• 한국안전학회지
• /
• 제7권4호
• /
• pp.105-114
• /
• 1992

This paper presents an study on the knowledge based system for diagnosing the fire causes using the Fuzzy Possibility Measure( FPM ) about the electric-fire ignition. The Ignition values needed for causes diagnosis is computed as FPM for electric-fire ignition based on the internal scale technique that assigns numerically the characteristic difference of facts to the-tin-ear scale. For the convinience of inference, ignition sources are classified into seven types : short, ground fault, leakge of electricity, overcurrent, cord junction overheating, bad Insulation and spark. The system for causes diagnosis of electric-fire is composed of Knowledge Acquisition System, Inference Engine and Man-Machine Interface, The diagnosis system is wrritten in an artificial intelligence langusge “PROLOG” which uses depth-first search and backward chaining schemes in reasoning process.

• 한국응급구조학회지
• /
• 제7권1호
• /
• pp.199-212
• /
• 2003

Fire is a disaster of uncertainty, but since it is an artificial disaster essentially, this study is to emphasize that prevention and suppression of fire should be done more efficiently to develop the national love and trust of fire fighting. And it examines small neighboring living facilities which can be the typical dead ground of fire fighting based on researcher's experiences, intuition and related materials. The main course of the study defines the concept of fire fighting administration, dead ground and small neighboring living facilities. compares and analyzes fire fighting at small neighboring living facilities and the whole fire fighting cases and divides the causes of dead ground of fire fighting into preventive administration and suppressive administration sides. Those causes were resulted from discrepancies of political and social structures, but some of them can be improved depending on firemen's efforts. In addition, the means available for preventing the dead ground of fire fighting based on analyzed causes are suggested. Institutional approaches should be consulted with related agencies and legalized, but most managerial approaches can be introduced easily. Other means are approached for PR.

• 한국화재조사학회논문지
• /
• 제11권1호
• /
• pp.1-8
• /
• 2008

가스연료는 사업체, 가정 등에서 사용이 증가하고 있으며, 이로 인한 사고위험도도 증가추세 이며, 사고원인 또한 다양하게 나타나고 있다. 가스사고를 원인(취급부주의, 제품불량 등), 형태(화재, 폭발, 누출 등), 피해등급(1,2,3,4급), 사상자(사망, 중상, 경상)로 분류하여 설명하였다. 가스연료 중 가정에서 많이 사용되는 LP가스 시설은 가스용기, 압력조정기, 호스, 중간밸브, 연소기로 크게 구분할 수 있으며, 이 구성요소 중의 어떤 부분에서 취급부주의, 제품불량 등의 원인에 의해 화재 및 폭발 등이 발생할 수 있다. 따라서 사고 발생시 과거화재사례에 대한 연구 및 화재조사 시 착안사항을 참고하여 정확한 원인이 규명되어야 한다.

• International Journal of Safety
• /
• 제6권2호
• /
• pp.27-32
• /
• 2007

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.

• 한국화재소방학회논문지
• /
• 제24권4호
• /
• pp.92-97
• /
• 2010

부산 실내사격장 화재의 원인을 추정하고 화재안전대책을 강구하기 위해 화재 시뮬레이션과 사격장 화재의 사례조사를 수행하였다. 현장조사와 잔류화약 분말에 대한 사격시험도 실시하였다. 총구불꽃과 탄자 받이에서의 스파크의 흔적이 CCTV 녹화영상에 나타나지 않았고, 유탄의 충격에 잔류화약이 점화하지 않았다. 따라서 잠재적 점화원 중 담뱃불이 가장 유력한 점화원으로 추정되었다. 또, 사격실에서의 폭발원인은 폴리우레탄 흡음재와 흡음재에 축적된 잔류화약 분말의 격렬한 연소 때문으로 판단되었다. 한편, 실내 사격장의 안전대책으로 프로파일 폴리우레탄 흡음재의 사용금지, 잔류화약 제거와 철저한 관리, 탄자받이의 강구조물 제거 등이 필요하다.

• 한국화재소방학회:학술대회논문집
• /
• 한국화재소방학회 2008년도 춘계학술논문발표회 논문집
• /
• pp.80-84
• /
• 2008

This research has been carried out in order to provide countermeasure plans, fire prevention, improving institutional plans through analyzing accidental causes and investigating the situation of damage from the fire incident of the cold storage at Icheon. By the analysis of the incident, which is organized the process; for incidence, firstly a field investigation, next the overview of related laws, finally the analysis of problems and deducting suggestions, it was possible to find out the causes of casualties. We also suggested improving plans through finding out several problems such as safety management system and safety regulations, the permit on the completion of the cold storage and the completion examination of fire facilities as institutional problems and fireproof construction and the selection of finishing materials.

• 한국안전학회지
• /
• 제21권3호
• /
• pp.16-21
• /
• 2006

This paper presents a knowledge-based electrical fire cause diagnosis system using the fuzzy reasoning. The cause diagnosis of electrical fires may be approached either by studying electric facilities or by investigating cause using precision instruments at the fire site. However, cause diagnosis methods for electrical fires haven't been systematized yet. The system focused on database(DB) construction and cause diagnosis can diagnose the causes of electrical fires easily and efficiently. The cause diagnosis system for the electrical fire was implemented with entity-relational DB systems using Access 2000, one of DB development tools. Visual Basic is used as a DB building tool. The inference to confirm fire causes is conducted on the knowledge-based by combined approach of a case-based and a rule-based reasoning. A case-based cause diagnosis is designed to match the newly occurred fire case with the past fire cases stored in a DB by a kind of pattern recognition. The rule-based cause diagnosis includes intelligent objects having fuzzy attributes and rules, and is used for handling knowledge about cause reasoning. A rule-based using a fuzzy reasoning has been adopted. To infer the results from fire signs, a fuzzy operation of Yager sum was adopted. The reasoning is conducted on the rule-based reasoning that a rule-based DB system built with many rules derived from the existing diagnosis methods and the expertise in fire investigation. The cause diagnosis system proposes the causes obtained from the diagnosis process and showed possibility of electrical fire causes.

• 한국안전학회지
• /
• 제7권1호
• /
• pp.31-38
• /
• 1992

This paper presents a study on application of expert system technique for the diagnosis of fire-causes in plants. A need is recognized for new methods to diagnose exactly the causes of fires without the help of the human experts. To cope with the difficulty, the expert system techiuque is applied to this area. The expert system suggested in this paper is developed to infer the causes of fires(or, ignition source ) by using the information drawn from the circumstances in fire. For the convenience of inference, ignition sources we classified into eight types ; elecoic spark, adiabatic compression, welding spark, material of high temperature, impact and friction, spontaneous ignition, naked fire, and static electricity. The knowledge base is composed of the rule base and dynamic database, which contain the rules and facts obtained by the expenence in this area, respectively. Both depth-first search and backward chaining schemes are used in reasoning process. This expert system is written in an artificial intelligence language "PROLOG", and its availability is demonstrated through the case study.

• 대한안전경영과학회지
• /
• 제12권4호
• /
• pp.53-60
• /
• 2010

When a fire breaks out, it is difficult to find out the causes of the fire, because combustible things around fire scene are usually burnt away. Among many causes of fires are electronic wires, this thesis deal with the destroyed sheath of electronic wires caused by fire. It was studied with the use of measurement devices focusing on the distinctions of wires and conductors. This study especially emphasized the process of deterioration, burning pattern, and composition of electronic wire conductor. It also has a phenomenological approach to the distinctive cause of fire by some partial force. The fire prevention methods have been suggested through the analysing results of fire patterns. This study is expected to be a useful material for analyzing various electrical fires.

• 한국건축시공학회지
• /
• 제20권4호
• /
• pp.383-389
• /
• 2020

Accidents on construction sites involving fires do not occur as often as accidents involving falls from height or collapses. However, once a fire accident occurs, there is a high risk of a large number of casualties. Fire on construction sites is affected by working conditions and the types of activities the construction workers are engaged in at the sites. This study aims to identify activities and working conditions at construction sites that are vulnerable to fire, and analyse how they correlate with each other and how they affect the causes and consequences of fire accidents at construction sties. I analysed 40 fire accident reports and listed the situations vulnerable to fire at construction sites considering direct causes, activities, and working conditions. The most dangerous combination of fire hazards can be the heating devices used during rest/sleep in the office/cabin/storage during cold weather. The next most hazardous combination can be sparks arising from painting, waterproofing, insulation, plumbing, or welding/melting work in an underground or confined space.