• Journal of the Korean Society of Safety
• /
• v.25 no.2
• /
• pp.29-34
• /
• 2010

This paper is aimed to develop monitoring software for detecting the characteristics of current and voltage signals for series arc on electric wire. In order to attain this purpose, the characteristics of series arc were analyzed by the current and voltage signals on electric wire which were installed, and also analyzed by the changes of RMS, instantaneous of waveform value in time domain and THD in frequency domain. Monitoring program which analyze the signal was developed by Labview which can analyze in time domain and frequency domain, and save data. Experimental setup for detecting verification of monitoring program was composed loads of a lamp, an electric heater and an electric fan loads which were usually using. Measurement points for detecting verification of monitoring program were selected at both the panel board and the arc generator at the same time. As results of the experiments by monitoring program, the arc current waveform showed the same characteristic in all measurement points of all load. But the arc voltage waveform was different in each measurement point. When arc occurred, the THD of current value increased above 20%. The results of this study will be effectively used in developing the preventive system of electric fire by series arc.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.2
• /
• pp.227-233
• /
• 2019

In recent years, vehicle fires account for the second highest rate after residential fires. It accounts for more than 10.7% of the total fire occurrence rate. Vehicle fires are very difficult to evolve at an early stage. Most of the vehicles are burned down in the event of a fire, resulting in a lot of physical and personal damage. In the EU and other countries, efforts are being made to install automatic fire extinguishing systems in preparation for vehicle fires. In addition, since the automatic fire extinguishing system applied to a vehicle must operate in a moving state of a car, a method for detecting a fire is needed. Therefore, this paper proposes a structure of an automatic fire extinguishing system that can evolve a fire when a fire occurs in a commercial vehicle among various vehicles. Especially, it confirms the feasibility of the automatic fire extinguishing system simulated in the laboratory environment and confirms its applicability.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.35-38
• /
• 2009

The paper presents an effective method to detect fire in video surveillance and monitoring system. The main contribution of this work is that we successfully use the Hidden Markov Models in the process of detecting the fire with a few preprocessing steps. First, the moving pixels detected from image difference, the color values obtained from the fire flames, and their pixels clustering are applied to obtain the image regions labeled as fire candidates; secondly, utilizing massive training data, including fire videos and non-fire videos, creates the Hidden Markov Models of fire and non-fire, which are used to make the final decision that whether the frame of the real-time video has fire or not in both temporal and spatial analysis. Experimental results demonstrate that it is not only robust but also has a very low false alarm rate, furthermore, on the ground that the HMM training which takes up the most time of our whole procedure is off-line calculated, the real-time detection and alarm can be well implemented when compared with the other existing methods.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.4
• /
• pp.237-245
• /
• 2017

This paper presents a fire detection algorithm using color and motion models from video sequences. The proposed method detects change in color and motion of overall regions for detecting fire, and thus, it can be implemented in both fixed and pan/tilt/zoom (PTZ) cameras. The proposed algorithm consists of three parts. The first part exploits color models of flames and smoke. The candidate regions in the video frames are extracted with the hue-saturation-value (HSV) color model. The second part models the motion information of flames and smoke. Optical flow in the fire candidate region is estimated, and the spatial-temporal distribution of optical flow vectors is analyzed. The final part accumulates the probability of fire in successive video frames, which reduces false-positive errors when fire-like color objects appear. Experimental results from 100 fire videos are shown, where various types of smoke and flames appear in indoor and outdoor environments. According to the experiments and the comparison, the proposed fire detection algorithm works well in various situations, and outperforms the conventional algorithms.

• Proceedings of the KSR Conference
• /
• 2009.05a
• /
• pp.457-465
• /
• 2009

Subway system including light-rail transit system is the representative public urban transportation. Accordingly, Nothing is more important than the safety operation as well as passengers' convenience. Due to the fire disaster of Daegu subway on 2003, more strict regulations of detecting fire and of conducting on emergency circumstances. However, regardless of this improved management, it was reported that installations of lots of fire-detection facilities may be harm than good to operate subway system due to frequent malfunction of some fire-detection facilities. It may cause mis-alarm for fire and induces abnormal operation of subway due to the strict regulation; the train shall be stopped on emergency circumstances. Therefore, in this paper, new scheme on surveiling breaking-out-of fire in the station is suggested with new IT technologies, Wireless Sensor Network(WSN) and CCTVs. which were integrated with an intelligent software. This intelligent system enables to surveil breaking-out-of fire in real time through sensor network technology and watch the emergency site on CCTV as well. Through this system, subway organizers could cope with the emergency circumstance rapidly as well as judge precisely whether fire breaks out or not.

• Journal of the Korean Society of Safety
• /
• v.37 no.4
• /
• pp.28-35
• /
• 2022

This study is aimed to develop a safety diagnosis system for fire pumps that detects normal and abnormal signals for the stable operation of the system. Hence, the following activities were carried out: first, a threshold value was identified for the normal operation and six abnormal operations (adherence of impeller, absence of water source, separation of pump and motor, run-stop operation, air inflow into the casing, and reverse-phase loss of the power line) reflecting changes in the current, flow and pressure of fire pumps; secondly, based on the identified signals, an algorithm capable of detecting three abnormal signals was developed and in terms of hardware, a current, pressure and flow sensor suitable for the analogue input values of NI-6009 was designed and installed. This combination of the hardware and software is applicable as a diagnosis system to ensure the stable operation of fire pumps.

• International Journal of Advanced Culture Technology
• /
• v.11 no.1
• /
• pp.320-324
• /
• 2023

As urbanization accelerates and facilities that use energy increase, human life and property damage due to fire is increasing. Therefore, a fire monitoring system capable of quickly detecting a fire is required to reduce economic loss and human damage caused by a fire. In this study, we aim to develop an improved artificial intelligence model that can increase the accuracy of low fire alarms by mixing DeepSORT, which has strengths in object tracking, with the YOLOv5s model. In order to develop a fire detection model that is faster and more accurate than the existing artificial intelligence model, DeepSORT, a technology that complements and extends SORT as one of the most widely used frameworks for object tracking and YOLOv5s model, was selected and a mixed model was used and compared with the YOLOv5s model. As the final research result of this paper, the accuracy of YOLOv5s model was 96.3% and the number of frames per second was 30, and the YOLOv5s_DeepSORT mixed model was 0.9% higher in accuracy than YOLOv5s with an accuracy of 97.2% and number of frames per second: 30.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.8
• /
• pp.1442-1449
• /
• 2016

This paper proposes a diagnosis to detecting poor contact fault and fault location. Electrical fire by poor contact fault of power cable occupied a large proportion in the total electrical installations. The proposed method has an object to prevent electrical fault in advance. But detecting poor contact fault is difficult to detect fault type and fault location by using conventional reflectometry due to faults generated intermittently and repeatedly on the time change. Therefore, in this paper poor contact fault and fault conditions were defined. System generating poor contact fault produced for the experimental setup. SSTDR and algorithm of reference signal elimination heighten performance detecting poor contact fault on live power cable. The diagnosis methods of signal process and analysis of reflected signal was proposed for detecting poor contact fault and fault location. The poor contact fault and location had been detected through proposed diagnosis methods. The fault location and error rate of detection were verified detecting accuracy by experiment results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7964-7970
• /
• 2015

In enclosed areas such as railway tunnels, the heat and smoke generated by a fire can pose a tremendous risk to the life of passengers. To prevent or mitigate such scenarios, fire detectors are installed for early fire detection. This numerical study is preformed for establishing the method of detecting performance of fire detectors installed on railway tunnels. Numerical analysis are conducted using the fire dynamics simulator, developed by the NIST. The temperature of the tunnel walls is determined using the assumed exterior structure of the tunnel. In addition, the detection times of detectors installed at different locations in the tunnel are obtained for different sizes of the fire source, and the results are compared and analyzed.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2008.11a
• /
• pp.7-10
• /
• 2008

In our study, Monitoring RF System in real-time on leakage of gas cylinder is developed. The system is consisted of Pressure Transmitting part, Main Controller and Operating program. The pressure data of gas cylinder are transmitted to the modem of main controller part by RF module of Pressure Transmitting part and the data received through the modem are recorded in real-time and showed the situation of gas cylinder on the PC monitor. Through the test on the case of the artificial pressure-reduction, the detecting performance. of the developed system is conformed.