[논문]적응형 뉴로-퍼지(ANFIS)를 이용한 도시철도 시스템 위험도 평가 연구

탁길훈; 구정서

doi:10.14346/jkosos.2022.37.1.78

적응형 뉴로-퍼지(ANFIS)를 이용한 도시철도 시스템 위험도 평가 연구
A Study on the Risk Assessment for Urban Railway Systems Using an Adaptive Neuro-Fuzzy Inference System(ANFIS) 원문보기

한국안전학회지 = Journal of the Korean Society of Safety, v.37 no.1, 2022년, pp.78 - 87

탁길훈 (서울과학기술대학교 철도안전공학과) , 구정서 (서울과학기술대학교 철도안전공학과)

Abstract ▼ AI-Helper

In the risk assessment of urban railway systems, a hazard log is created by identifying hazards from accident and failure data. Then, based on a risk matrix, evaluators analyze the frequency and severity of the occurrence of the hazards, conduct the risk assessment, and then establish safety measures for the risk factors prior to risk control. However, because subjective judgments based on the evaluators' experiences affect the risk assessment results, a more objective and automated risk assessment system must be established. In this study, we propose a risk assessment model in which an adaptive neuro-fuzzy inference system (ANFIS), which is combined in artificial neural networks (ANN) and fuzzy inference system (FIS), is applied to the risk assessment of urban railway systems. The newly proposed model is more objective and automated, alleviating the limitations of risk assessments that use a risk matrix. In addition, the reliability of the model was verified by comparing the risk assessment results and risk control priorities between the newly proposed ANFIS-based risk assessment model and the risk assessment using a risk matrix. Results of the comparison indicate that a high level of accuracy was demonstrated in the risk assessment results of the proposed model, and uncertainty and subjectivity were mitigated in the risk control priority.

주제어

표/그림 (29)

그림 Fig. 1. Risk acceptance categories.
그림 Fig. 2. Procedure of risk assessment.
그림 Fig. 3. Sugeno fuzzy inference system.
표 Table 1. Definition of risk assessment terms
그림 Fig. 4. Architecture of ANFIS.
표 Table 2. Classification of input fuzzy variables
표 Table 3. Seoul metro line 1 ~ Line 8 systems
그림 Fig. 5. Input variable(F, Frequency).
그림 Fig. 6. Input variable(S, Severity).
그림 Fig. 7. ANFIS Model structure.
표 Table 4. Training datas and testing datas
표 Table 5. RMSE of Membership Function
그림 Fig. 8. Surface viewer.
그림 Fig. 9. Rule viewer.
그림 Fig. 10. Procedure of risk assessment(Seoul metro).
표 Table 6. Seoul Metro systems and subsystems
표 Table 7. Classification of Seoul Metro's Accidents
표 Table 8. Hazard events and hazards identified by accident type
그림 Fig. 11. Quantitative evaluation.
그림 Fig. 12. Risk matrix of seoul metro.
표 Table 9. Action criteria by risk level
표 Table 10. Frequency and severity of accidents by accident type
그림 Fig. 13. Risk assessment based on risk matrix.
표 Table 11. Risk level of accident type
표 Table 12. Risk priority number(Risk > Frequency > Severity)
그림 Fig. 14. Risk assessment based on ANFIS.
그림 Fig. 15. R² of outputs.
표 Table 13. Risk priority number(Risk > Severity > Frequency)
표 Table 14. Risk priority number(ANFIS Output)

참고문헌 (11)

"Railroad Safety Act", Act No.16395, Ministry of Land, Infrastructure and Transport(ROK), 2019.
"Guide Line of Risk Assessment for Railway", Ministry of Land, Infrastructure and Transport(ROK), 2018.
IEC 62278, "Railway Applications-The Specifications and Demonstration of Reliability, Availability, Maintainability and Safety(RAMS)", CENELEC, 2017.
H. K. Yang and J. W. Lee, "A Study on SIL Allocation for Signaling Function with Fuzzy Risk Graph", Journal of the Korean Society for Railway, Vol. 19, No. 2, pp. 145-158, 2016.
J. B. Wang, K. J. Choi and C. W. Park, "Establishment of Risk Analysis and Assessment System for Railway Accidents and Hazards", Ministry of Land, Transport and Maritime Affairs(ROK), 2011.
J. S. Roger Jang, "Neuro-Fuzzy and Soft Computing", Prentice Hall, 1997.
K. W. Kim, J. U. Kim and H. H. Yoo, "Estimation of Distribution Demand for an Urban Rail Transit by Using the Adaptive Neuro-Fuzzy Inference System", Journal of the Korean Society of Civil Engineers, Vol. 27(2D), pp. 171-178, 2007.
S. Boran and S. H. Gokler, "A Novel FMEA Model Using Hybrid ANFIS-Taguchi Method", Arabian Journal for Science and Engineering 45, pp. 2131-214, 2020.
Report of Risk Assessment, Seoul Metro, 2019.
Y. S. Kim, "The Study of Risk Matrix Development for Urban Metro EMU", Journal of the KOSOS, Vol. 26, No. 6, pp. 111-117, 2011.
MIL-STD-882d, "Standard Practice for System Safety", Department of Defence(USA), 2000.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증