선박 추진용 2행정 저속엔진의 고장모드 데이터 개발 및 LSTM 알고리즘을 활용한 특성인자 신뢰성 검증연구
The Study of Failure Mode Data Development and Feature Parameter’s Reliability Verification Using LSTM Algorithm for 2-Stroke Low Speed Engine for Ship’s Propulsion
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In the 4th industrial revolution, changes in the technological paradigm have had a direct impact on the maintenance system of ships. The 2-stroke low speed engine system integrates with the core equipment required for propulsive power. The Condition Based Management (CBM) is defined as a technology that predictive maintenance methods in existing calender-based or running time based maintenance systems by monitoring the condition of machinery and diagnosis/prognosis failures. In this study, we have established a framework for CBM technology development on our own, and are engaged in engineering-based failure analysis, data development and management, data feature analysis and pre-processing, and verified the reliability of failure mode DB using LSTM algorithms. We developed various simulated failure mode scenarios for 2-stroke low speed engine and researched to produce data on onshore basis test_beds. The analysis and pre-processing of normal and abnormal status data acquired through failure mode simulation experiment used various Exploratory Data Analysis (EDA) techniques to feature extract not only data on the performance and efficiency of 2-stroke low speed engine but also key feature data using multivariate statistical analysis. In addition, by developing an LSTM classification algorithm, we tried to verify the reliability of various failure mode data with time-series characteristics.
Abstract
In the 4th industrial revolution, changes in the technological paradigm have had a direct impact on the maintenance system of ships. The 2-stroke low speed engine system integrates with the core equipment required for propulsive power. The Condition Based Management (CBM) is defined as a technology that predictive maintenance methods in existing calender-based or running time based maintenance systems by monitoring the condition of machinery and diagnosis/prognosis failures. In this study, we have established a framework for CBM technology development on our own, and are engaged in engineering-based failure analysis, data development and management, data feature analysis and pre-processing, and verified the reliability of failure mode DB using LSTM algorithms. We developed various simulated failure mode scenarios for 2-stroke low speed engine and researched to produce data on onshore basis test_beds. The analysis and pre-processing of normal and abnormal status data acquired through failure mode simulation experiment used various Exploratory Data Analysis (EDA) techniques to feature extract not only data on the performance and efficiency of 2-stroke low speed engine but also key feature data using multivariate statistical analysis. In addition, by developing an LSTM classification algorithm, we tried to verify the reliability of various failure mode data with time-series characteristics.
참고문헌 (12)
- 배준형, "고장 검출 필터를 사용한 항공기 터보팬엔진 시스템의 고장 검출", 전기전자학회논문지, 25(2), pp.330~336 (2021), 한국전기전자학회
- Benkamin, L., "A survey on long short-term memory networks for time series prediction", 14th CIRP, 99, pp.650~655 (2021)
- 변성일, "고장수목분석(FTA) 기법을 이용한 무인잠수정 건전성 진단", 제어.로봇.시스템학회 논문지, 28(5), pp.398~405 (2022), 제어·로봇·시스템학회[DOI]
- 채선규, "fastICA 기반 발전기 고장 진단 및 예측", 신뢰성 응용연구, 21(4), pp.341~351 (2021), 한국신뢰성학회[DOI]
- 조현준, "무인 수상선의 수중 추진기 고장 진단 연구를 위한 고장 특성 인자 선정 및 실험", 제어.로봇.시스템학회 논문지, 28(6), pp.542~550 (2022), 제어·로봇·시스템학회[DOI]
- 황세윤, "통계적 기계학습법을 적용한 플랜트 공정 장비의 시계열 데이터 분석및 고장 상태 진단", 한국CDE학회 논문집, 23(3), pp.193~201 (2018), 한국CDE학회[DOI]
- 김성현, "소음기반 엔진고장 진단 기계학습 기법 연구", 한국해군과학기술학회지, 5(1), pp.16~19 (2022), 한국해군과학기술학회[DOI]
- 김정영, "선박 기관시스템 보조기기의 상태기반 고장진단", 예측을 위한 고장 모사 데이터베이스 구축, 2022, pp.59(4), 200~206[DOI]
- 김승일, "진동 데이터의 시간영역 특징 추출에 기반한 고장 분류 모델", 한국전산구조공학회논문집, 34(1), pp.25~33 (2021), 한국전산구조공학회[DOI]
- 이정형, "시계열 특징을 갖는 선박용 공기 압축기 전류 데이터의 이상 탐지 알고리즘 적용 실험", 해양환경안전학회지, 27(1), pp.127~134 (2021), 해양환경안전학회[DOI]
- Ugo Campora, "Marine gas turbine monitoring and diagnostics by simulation and pattern recognition", International Journal of Naval Architecture and Ocean Engineering, 10(5), pp.617~628 (2018), 대한조선학회
- Recurrent neural networks for multivariate time series with missing values, "Zhengping, C.", ~, pp.Scientific Reports, 8:6085 (2018)