빅데이터 분석을 통해 살펴본 비화재출동 경감방안에 관한 연구
- Author(s)
- 백진우
- Issued Date
- 2020
- Abstract
- 본 연구 논문은 빅데이터 분석을 위한 원 데이터(Raw Data) 자료를 수집하고, 4차 산업혁명기술 빅데이터 분석 시스템을 활용한 소방활동의 융합에 관한 연구 논문이다.
소방활동현장은 40도를 넘어서는 기후변화와 도시의 과밀화 및 건물의 고층화 등으로 갈수록 악화일로에 있다. 고드름이나 벌집 제거와 같은 생활안전출동으로 인해 긴박한 화재나 구조 출동에 골든타임을 놓치는 안타까운 사연을 접하면서, 한정된 소방력으로 증가하는 소방수요를 감당해야 하는 현 상황에서 ‘어떻게 하면 119 본연의 업무인 화재출동과 인명구조 활동을 위한 소방력을 확보할 수 있을까?’ 하는 절심함이 본 연구를 시작하게 된 배경이 되었다.
현장활동 소방대원의 의견을 청취한 결과 오인 출동에 의한 소방력 손실을 줄이는 것만으로도 출동 소방력을 확보할 수 있음을 확인하고, 비화재 출동건수를 줄이기 위해 계절별·기간별·지역별 비화재 출동건수를 경감할 수 있는 방안에 대한 선행 연구 및 고찰을 통해 본 연구를 진행하였다. 119구조대 및 119안전센터 출동 소방대원을 대상으로 계절별 구조 출동 및 생활안전민원 출동에 대한 의견 청취 결과, 그 어떤 계절보다 고온 다습한 여름철에 인명 구조 출동 중 승강기 갇힘 인명구조 출동과 119안전센터의 생활안전민원 출동 중 소방시설 오작동에 대한 출동이 빈번함을 할 수 있었다.
우리나라는 사계절이 뚜렷하고 주기적으로 변동하는 계절적인 영향으로 인하여 여름은 고온 다습, 겨울은 저온 저습한 특징을 가지고 있다 송동우·김기성·이수경, 공공데이터를 이용한 습도 및 온도와 실화 발생 간의 관계분석, 한국화재소방학회, vol. 28, No. 2, 2014, p. 81
. 고온 다습한 7월에 비화재 119출동 건수가 많다는 것은 비화재 119출동건수와 기상 인자간 영향이 있음을 짐작할 수 있다. 기상과 화재출동에 관한 선행연구 조사결과 비화재 화재출동과 기상과의 상관관계에 관한 연구는 많지 않은 것으로 조사되었다.
하인리이히(Herbert William Heinrich)는 1931년 “산업 재해 예방 과학적 접근”이란 책에서 한번(1번)의 대형사고가 발생하기 전에는 그와 유사한 작은 사고가 몇 번(29번) 일어나고 그 작은 사고가 일어나기 전에 반드시 사소한 징후(300번)가 일어난다는 ‘1 : 29 : 300’의 의미 있는 법칙을 통계학적으로 풀어냈다. 즉, 「연속된 것에는 반드시 패턴이 존재한다」라는 것이다. 119출동에 있어서도 기간별·기상별·지역별 반복되는 119구조대 구조출동 및 119안전센터 생활안전대의 생활민원 출동 패턴이 존재할 것으로 판단된다.
이에 본 연구는 ‘온도·습도 기상인자와 119출동 사이에 어떤 상관관계가 있을 것이다’라는 가정 하에 최근 5년간 광주광역시 119구조대의 승강기 갇힘 구조출동 및 119안전센터의 소방시설 오작동(비화재보) 관련 119생활안전대의 출동 데이터를 원자료(Raw Data)로 하여 빅데이터 분석시스템을 통해 상관관계를 분석해 보고, 그 결과를 바탕으로 온도·습도 기상인자와 119출동과의 상관관계를 규명 및 비화재보 119 출동 빈도수 경감 방안을 제언하고자 한다.|ABSTRACT
A Study on the Reduction for Non-fire operation through
Big Data Analysis
Baek Jin-Woo
Advisor : Prof. Kim Hak-dong, Ph.D.
Department of Public Administration
Graduate School of Chosun University
This research paper collects raw data data for big data analysis
and is a research paper on the fusion of firefighting activities using
the fourth industrial revolution technology big data analysis system.
Fire fighting sites are getting worse due to climate change
exceeding 40 degrees Celsius, overcrowding of cities and high-rise
buildings. With the unfortunate story of losing golden time to urgent
fires or rescue operations due to safe-housing activities such as
icicles and beehives, the urgency of 'how to secure fire power for
119's own work and life-saving activities' is behind the study.
After listening to the opinions of firemen in field activities, we
confirmed that the firepower can be secured by reducing the loss
of firepower caused by misfire operation, and conducted this study
through advance research and consideration on ways to mitigate
the number of non-fires dispatched by season, period, and region
to reduce the number of non-fires. As a result of listening to the
opinions of firefighters who were dispatched to 119 rescue teams
and 119 safety centers on seasonal relief and safe-haven
mobilization, the elevator was trapped during the rescue operation
during the hot and humid summer months, and the 119 safety
center was dispatched to the living safety center, which frequently
showed signs of
Our country has features that are hot and humid in summer and
cold in winter due to seasonal effects that are clear and fluctuate
periodically in four seasons. Song Dong-woo, Kim Ki-sung, Lee
Soo-kyung, and Analysis of the Relationship between Humidity and
Temperature and Misfire Using Public Data, Vol. 28, No. 2, 2014,
p. 81
It can be inferred that the high number of non-fire 119 departures
in July, when it is hot and humid, has an effect between the
number of non-fire 119 departures and weather factors. The results
of the preceding study on weather and fire operation showed that
not many studies have been conducted on the correlation between
non-fire fire start and weather.
In his book "The Scientific Approach to Industrial Disaster
Prevention" in 1931, Heinrich unraveled the meaningful statistical
principle of "1: 29: 300" that before a major accident occurs,
similar small accidents occur several times (29 times) and must
occur before a small accident occurs. In other words, "there must
be a pattern in a continuous one." In the 119 operation, the 119
rescue team's rescue operation, which is repeated by period,
weather, and region, and the 119 safety center's life support
dispatch pattern are expected to exist
Based on the assumption that there will be some correlation
between temperature and humidity weather factors and 119
start-ups, this study analyzed the dispatch data of 119 lifeguards
related to elevator entrapment and malfunction of 119 safety
centers in Gwangju over the past five years through raw data, and
identified the correlation with weather and humidity based on the
results of the analysis system.
- Alternative Title
- A Study on the Reduction for Non-fire operation through Big Data Analysis
- Alternative Author(s)
- Baek Jin Woo
- Department
- 일반대학원 소방안전방재학과
- Advisor
- 강인호
- Awarded Date
- 2020-02
- Table Of Contents
- 목 차
제1장 서론 ··········································································································1
제1절 연구의 배경 및 필요성 ·······························································1
제2절 연구의 목적 ·························································································3
제3절 연구의 범위 및 연구방법 ·························································3
1. 연구의 범위 ································································································3
2. 연구의 방법 ································································································3
가.「혜안」빅데이터 분석 시스템을 통한 시각화 ····································5
나. Visual Analytics SAS 7.4 기반 빅데이터 분석 ····················5
제2장 이론적 고찰·························································································6
제1절 빅데이터의 개념과 활용······························································6
1. 빅데이터의 개념과 진화 ·····································································6
가. 빅데이터의 개념 ······················································································6
나. 빅데이터의 진화 ······················································································7
2. 빅데이터의 활용 3대 요소 및 요소기술 ··································7
가. 빅데이터의 활용요소 및 활용 단계 ···············································7
(1) Gartner의 빅데이터 활용 3대 요소 ··························································7
(2) 빅데이터 지식 활용 단계 ···········································································9
나. 빅데이터의 요소 기술 ···········································································9
제2절 빅데이터 분석 시스템 ································································13
1. 빅데이터 분석시스템「혜안」························································13
2. 빅데이터 기반 소방정책개발 및 평가시스템 ······················14
가. 빅데이터 기반 소방정책개발 및 평가시스템 개요 ················14
(1) 소방 정책 개발 평가 분석 시스템 ··························································15
(2) Visual Analytics SAS 7.4 기반 빅데이터 분석시스템 구성 및 분석 기능 16
제3절 승강기(엘리베이터) 및 소방시설 구조 ·························19
1. 승강기의 종류 및 구조 ······································································19
가. 승강기의 종류 ·························································································19
나. 승강기의 구조 ·························································································21
(1) 전기식 엘리베이터 구조 ···········································································21
(2) 유압식 엘리베이터 구조 ···········································································22
2. 승강기(엘리베이터) 설치대상 ························································23
제4절 오작동(비화재보) 소방시설 ···················································24
1. 감지기 ···········································································································24
가. 감지기의 정의 ·························································································24
나. 감지기의 종류 ·························································································24
다. 감지기 설치대상 ····················································································26
라. 감지기 설치장소 ····················································································27
(1) 부착 높이별 감지기의 종류 ·····································································27
(2) 연기감지기 설치 장소 ···············································································28
2. 자동화재속보기 ·······················································································28
가. 자동화재 속보설비 ···············································································28
나. 자동화재 속보설비 제품성능 인정기준 ······································29
다. 자동화재 속보설비 설치대상 ···························································29
제3장 광주광역시 119출동 분석··················································31
제1절 119구조대의 승강기 갇힘 구조 출동 분석················· 31
1. 구조활동정보시스템 원자료(RAW DATA) 분석 ············ 31
2. 광주광역시 연도별 구조활동 실적 분석 ································33
3. 광주광역시 최근 5년간 사고유형별 구조활동 실적 ········34
4. 119구조대 승강기 갇힘 연도별 구조활동 실적 ················· 35
5. 119구조대 승강기 갇힘 월별 구조활동 실적 ······················37
제2절 119생활안전대 119출동 분석·················································39
1. 119생활안전대 생활안전 활동 수행 ··········································39
2. 119생활안전대 생활안전출동 유형별 수행실적 ·················39
3. 119생활안전대 소방시설 오작동 월별 출동 실적 ············ 40
제4장 광주광역시 119출동 빅데이터 분석 ·····················42
제1절「혜안」과 SAS 7.4를 통한 승강기 갇힘 사고 빅데이터 분석 ·· 42
1. 지역별 승강기 갇힘 사고 119구조대 구조출동 분석 ····· 42
가. 월별 승강기 갇힘 사고 출동 건수 ···············································43
나. 기상별 승강기 갇힘 사고 출동 빈도 ···········································45
(1) 온도와 승강기 갇힘 사고 119구조대 구조 출동 상관관계 ··················45
(2) 습도와 승강기 갇힘 사고 119구조대 구조 출동 상관관계 ··················46
제2절「혜안」과 SAS 7.4를 통한 소방시설 오작동 빅데이터 분석 ····48
1. 기간별, 기상별 소방시설오작동 출동 분석 ··························48
가. 연도별 월별 추이분석 ········································································48
나. 온도․습도 기상인자와 소방시설 오작동 출동 빈도의 상관관계 ············ 50
다. 온도․습도 기상인자와 소방시설별 오작동 출동 빈도의 상관관계 ·········52
(1) 자동화재속보설비 ······················································································52
(2) 감지기 ·········································································································53
2. 지역별 소방시설 오작동 출동건수에 따른 비교 ···············54
가. 소방시설 오작동 각 소방서별 출동건수 및 출동률 분석 · 54
나. 소방시설 오작동 구별 동별 발생빈도(광산구) ·······················55
다. 소방시설 오작동 구별 동별 발생빈도(북구) ····························57
제5장 개선방안 ······························································································60
제1절 119구조대 승강기 갇힘 구조출동 경감을 위한 개선방안 ········60
1. 계절 특성을 고려한 맞춤형 관리 대책 강화 ·······················60
2. 빅데이터 분석을 통한 고장발생 특징 분석 정보 제공 · 61
3. 승강기(엘리베이터) 유지관리업체 출동시간 단축 ··········· 62
제2절 소방시설 오작동 119생활안전대 출동경감을 위한 개선방안 63
1. 계절 특성을 고려한 맞춤형 소방시설 관계인 예방 교육 강화 ···········63
2. 감지기의 형식승인 및 제품검사의 기술 기준 강화 ········ 64
3. 감지기의 내용연수 제정 ···································································66
4. 동일 대상 비화재보 출동 대상물 이력 관리 ·······················66
5. 정밀한 빅데이터 분석을 위한 구조활동일지 분류체계 상세화 ···········67
제6장 결론 ··········································································································70
참고문헌 ·············································································································73
- Degree
- Master
- Publisher
- 조선대학교 대학원
- Citation
- 백진우. (2020). 빅데이터 분석을 통해 살펴본 비화재출동 경감방안에 관한 연구.
- Type
- Dissertation
- URI
- https://oak.chosun.ac.kr/handle/2020.oak/14150
http://chosun.dcollection.net/common/orgView/200000278426
-
Appears in Collections:
- General Graduate School > 3. Theses(Master)
- Authorize & License
-
- AuthorizeOpen
- Embargo2020-02-26
- Files in This Item:
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.