (73%), and Sprinkler analysis based on SNI 03-3989-2000 (0%). Conclusion: Active fire protection system has been implemented well with a percentage of 69% value but it need some improvement in maintenance, placement, recording and completeness of active fire protection system components. Keywords: Hospital, Fire, Active Fire Protection System

PULSE METHOD FOR DETERMINATION OF TIME PARAMETERS THERMAL FIRE DETECTOR

For thermal fire detectors with a thermoresistive sensitive element, the method of determining its time parameters is justified. The time parameters of operation and the time constant of the thermal fire detector are considered as time parameters. The method is based on the use of the Joule-Lenz effect, for the implementation of which single pulses of electric current are passed through the thermoresistive sensitive element of the fire detector. Pulses having the shape of a quarter sinusoid or a quarter cosinusoid are used as such test signals. Using the Laplace integral transformation, analytical expressions are obtained, which represent the formalization of the reaction of the thermoresistive sensitive element of the fire detector to the corresponding test signals. These analytical expressions are used to obtain the functional dependences of the fire detector time constants on the pulse duration of the electric current and the auxiliary parameter. The auxiliary parameter is the ratio of the values ​​of the output signal of the thermal fire detector at two fixed points in time. This choice of auxiliary parameter allows to ensure invariance with respect to the transfer coefficient of the thermal fire detector with a thermoresistive sensing element. The fixed moments of time are chosen to be equal to half and three quarters of the duration of the pulses of electric current flowing through the thermoresistive sensitive element of the fire detector. The time of operation of the thermal fire detector is determined in the form of two additive components, one of which is a time constant of the fire detector, and the other is determined by the values ​​of normalized parameters in accordance with existing regulations. A sequence of procedures is given, which together represent a method of determining the time parameters of thermal fire detectors of this type.

An Improvement of the Fire Detection and Classification Method Using YOLOv3 for Surveillance Systems

Currently, sensor-based systems for fire detection are widely used worldwide. Further research has shown that camera-based fire detection systems achieve much better results than sensor-based methods. In this study, we present a method for real-time high-speed fire detection using deep learning. A new special convolutional neural network was developed to detect fire regions using the existing YOLOv3 algorithm. Due to the fact that our real-time fire detector cameras were built on a Banana Pi M3 board, we adapted the YOLOv3 network to the board level. Firstly, we tested the latest versions of YOLO algorithms to select the appropriate algorithm and used it in our study for fire detection. The default versions of the YOLO approach have very low accuracy after training and testing in fire detection cases. We selected the YOLOv3 network to improve and use it for the successful detection and warning of fire disasters. By modifying the algorithm, we recorded the results of a rapid and high-precision detection of fire, during both day and night, irrespective of the shape and size. Another advantage is that the algorithm is capable of detecting fires that are 1 m long and 0.3 m wide at a distance of 50 m. Experimental results showed that the proposed method successfully detected fire candidate areas and achieved a seamless classification performance compared to other conventional fire detection frameworks.

Study on Smoke Detector Characteristics Using Fire Simulations

To reduce the damage caused by fire detector malfunctions, we investigated the standards and literature pertaining to fire detectors in Korea. The domestic standards cite UL's technical specifications, which provide only the standards and types of combustible materials; however, additional research is needed because no facilities related to the experiments are investigated and no fire experiments have actually been conducted. In this study, we refer to UL 268, which is similar to the domestic standards, as well as detailed experimental conditions and methods to improve smoke detector performances; we also use wood as the combustion material from among the fire sources specified in UL 268. Experiments were conducted to measure the sensitization rates using an optical density meter and repeated to match the wood smoke profile standard provided in UL 268. Furthermore, we compared the smoke concentrations detected by the smoke detectors in the fire experiments with those from fire simulations using FDS software to confirm the detector characteristics. Through these comparisons, we show that this research could be used as preliminary data for performance testing of detectors using UL 268.

Detection and Monitoring a Forest Fire using GSM Module

In the present arena, wildlife and forest departments are facing the problem of movement of animals from forest area to residential area. The number of trees has reduced drastically from the forest that creates an unhealthy environment for animals to survive in the forest. It has been found in a survey that 80% losses are caused due to fire. This could have been avoided if the fire was detected in the early stages. This project proposes a system for tracking and alarming for the protection of trees against forest fires. Nowadays IOT (Internet of Things) devices and sensors allow the monitoring of different environmental variables, such as temperature, humidity, moisture etc. Arduino platform based IOT enabled fire detector and monitoring system is the solution to this problem. In this project we have built fire detector using ESP32 which is interfaced with a fire sensor and a buzzer. In order to implement this project, we will be using GSM which is used to provide the final SMS to the user through the given number in the simulation program. The sensor data is displayed on LCD. Whenever a fire occurs, the system automatically senses and alerts the user by sending an alert to an app installed on user’s android mobile.

A Study on the Real-time Fire Classification Algorithm Based on Stacked LSTM

Several researchers have been drawn to the development of fire detector in recent years, to protect people and property from the catastrophic disaster of fire. However, studies related to fire monitoring are affected by some unique characteristics of fire sensor signals, such as time dependence and the complexity of the signal pattern based on the variety of fire types,. In this study, a new deep learning-based approach that accurately classifies various types of fire situations in real-time using data obtained from multidimensional channel fire sensor signals was proposed. The contribution of this study is to develop a stacked-LSTM model that considers the time-series characteristics of sensor data and the complexity of multidimensional channel sensing data to develop a new fire monitoring framework for fire identification based on improving existing fire detectors.