• 한국안전학회지
• /
• 제32권6호
• /
• pp.22-28
• /
• 2017

According to the National Fire Data System (NFDS), more than 5,000 vehicle fires have occurred every year for the last 10 years. Vehicle fires are primarily caused by mechanical (breaking system and engine), electrical (wiring and battery), and chemical (oil and fuel gas leakage) problems. The electrical factor has increased with the installation of driver convenience equipment. For example, today, the black box is widely used to provide video data recording of motor vehicle accidents. The black box consists of a front camera, rear camera, and wires. The black box wires are directly connected to the junction box or fuse box from the start battery that operates to provide normal on power supplying for engine stop. It is extremely dangerous when the wires short circuit due to insulation aging, mechanical and electrical stress, etc. In this study, the black box wiring fire risk have been analyzed and investigated when the steady state and abnormal operations, and under the following conditions: wiring arrangements with a high temperature condition, insulation aging, poor contact, and short circuits. The results showed that black box wiring short circuits had a higher fire risk than the other fire hazard elements. To prevent fire hazards caused by black box wiring, the black boxes must be installed by qualified service personnel. Do not modify the wiring, remove the fuse and secure the wiring using cable ties or insulation tape.

• 한국전기전자재료학회논문지
• /
• 제37권3호
• /
• pp.261-273
• /
• 2024

This paper is an experimental study on the improvement of smoke and flame detection from different materials with YOLO. For the study, images of fires occurring in various materials were collected through an open dataset, and experiments were conducted by changing the main factors affecting the performance of the fire object detection model, such as the bounding box, polygon, and data augmentation of the collected image open dataset during data preprocessing. To evaluate the model performance, we calculated the values of precision, recall, F1Score, mAP, and FPS for each condition, and compared the performance of each model based on these values. We also analyzed the changes in model performance due to the data preprocessing method to derive the conditions that have the greatest impact on improving the performance of the fire object detection model. The experimental results showed that for the fire object detection model using the YOLOv5s6.0 model, data augmentation that can change the color of the flame, such as saturation, brightness, and exposure, is most effective in improving the performance of the fire object detection model. The real-time fire object detection model developed in this study can be applied to equipment such as existing CCTV, and it is believed that it can contribute to minimizing fire damage by enabling early detection of fires occurring in various materials.

• 한국안전학회지
• /
• 제27권1호
• /
• pp.14-19
• /
• 2012

This study proposes to suggest a direction hereafter which is the most suitable operating system of electrical safety management agency for electrical facilities to enhance electrical safety considering our domestic conditions. It was designed to prevent electrical disasters which are increasing due to environmental changes in the electrical industry, and the diversification and complication of the electrical facilities. And the strategy of this research is based on conditions of safety management agency for the electrical facilities, with the analysis on conditions of electrical disasters, and with a questionnaire investigation for owner of electrical facilities, safety management agency. Results of this research are expected to be used to prevent electric fires and shocks effectively by reinforcing the electrical safety management agency of electrical facilities having danger of large-scaled accidents. It is expected to enhance the nation's competing power against foreign countries by reducing the human and physical loss, resulted from the development of reasonable operating system for electrical safety management agency.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.255-257
• /
• 2021

매년 전기 사용량이 급증하는 동절기에 전통시장, 찜질방 등 다중이용시설과 아파트, 다가구주택 등 집합건물에서 노후화된 전기시설의 누전으로 인한 화재가 빈번해 지고 있다. 이러한 화재의 원인은 대부분 노후화된 전선에 과도하게 걸리는 부하로 전선 피복이 녹아내리며 주변의 발화물질에 옮겨붙어 발생하고 있다. 본 연구에서는 복합센서를 통해 전선에 걸리는 과부하와 과열을 측정하고 여기서 발생하는 유독가스를 검출하여 게이트웨이를 통해 서버에 로깅하는 시스템을 구현한다. 이를 바탕으로 빅데이터 분석을 통해 실시간 전기화재를 예측하고 경보하고 차단할 수 있는 플랫폼과 모의 화재 발생 실험이 가능한 시뮬레이터를 개발한다.

• 한국전기전자재료학회논문지
• /
• 제30권4호
• /
• pp.258-262
• /
• 2017

Recently energy consumption has been increasing because of advances in the industry, and electrical fires have accounted for 31.9% of all fire accidents. An electrical fire is caused by a short circuit, power surge, or poor contact. Safety devices for short circuits or power surges are currently mandatory and can actually detect problems, but arcing caused by contact failure is difficult to detect in advance. This study used an IR sensor to detect the heat concentration caused by the arc. The data from the low-resolution sensor was amplified as much as four times by interpolation to find the exact location of the heat source and were then investigated.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.811-813
• /
• 1996

High impedance fault can not be easily detected by conventional method. But if it would not be detected and cleared quickly, it can result in fires, and electric shock. In this paper, neural network, which has learning capability, is used for high impedance fault detector. The potential of the neural network approach is demonstrated by simulation using KEPCO's measured data. The instantaneous values and frequency spectrum of current are respectively used as the inputs of neural networks. Also, the methods using combined data to exploit the advantage of each data are proposed. In this paper, back-propagation network(BPN) is used for high impedance fault detector and can use for high speed relay because it detects faults within 1 cycle.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2007년도 추계학술대회 논문집
• /
• pp.478-479
• /
• 2007

Many electrical fires are occurred by leakage currents and sparks generated by a short circuit. Earth leakage circuit breakers (ELCBs) should be tripped at the moment of the faults mentioned above. In this paper, we described the tripping characteristics of ELCBs against parallel arcing faults. A diesel engine generator with the capacity of 375 kVA source was adopted to provide enough large current when a parallel arcing occurred. The experimental results showed that most ELCBs we experimented were not tripped against short-duration pulse currents produced by parallel arcing because the ELCBs are designed to be tripped by a large current with long duration similar to power frequency.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 C
• /
• pp.1655-1657
• /
• 2004

The electrical fire frequently happens through carelessness of a vinyl and rubber cords such as a poor contact, a mechanical stress and so on. Electrical fire occupies the greater part(about 30%) of all fires in Korea. In this paper, we compared to the fire dispersive patterns of vinyl and rubber cords according to the external flame in the wall-model. The fire progress and dispersive patterns were measured by a high speed imaging system(HG-100K, REDLAKE, USA). From the results, short-circuit of the vinyl cords are easy to happen than the rubber cords by the external flame. The pattern of fire was progressed a flashover, scattering and disconnection. The fire progress on the vinyl cord is not observed because the ignition energy decreases. However, the fire was progressed continuously on the rubber cord.

• 한국안전학회지
• /
• 제24권3호
• /
• pp.13-18
• /
• 2009

This paper is purposed to develop DAQ H/W, S/W and DB which can be used in developing electrical fire alarm system or in analyzing electrical fire cause, by detecting and monitoring precursor signals which have high possibility leading to electrical fire on electrical distribution wires. In this paper, developed was DAQ H/W adopting the C8051FXXX CPU which can analyze the measurement signals of current and voltage in electrical distribution wires, other CPU was investigated in view of the best digital sampling rate on the basis of previous researches for electrical fire alarm system. Also, the S/W which can interface with DAQ H/W's communication protocol and can be applied for electrical fire causes analysis, are embodied by LabVIEW. The combined DAQ H/W and S/W could analyze efficiently normal as well as abnormal electrical signals such as RMS value, instantaneous value of current and voltage, frequency signals etc, on the electrical wires. Also, DB system was constructed for recording various analysis results for precursor signals including voltage and current signals. The results by simulator and experiment showed that the suggested scheme with DAQ H/W, S/W and DB in this paper has high usability.

• 전기학회논문지
• /
• 제63권2호
• /
• pp.313-318
• /
• 2014

In the last couple of decades industrialization and technological development has not only increase in the scale of electrical facilities and it has become more and more complicated and diversified. Furthermore, fires in the electrical transformers, like those that have knocked out power in the country in the past years, are likely to become more common as utility systems begin to show their age. The importance of preventing electrical accidents can never be overemphasized and for this reason, supply of on-line diagnosis system combining information and communication technology(ICT) for the customer's electrical facilities has been increasing recently. The major advantage of on-line diagnosis system is that the device's potential problems could be detected early before a serious deterioration or breakdown occurs. In this paper, We estimated the benefit from the investment in the right of present value of sales, success rate of commercialization regarding R&D investment for development and commercialization of on-line diagnosis technology targeting customer electrical facilities. As a result, the net value added of 29.7 billion won and the increased profit by roughly 7.52 precent are expected.