Earticle

In recent years, along with the increase in the use of electrical energy, the number of electrical disasters tends to increase. An electrical connection exists to use the electrical energy where it is needed, and the contact resistance increases at the electrical connection, causing electrical heat generation. Electric fires are caused by such electrical heat generation. In this paper, we evaluated the fire risk of electrical connection finish treatment methods. It has been confirmed that the twist connection by the finish treatment method of the electrical connection causes a relatively high temperature rise, resulting in a high risk of fire. When a dedicated connection terminal was used for the electrical connection, the temperature rise occurred in a limited manner, and the temperature change to the extent that it led to a fire did not occur. Therefore, in order to prevent fires from occurring at the electrical connections that inevitably occur, it is judged that fires can be minimized by using dedicated connection terminals.

본 논문에서는, 단락흔과 열흔 판별을 위한 CNN기법과 ResNet의 성능 분석을 비교 분석하는 알고리즘 을 제안하고 검증하였다. 학습을 위한 데이터는 실험을 통해 제작하여 원본 데이터로 생성한 후, 알고리즘에 적용 시켜 학습데이터와 검증데이터로 확보하였다. Resnet 기법을 활용하여 CNN의 오차를 줄이는 방법으로 신경망의 파라미터를 학습하는 것과는 다르게 입력과 출력의 차이를 이용하는 잔차 학습(Residual learning)을 도입함으로 써, 더욱 깊은 네트워크층을 사용하여 효율적으로 학습 가능한 구조를 나타내고 있다. 분석결과 CNN과 Resnet 판별 정확도는 각각 93,54%, 96.81%로 얻었다.

In this paper, we proposed and verified an algorithm that compares and analyzes the performance analysis of the CNN method and Resnet for the distinguish Arc beads and Molten mark. The data for training was produced through experiments and generated as original data, and then applied to the algorithm to obtain training data and validation data. Unlike learning neural network parameters as a way to reduce CNN errors using Resnet techniques, by introducing Residual learning that utilizes the difference between input and output, it shows a structure that can be efficiently learned using a deeper network layer. As a result of the analysis, the CNN and Resnet classification accuracies were 93.54% and 96.81% respectively.

Determining the short circuit of molten rock found at the site when determining the cause of the fire is a very important clue to estimate an electrical fire or ignition point. Characteristics such as pores, metal structures, and boundary surfaces, which are the determining factors of short circuit wounds, are quantified with objective numerical data. As a result, the difference by the thickness of the boundary surface is analyzed as the most suitable criterion for determining whether the melt is shorted or not, and the cause of the difference is due to the difference in the occurrence time of the shorting wound due to the coating melt.

With the steady increase in electricity use, electric fires account for more than 20% of the total number of fires each year. Electrical fires are caused by electrical arcs or sparks inside the cover of wires, but they are also caused by external flames melting the cover of wires into contact with each other. In electric fires, melting of wires is usually found, which is commonly referred to as short circuit. The molten marks are divided into the primary one that occurs inside the wire and causes the fire directly, the secondary one caused by external fire, and the heat melt found in the unenergized state. Scientific criteria for the distinction between primary and secondary molten mark is presented by using qualitative and quantitative analysis, through analytical chemistry such as SEM and EDS, XRD and EA.

본 연구는 지하주차장 전기자동차 화재 발생 시 환경적 특성과 이용자 행동 특성을 반영한 대피 안정성 확보를 위하여 서비스디자인을 적용한 개선 방향을 제시하기 위하여 실시하였다. 이를 위하여 사용자 중심의 해결책을 모색하는 서비스디자인 방법론을 적용하였다. 지하주차장 전기 화재와 관련된 문헌조 사와 서비스디자인 사례를 분석하고, 페르소나 정의, 대피 시나리오에 따른 고객여정맵 분석을 실시하였 다. 이후 현장 대피 실험을 통해 사용자 관점의 핵심 이슈를 도출하였다. 조사 결과, 사용자 관점을 통해 대피에 필요한 소방시설과 시스템은 바닥 야광 피난유도선, 대피 동선 내 호흡용 수건, 스마트 대피안내 시스템 도입이 시급한 것으로 나타났다. 이용자의 적합 행동을 위해 정기적인 대피 훈련, 사용자 위치를 감안한 대피 안내 정보 및 알림 서비스 등이 필요한 것으로 도출되었다. 본 연구는 지하주 차장 전기자동차 화재 대피 안전성 제고를 위한 대안을 제시하며, 사용자 경험과 관점에서 접근했다는 점에 의미가 있다.

This study addresses the critical challenge of ensuring safe evacuation during electric vehicle fires in the complex environment of underground parking facilities. Applying service design methodology, it proposes user-centered improvement measures that consider both site specific environmental characteristics and user behavior patterns. The research methodology includes a comprehensive literature review, service design case analysis, and the application of core design tools such as persona development and customer journey mapping. Key issues were identified through on site evacuation experiments. The findings suggest the urgent need to enhance safety infrastructure, including floor-mounted luminous guide lines, escape breathing towels, and smart guidance systems. This study holds significant meaning as it presents alternatives for improving electric vehicle fire evacuation safety in underground parking garages from a user perspective.

In the fire there are fusion signs and damage by fire, and insulation aging and carbonization of the electric wiring in the ignition spot because of special characteristic of the appliance in the electricity fire. Because of the physical factor applied in the damage of fire, the decision of ignition spot by eye investigation is insufficient. In this paper, the cause of electricity fire is researched. The focus is on the operation state of operated MCCB(Molded Case Circuit Breaker) at the time of electricity fire. Through grasping the operation principle of MCCB and the experiment, the state of MCCB after fire suppression is discriminated. The distinction possibility on the exist of electricity fire is proposed.

최근 경제 성장과 국민 삶의 수준 향상으로 전력수요의 증가에 따라 전기재해도 증가하 고 있는 실정으로 공기는 일정량의 수증기를 포함할 수 있으며, 같은 기압 하에서 공기 중 에 존재할 수 있는 수증기의 최대치는 온도에 비례, 일정 온도의 공기가 그보다 차가운 표 면에 접촉하여 기온이 내려가면 상대습도가 증가하게 되며, 기온이 이슬점(노점)에 이르면 수증기는 물방울이 되어 벽면에 부착되는 현상인 결로현상(condensation phenomenon) 의 방치는 전기화재의 주요 원인으로 확대는 전기재해(안전사고)예방에 대한 관심이 증가 하고 있으므로 본 논문에서는 사고사례와 동종 사고를 예방하고 안전 시공과 유지관리 및 화재 원인조사, 전기안전 분야에서 도움이 되기를 기대한다.

Recently, as the demand for electricity increases due to economic growth and the improvement of people's standard of living, electric accidents are also increasing. Air can contain a certain amount of water vapor. The maximum amount of water vapor that can exist in the air under the same pressure is proportional to the temperature, and the relative humidity increases when the temperature drops due to the contact of the air at a certain temperature with the cooler surface. When the temperature reaches the dew point, the condensation phenomenon, in which the water vapor becomes a droplet and adheres to the wall, is the main cause of electric fires. As interest in preventing electric accidents (safety accidents) is increasing, this paper hopes to prevent accident cases and similar accidents and help with safety construction, maintenance, fire cause investigation, and electrical.

본 논문에서는 이미지 학습 및 분류에 가장 많이 활용되고 있는 CNN모델중의 하나인 VGG19알고리즘 을 이용하여 전기화재시 발생하는 용융 흔적을 분류를 방법을 제안하였다. 전기화재의 직접적인 유무를 감지하기 위한 가장 기본적인 근거는 전선의 녹는 정도와 형태에 따라 전기화재 현장에서 발생하는 전선의 용융흔적이다. 제 안된 방법은 VGG19 알고리즘을 활용하여 용융 흔적의 유무를 검출할 수 있도록 변형하여 사용하였으며, 학습에 필요한 데이터는 연구실에서 실제제적하여 사용하였다. 실험결과 제안된 알고리즘의 최종 검증 정확도는 96.31% 이고, 손실율은 0.1169로 확인되었다. 이와 같이 높은 정확도를 확보한 결과를 통하여 용융흔적 검출 알고리즘이 전기화재 유무 검증에 활용될 수 있는 가능성을 보였다.

In this paper, the VGG19 algorithm was used by applying the transfer learning for the classification of molten traces of electric fire arc-beads data which is one of the most used models in convolutional neural network(CNN) computer vision tasks. The most essential basis for detecting direct indications of electric fires is the melting traces of wires that occur at the site of an electric fire, depending on the severity and shape of the melting. The proposed VGG19 method was altered and used such that it could detect molten traces, and the molten trace data of the wires required for learning were created in the lab. The final validation accuracy result was 96.31% with validation loss of 0.1169. Through the result of securing such high accuracy, the possibility of using the melting trace detection algorithm to verify the presence or absence of an electric fire was shown.

This study aimed to identify fire safety measures for electric vehicle (EV) fire prevention in underground parking lots and prioritize them through an Importance-Performance Analysis (IPA). A third-round Delphi analysis with 18 experts identified 19 key factors. An IPA analysis with 52 practitioners identified “installation of battery thermal runaway (off-gas) detectors” and “establishment of a dedicated smoke exhaust mode” as the most urgent improvement tasks (Quadrant 2). The results of this study can serve as a foundation for establishing EV fire safety policies and implementing them in practice.

With the rapid increase in electric vehicle penetration, fires are increasing every year. So far, the results of electric vehicle fire investigation have reached the limit of direct evidence in the face of the disappearance of tangible evidence due to thermal runaway of the large lithium-ion battery pack, an essential component of electric vehicles. In this study, we identified commonalities in various electric vehicle fire investigation cases along with a clear understanding of electric vehicles. If direct evidence cannot be prevented from being destroyed due to thermal runaway of the lithium-ion battery, The indirect evidence will remain in the vehicle's BMU(Battery Management Unit) just before the fire. By utilizing indirect evidence, such as available battery voltage information, to reduce the scope of inspection in large lithium-ion battery packs and to conduct diverse and precise inspections on direct evidence within a limited range, we suggest an efficient direction for electric vehicle fire investigation in the future(Oman, H. 2002).