DOI QR코드

DOI QR Code

Forecasting Algorithm for Vessel Engine Failure

선박 엔진의 고장 예측 알고리즘

  • 박준현 (동아대학교 컴퓨터공학과) ;
  • 장민국 (한국해양대 기관시스템공학과 유수에스엠) ;
  • 이강희 (동아대학교 컴퓨터공학과) ;
  • 오은경 (동아대학교 컴퓨터공학과) ;
  • 허성우 (동아대학교 컴퓨터공학과)
  • Received : 2016.10.05
  • Accepted : 2016.11.09
  • Published : 2016.11.30

Abstract

As the size of a vessel is getting bigger, the speed of that is getting higher, and the most controling mechanism is automated, the volume of marine cargo and the number of vessels held by a company increases continually. So, the role of ship management industry becomes more important. A sudden failure of major equipments of a vessel causes a great economical damage to the vessel management company, hence an algorithm which can predict and prevent failures in advance is required. Most of existing algorithms for the requirement have a limit in predicting failures in advance because they usually use simple method like setting the threshold values of sensors or examining the correlation between sensors. In this paper, we present an effective algorithm to detect engine failure, which reduces a large amount of sensor data into smaller set of useful data by analysing correlation among them and which detects defect data by regression analysis. Results obtained by simulation using the real data generated by a vessel, which belongs to H marine company, and the failure report, our proposed algorithm is proved to be effective to predict engine failure in advance.

선박의 대형화, 고속화, 자동화로 해상물동량과 선박보유량이 지속해서 증가하고 있으며 이로 인한 선박 관리 산업의 역할이 중요해지고 있다. 선박 운항 중 갑작스러운 주요설비 고장은 선박관리업계에 큰 경제적 손실을 야기시키며, 따라서 사전에 고장을 예측하고 예방할 수 있는 알고리즘이 요구되고 있다. 이런 요구를 위한 기존의 알고리즘은 일반적으로 센서들의 임계치를 설정하거나 센서 간의 상관관계를 검토하여 고장을 예측하는 단순한 방법들을 사용하기 때문에 고장 사전 예측에 한계가 있다. 본 논문에서는 실시간으로 들어오는 빅 데이터의 센서 값들을 상관분석을 이용하여 차원을 축소시켜 계산의 효율성을 높이고, 회귀분석적 방법을 적용하여 결함데이터를 검출할 수 있는 효과적인 알고리즘을 제시한다. H해운사의 실제 운항 중인 선박에서 생성된 데이터와 고장 보고서에 근거하여 시뮬레이션 해 본 결과 제시한 알고리즘이 효과적으로 고장을 미리 예측할 수 있음을 실험적으로 입증하였다.

Keywords

References

  1. MAN B&W Diesel A/S, "Project Guide and S80MC/S80MCE", Copenhagen Denmark, pp. 1.1-1.20, 1990.
  2. New Sulzer Diesel Ltd, "Engine Selection and Project Manual", RTA84(C,T,M), Winterthur Switzerland, pp. 1-9, 1994.
  3. Y. I. Kim, H. K. Oh, and Y. H. Yu, "The Development of Diesel Engine Room Fault Diagnosis System Using a Correlation Analysis Method", Korean Society of Marine Engineers, Vol. 30, No. 2, pp. 253-259, 2006.
  4. J. C. Bae, G. H. Kang, Y. C. Ha, K. S. Hwang, H. S. Lee, and S. M. Kim, "A Study of a Marine Engine Monitoring System base on IEEE 802.15.4", The Korean Society of Marine Engineering (KOSME), pp. 383-385, 2010.
  5. D. H. Kim, "A study on Implementation of a Real-Time Fault Diagnossis System for Marine Diesel Engines", Master Thesis, University of KOREA Marine and Ocean University, 2001.
  6. Marine safety forecast, "http://donghae.mof.go.kr/article/view.do?menuKey=106&boardKey=5&articleKey=4465", [Accessed: Sep. 09, 2016]
  7. Junichi Hirata and Koji Takasaki, "Support Scheme in Collaboration with Manufacturers Making Use of the Diagnostic Platform Based on Big Data Analysis", CIMAC World Congress, No. 74, 2016.
  8. J Gertler, "Fault Detection and Diagnosis in Engineering System", CRC, Virginia, USA. 1998.
  9. Y. J. Lee, D. Y. Kim, M. S. Hwang, and Y. S. Cheong, "An event-driven intelligent failure analysis for marine diesel engines", Korea Industrial Information System Research: Vol. 17, No. 4, pp. 71-85, 2012.
  10. Y. J. Lee, D. Y. Kim, M. S. Hwan,g and Y. S. Cheong, "An event-driven Failure Analysis System for Real-Time Prognosis", Journal of the Korea Industrial Information System Society, Vol. 18, No. 4, pp. 250-257, 2013.
  11. K. Y. Kim, Y. I. Kim, and Y. H. Yu, "The Fault Diagnosis of Marine Diesel Engines Using Correlation Coefficient", The Institute of Electronics and Information Engineers, pp. 41-45, 2010.
  12. S. I. Pak and T. H. Oh, "Correlation and Simple Linear Regression", The Korean Society of Veterinary Clinics, Vol. 27, No. 4, pp. 427-434, 2010.

Cited by

  1. Improved Forecasting Algorithm for Vessel Engine Failure vol.15, pp.11, 2016, https://doi.org/10.14801/jkiit.2017.15.11.175