전기화재 원인진단을 위한 지능형 프로그램 개발

권동명,홍성호,김두현 한국산업안전학회 2003 한국안전학회지 Vol.18 No.1

This paper presents as intelligent computer system, which can easily diagnose electrical fir causes, without the help of human experts of electrical fires diagnosis. For this system, a database is built with facts and rules driven from real electrical fires, and an intellectual database system which even a beginner can diagnose fire causes has been developed, named as an Electrical Fire Causes Diagnosis System : EFCDS. The database system has adopted, as an inference engine, a mixed reasoning approach which is constituted with the rule-based reasoning and the case-based reasoning. The system for a reasoning model was implemented using Delphi 3, one of program development tools, and paradox is used as a database building tool. To verify effectiveness and performance of this newly developed diagnosis system, several simulated fire examples were tested and the causes of fire examples were detected effectively by this system. Additional researches will be needed to decide the minimal significant level of the solution and the weighting level of important factors.

신공공관리론으로 바라본 보령화력발전소 화재 사고의 원인

이원주,박찬석 한국재난정보학회 2019 한국재난정보학회 논문집 Vol.15 No.2

연구목적: 본 연구는 시대적 행정 패러다임이 공공부문의 화재 발생에 어떤 영향을 주었는지 찾으려는 목적으로 수행되었다. 연구방법: 이를 위해 신공공관리론에 대한 이론적 고찰을 하고, 보령화력발전소 화재 사고 사례의 원인을 신공공관리론적 가치의 한계를 이용하여 분석하였다. 연구결과: 이론적 고찰 결과, 신공공관리론의 가치 3가지(관리적 책임성, 능률성, 전문성)와 그에 따른 연구준거를 도출할 수 있었다. 사고 사례의 원인 분석 결과, 공공부문에서 신자유주의 시장화에 기반을 둔 능률성이 과도하게 강조되어 관리적 책임성과 전문성 고양에는 미흡했던 것으로 나타났다. 결론: 결론적으로 신공공관리 론적 가치를 공공부문의 안전관리 부분에 과도하게 적용하는 한계가 있다는 것을 확인할 수 있었다. 이 연구결과는 소방행정이론의 학술적 발전에 기초자료로 사용될 것으로 기대된다. Purpose: The purpose of this study was to find out how the administrative paradigm of the times affected the public sector's fire. Method: For this purpose, we investigated the New Public Management (NPM). In addition, the reasons of fire accident of Boryeong thermal power plant were analyzed in the limited values of NMP. Result: In theoretical investigation, the 3 values (managerial accountability, efficiency, expertise) of NMP and evaluation criteria were drew out. In investigation on reasons of fire accident, the improvement of accountability and expertise was insufficient due to the emphasis of the efficiency based on the introduction to free market by neoliberalism in public sector. Conclusion: In conclusion, we confirmed that the values of NMP were limited to forcingly apply to the public sector. This study is expected to contribute basic research references to fire administration theory.

Electrical Fire Cause Diagnosis System Using a Knowledge Base

( Jong Ho Lee ),( Doo Hyun Kim ),( Sung Chul Kim ) 한국안전학회(구-한국산업안전학회) 2007 International Journal of Safety Vol.6 No.2

For last several decades with the achievement of fast economic development, the electrical fires occupies over 30 percent of total fire incidents almost every year in Korea and not decreased in spite of much times and efforts. Electrical fire cause diagnostics are to confirm a cause for the fire by examination of fire scene. Cause diagnosis methods haven`t been systematized yet, because of limits for available information, investigator`s biased knowledge, etc. Therefore, in order to assist the investigators and to find out the exact causes of electrical fires, required is research for an electrical fire cause diagnosis system using DB, computer programming and some mathematical tools. The electrical fire cause diagnosis system has two functions of DB and electrical fire cause diagnosis. The cause diagnosis is conducted by a case-based reasoning on a case base and rule-based reasoning on a rule base. For the diagnosis with high reliability, a mixed reasoning approach of a case-based reasoning and fuzzy rule-based reasoning has been adopted. The electrical fire cause diagnosis system proposes the electrical fire causes inferred from the diagnosis processes, and possibility of the causes as well.

Electrical Fire Cause Diagnosis System Using a Knowledge Base

Lee, Jong-Ho,Kim, Doo-Hyun,Kim, Sung-Chul The Korean Society of Safety 2007 International Journal of Safety Vol.6 No.2

For last several decades with the achievement of fast economic development, the electrical fires occupies over 30 percent of total fire incidents almost every year in Korea and not decreased in spite of much times and efforts. Electrical fire cause diagnostics are to confirm a cause for the fire by examination of fire scene. Cause diagnosis methods haven't been systematized yet, because of limits for available information, investigator's biased knowledge, etc. Therefore, in order to assist the investigators and to find out the exact causes of electrical fires, required is research for an electrical fire cause diagnosis system using DB, computer programming and some mathematical tools. The electrical fire cause diagnosis system has two functions of DB and electrical fire cause diagnosis. The cause diagnosis is conducted by a case-based reasoning on a case base and rule-based reasoning on a rule base. For the diagnosis with high reliability, a mixed reasoning approach of a case-based reasoning and fuzzy rule-based reasoning has been adopted. The electrical fire cause diagnosis system proposes the electrical fire causes inferred from the diagnosis processes, and possibility of the causes as well.

Nighttime Fire Smoke Detection System Based on Machine Vision

Chao-Ching Ho,Ming-Chen Chen 한국정밀공학회 2012 International Journal of Precision Engineering and Vol. No.

A real-time machine vision–based nighttime fire smoke detection method that can be incorporated into a surveillance system for early fire alert is proposed in this paper. Nowadays, video surveillance–based early fire smoke detection is crucial to the prevention of large fires and the protection of life and goods. However, many of the known video smoke detection methods require that minimum illumination be provided for the cameras to recognize the existence of fire smoke in a scene. To overcome the nighttime limitations of video smoke detection methods, a laser light is projected into the monitored field of view, and the returning projected light section image is analyzed in order to fire smoke. If the fire smoke appears within the monitoring zone created from the diffusing or scattering projected light path, the camera sensor receives a corresponding signal. The successive processing steps of proposed real-time algorithm are using the spectral, diffusing, and scattering characteristics of the fire smoke regions in the image sequences to register the possible smoke position in a video. Characterization of smoke is carried out by calculating accumulative deviation from the extracted feature vectors, and a classification method using a fuzzy reasoning system is applied to assign a score to the potential fire smoke candidate. Experimental results in a variety of nighttime conditions demonstrate that the proposed fire smoke detection method can successfully and reliably detect fire smoke.

플랜트 설비의 케이블 화재 시 다중 감지기를 이용한 실시간 경보기법에 관한 연구

이홍철(Hong-cheol Lee),조은비(Eun-bi Cho),노고섭(Go-seop Roh),황인주(In-ju Hwang) 융복합지식학회 2018 융복합지식학회논문지 Vol.6 No.2

본 논문에서는 제한된 공간에서 플랜트 설비의 케이블에 화재가 발생할 경우에 변화되는 온도, 농도, 이온 데이터를 획득하여 화재정보를 실시간으로 판별하는 기법을 평가하였다. 이를 위하여 규칙 및 사례 기반 알고리즘을 설계하고, 실험실 화재 데이터를 이용하여 시간에 따른 유사도 패턴을 분석하였다. 기본적인 개념은 열, 연기, 이온 등 다중 감지기를 이용하여 신뢰성을 높이고, 데이터 융합을 통한 화재 판별 시나리오를 전개하고 유용한 정보를 생성하는 방법이다. 본 연구를 통하여 제한적인 조건에서 유형별 화재판별기준을 제시하고, 적용기법 및 시나리오의 신뢰성을 평가하였다. 기존 감지방식으로는 화재정보의 생성이 불가능한 초기 단계에서 화재감지 정보를 제공할 수 있음을 파악하였다. 또한 정형화된 화재신호 데이터 및 사례기반 추론알고리즘을 적용하여 최대 38%의 화재감지 반응시간이 감소하는 것으로 평가되었다. This paper deals with a technique to detect fire information in real time by acquiring temperature, concentration, and ion data when a cable in a plant facility is exposed to fire in a confined space. To do this, we designed rules and case - based algorithms and analyzed similarity patterns over time using laboratory fire data. The basic concept is to improve reliability by using multiple sensors such as heat, smoke, and ions, to develop fire detection scenarios through data fusion, and to generate useful information. Through this study, it was possible to propose the fire discrimination criteria for each type under limited conditions, and to secure the reliability of application techniques and scenarios. In the conventional detection method, fire detection information can be provided at an early stage when fire information can not be generated. In addition, it was evaluated that up to 38% of fire detection response time is reduced by applying formalized fire signal data and case based reasoning algorithm.

제한공간에서 케이블 화재의 다중 감지특성의 정형화에 관한 연구

이홍철(Hong-cheol Lee),조은비(Eun-bi Cho),노고섭(Go-seop Roh),황인주(In-Ju Hwang) 융복합지식학회 2018 융복합지식학회논문지 Vol.6 No.1

제한된 공간에 밀집한 설비의 경우에 화재에 취약한 부분은 케이블이나 전기적인 접촉을 가지는 스위치류 등이다. 본 연구는 제한된 공간에서 케이블에 화재가 발생하는 공간에서 온도, 농도, 이온 변화 특성을 고찰하여 화재 판별과 경보에 활용 가능성을 평가하였다. 방법론은 열, 연기, 이온 등 화재 감지를 위한 다종의 센서로부터 실시간 획득되는 데이터에 대한 실시간 유사도 평가기법을 도입하였다. 제한공간에서 케이블에 의한 급속화재와 훈소화재의 경우에 실시간 유사도 패턴을 분석하여 조기에 화재경보를 판단할 수 있음을 보였다. 본 연구의 경우에 실제 화재 시점보다 30~40% 이른 시간에 화재경보 여부를 판단할 수 있었다. In the confined space with dense facilities, the vulnerable parts to fire are cables or switches that make electrical contact. This study reviewed the characteristics of temperature, concentration, ion concentration changes in a confined space where cable fire occurred to evaluate the applicability to fire decision and alarm. The methodology introduced real-time similarity evaluation on data from multi-sensors for fire detection such as heat, smoke, and ions. It was shown that fire alarm can be decided early by analyzing real-time similarity pattern of fast fire and smouldering fire by cable in confined space. In this study, fire alarm was judged 30%~40% earlier than actual fire point.

Electrical Fire Cause Diagnosis System based on Fuzzy Inference

Lee, Jong-Ho,Kim, Doo-Hyun The Korean Society of Safety 2005 International Journal of Safety Vol.4 No.2

This paper aims at the development of an knowledge base for an electrical fire cause diagnosis system using the entity relation database. The relation database which provides a very simple but powerful way of representing data is widely used. The system focused on database construction and cause diagnosis can diagnose the causes of electrical fires easily and efficiently. In order to store and access to the information concerned with electrical fires, the key index items which identify electrical fires uniquely are derived out. The knowledge base consists of a case base which contains information from the past fires and a rule base with rules from expertise. To implement the knowledge base, Access 2000, one of DB development tools under windows environment and Visual Basic 6.0 are used as a DB building tool. For the reasoning technique, a mixed reasoning approach of a case based inference and a rule based inference has been adopted. Knowledge-based reasoning could present the cause of a newly occurred fire to be diagnosed by searching the knowledge base for reasonable matching. The knowledge-based database has not only searching functions with multiple attributes by using the collected various information(such as fire evidence, structure, and weather of a fire scene), but also more improved diagnosis functions which can be easily wed for the electrical fire cause diagnosis system.

Beliefs of University Employees Leaving During a Fire Alarm: A Theory-based Belief Elicitation

Owens Christopher,Le Aurora B.,Smith Todd D.,Middlestadt Susan E. 한국산업안전보건공단 산업안전보건연구원 2023 Safety and health at work Vol.14 No.2

Background: Despite workplaces having policies on fire evacuation, many employees still fail to evacuate when there is a fire alarm. The Reasoned Action Approach is designed to reveal the beliefs underlying people's behavioral decisions and thus suggests causal determinants to be addressed with interventions designed to facilitate behavior. This study is a uses a Reasoned Action Approach salient belief elicitation to identify university employees' perceived advantages/disadvantages, approvers/disapprovers, and facilitators/barriers toward them leaving the office building immediately the next time they hear a fire alarm at work. Methods: Employees at a large public United States Midwestern university completed an online cross-sectional survey. A descriptive analysis of the demographic and background variables was completed, and a six-step inductive content analysis of the open-ended responses was conducted to identify beliefs about leaving during a fire alarm. Results: Regarding consequence, participants perceived that immediately leaving during a fire alarm at work had more disadvantages than advantages, such as low risk perception. Regarding referents, supervisors and coworkers were significant approvers with intention to leave immediately. None of the perceived advantages were significant with intention. Participants listed access and risk perception as significant circumstances with the intention to evacuate immediately. Conclusion: Norms and risk perceptions are key determinants that may influence employees to evacuate immediately during a fire alarm at work. Normative-based and attitude-based interventions may prove effective in increasing the fire safety practices of employees.

퍼지추론을 이용한 지식기반 전기화재 원인진단시스템

이종호 ( Jong Ho Lee ),김두현 ( Doo Hyun Kim ) 한국안전학회 2006 한국안전학회지 Vol.21 No.3