Korean Journal of Computational Design and Engineering (한국CDE학회논문집)

Society for Computational Design and Engineering (한국CDE학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Data Pre-filtering Methods for Fault Diagnosis

시스템 결함원인분석을 위한 데이터 로그 전처리 기법 연구

  • 이양지 (울산과학기술대학교 디자인 및 인간공학부) ;
  • 김덕영 (울산과학기술대학교 디자인 및 인간공학부) ;
  • 황민순 (현대중공업 통신운영부) ;
  • 정영수 (현대중공업 통신운영부)
  • Received : 2012.02.09
  • Accepted : 2012.02.28
  • Published : 2012.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

High performance sensors and modern data logging technology with real-time telemetry facilitate system fault diagnosis in a very precise manner. Fault detection, isolation and identification in fault diagnosis systems are typical steps to analyze the root cause of failures. This systematic failure analysis provides not only useful clues to rectify the abnormal behaviors of a system, but also key information to redesign the current system for retrofit. The main barriers to effective failure analysis are: (i) the gathered data (event) logs are too large in general, and further (ii) they usually contain noise and redundant data that make precise analysis difficult. This paper therefore applies suitable pre-processing techniques to data reduction and feature extraction, and then converts the reduced data log into a new format of event sequence information. Finally the event sequence information is decoded to investigate the correlation between specific event patterns and various system faults. The efficiency of the developed pre-filtering procedure is examined with a terminal box data log of a marine diesel engine.

Keywords

References

  1. Lee, J.-H., Park, S.-W. and Seo, B.-H., 2000, Fault Diagnosis for a System Using Classified Pattern and Neural Networks, Journal of the Korean Institute of Electrical Engineers, 49, pp. 643-650,
  2. Kim, Y.-I., Oh, H.-K. and Yu, Y.-H., 2006, The Fault Diagnosis Method of Diesel Engines Using a Statistical Analysis Method, Journal of the Korean Society of Marine Engineering, 30, pp. 247-252.
  3. Lee, S.-S. and Lee, D.-K., 2008, Development of Integrated System for Safety Assessment of Damaged Ship, Trans. of the SCCE, 13, pp. 227- 234.
  4. Lee, K.-H., Kin, H.-S., Han, S.-W., Park, J.-H. and Oh, J., 2005, Network-based Simulation System Framework for the Safety Assessment of Ship, Trans. of the SCCE, 10, pp. 356-364.
  5. Kim, S.-H., Kim, J.-K., Lee, D.-C. and Jang, S.-K., 2003, A Study of Torsional Vibration Monitoring System of Diesel Engine, Journal of the Korean Society of Marine Engineering, pp. 197-204.
  6. Kim, K.-Y., Kim, Y.-I. and Yu, Y.-H., 2011, The Fault Diagnosis of Marine Diesel Engines Using Correlation Coefficient for Fault Detection, Journal of Korea Navigation Institute, 15, pp. 18- 24.
  7. Y.-M. Lee, K.-Y. Lee, S.-H. Bae, I.-S. Shin, H. Jang, J.-K. Lee, Defect Detection of Ship Engine Using Duplicated Checking of Vibration-data-distinction Method and Classification of Fault-wave, Journal of Korean Navigation and Port Research, 33, pp. 671-678. https://doi.org/10.5394/KINPR.2009.33.10.671
  8. Chun, H.-C. and Yu, Y.-H., 2007, A Data Fault Detection System for Diesel Engines Using Neural Networks, Journal of the Korean Society of Marine Engineering, 26, pp. 493-500.
  9. Yi, S.-K., Hong, S.-E. and Park, S.-H., 2006, A Similar Price Zone Determination of Public Land Price Using a Hybrid Clustering Technique, Journal of the Korean Geographical Society, 41, pp. 121-135.
  10. Jeon, J.-H., Yoo, J.-S. and Kim, M.-H., 2006, Path-based In-network Join Processing for Event Detection and Filtering in Sensor Networks, Journal of the Korean Institute of Information Scientists and Engineers, 33, pp. 620-630.
  11. Yang, P. and Liu, S. S., 2006, Fault Diagnosis for Boilers in Thermal Power Plant by Data Mining. Journal of Information and Computational Science, 3 pp. 117-127.
  12. Song, B.-H., Park, K.-W., Lee, J.-S., Lee, K.-H., Jung, M.-A. and Lee, S.-R., 2010, Efficient Processing of Multidimensional Sensor Stream Data in Digital Marine Vessel, Journal of Communication and Network, 35 pp. 794-800.
  13. Rabatel, J., Bringay, S. and Poncelet, P., 2009, SO_MAD: SensOr Mining for Anomaly Detection in Railway Data, In Proceedings of ICDM, 5633, pp. 191-205.
  14. Kim, J.-I., Kim, D.-I., Song, M.-J., Han, D.-Y. and Hwang, B.-H., 2010, Discovering Temporal Relation Considering the Weight of Events in Multidimensional Stream Data Environment, Journal of the Korea Contents Association, 10, pp. 99-110.
  15. Das, G., Lin, K.-I., Mannila, H., Renganathan, G. and Smyth, P., 1998, Rule Discovery from Time Series, Knowledge Discovery and Data Mining, pp. 16-22.
  16. Elomaa, T. and Rousu, J., 1999, General and Efficient Multisplitting of Numerical Attributes, Machine Learning, 36, pp. 201-244. https://doi.org/10.1023/A:1007674919412
  17. Lee, S.-H., 2003, A Density-based Approach to Discretizing Numeric Attributes, pp. 83-88.
  18. Jun, B.-H. and Kim, J.-H., 1995, Introduction to Relative Entropy for the Discretization of Continuous-Valued Attributes, Journal of the institute of Electronics Engineers of Korea, 18, pp. 1210-1213.
  19. Han, J., Pei, J., Yin, Y. and Mao, R., 2004, Mining Frequent Pattern without Candidate Generation: A Frequent-Pattern Tree Approach, Data and Knowledge Discovery, 8, pp. 53-81. https://doi.org/10.1023/B:DAMI.0000005258.31418.83
  20. Mugan, J. and Truemper, K., 2007, Discretization of Rational Data, In Proceedings of MML (Mathematical Methods for Learning).
  21. Isermann, R., 2006, Fault-Diagnosis Systems: An introduction from Fault Detection to Fault Tolerance, Springer, Germany, pp. 475.
  22. Lee, Y.-J., Kim, D.-Y., Hwang, M.-S. and Cheong, Y.-S., 2012, "A Study on Data Prefiltering Methods for Fault Diagnosis, Proceedings of the Korea society of CAD/CAM Engineers Conference, pp. 301-308.

Cited by

  1. An Event-Driven Failure Analysis System for Real-Time Prognosis vol.18, pp.4, 2013, https://doi.org/10.7315/CADCAM.2013.250