DOI QR코드

DOI QR Code

Feature Extraction for Bearing Prognostics based on Frequency Energy

베어링 잔존 수명 예측을 위한 주파수 에너지 기반 특징신호 추출

  • Kim, Seokgoo (Dept. of Aerospace and Mechanical Eng., Korea Aerospace University) ;
  • Choi, Joo-Ho (School. of Aerospace and Mechanical Eng., Korea Aerospace University) ;
  • An, Dawn (Daegyeong Division/Aircraft System Technology Group., Korea Institute of Industrial Technology)
  • 김석구 (한국항공대학교 항공우주 및 기계공학과) ;
  • 최주호 (한국항공대학교 항공우주 및 기계공학부) ;
  • 안다운 (한국생산기술연구원 대경지역본부/항공시스템기술그룹)
  • Received : 2017.01.31
  • Accepted : 2017.03.10
  • Published : 2017.04.30

Abstract

Railway is one of the public transportation systems along with shipping and aviation. With the recent introduction of high speed train, its proportion is increasing rapidly, which results in the higher risk of catastrophic failures. The wheel bearing to support the train is one of the important components requiring higher reliability and safety in this aspect. Recently, many studies have been made under the name of prognostics and health management (PHM), for the purpose of fault diagnosis and failure prognosis of the bearing under operation. Among them, the most important step is to extract a feature that represents the fault status properly and is useful for accurate remaining life prediction. However, the conventional features have shown some limitations that make them less useful since they fluctuate over time even after the signal de-noising or do not show a distinct pattern of degradation which lack the monotonic trend over the cycles. In this study, a new method for feature extraction is proposed based on the observation of relative frequency energy shifting over the cycles, which is then converted into the feature using the information entropy. In order to demonstrate the method, traditional and new features are generated and compared using the bearing data named FEMTO which was provided by the FEMTO-ST institute for IEEE 2012 PHM Data Challenge competition.

철도는 항공기, 선박 등과 더불어 대표적 대중교통 수단으로서 최근 고속 철도의 등장으로 인해 그 비중이 점점 더 높아지고 있으며, 아울러 대형사고의 위험 또한 증가하고 있다. 이중에서 철도 차량의 차축 베어링은 높은 안전성이 요구되는 부품으로서 최근 이의 고장예측을 위한 건전성 관리기술(Prognostics and Health Management, PHM)에 많은 연구가 집중되고 있다. PHM은 센서를 통해 얻은 데이터로부터 결함관련 특징신호를 추출하고 현재의 고장수준 진단과 미래의 고장싯점을 예측하는 기술로서, 이중에서 가장 중요한 부분은 올바른 특징신호를 추출하는 것이다. 그러나 지금까지의 특징신호들은 잡음으로 인한 심한 변동이나 비단조 경향으로 인해 고장예측에 이용하기에 부족한 점이 있었다. 본 연구에서는 이를 극복하기 위해 주파수 에너지 이동현상을 기반으로 정보 엔트로피를 특징신호로 사용하는 새로운 특징신호 추출법을 개발하고 IEEE 2012 PHM 경진대회에서 공개된 FEMTO 베어링 수명시험 데이터를 대상으로 기존의 특징신호들과 고장예측 성능비교를 함으로써 그 우수성을 검증하였다.

Keywords

References

  1. An D., Kim N. H. and Choi J.(2016), "Bearing Prognostics Method Based on Entropy Decrease at Specific Frequency," In 18th AIAA Non-Deterministic Approaches Conference, p.1678.
  2. Antoni J.(2006), "The spectral kurtosis: a useful tool for characterising non-stationary signals," Mechanical Systems and Signal Processing, vol. 20, no. 2, pp.282-307. https://doi.org/10.1016/j.ymssp.2004.09.001
  3. FEMTO Bearing Data Set, NASA Ames Prognostics Data Repository, http://ti.arc.nasa.gov/project/ prognostic-data-repository, NASA Ames Research Center, Moffett Field, CA.
  4. NECTOUX, Patrick et al.(2012), PRONOSTIA: An experimental platform for bearings accelerated degradation tests, In: IEEE International Conference on Prognostics and Health Management, PHM'12. IEEE Catalog Number: CPF12PHM-CDR, p.1-8.
  5. Note S. F. A.(2012), Rolling Element Bearings, REB, Sales Technology, Inc, League City TX.
  6. Randall R. B. and Antoni J.(2011), "Rolling element bearing diagnostics-a tutorial," Mechanical systems and signal processing, vol. 25, no. 2, pp.485-520. https://doi.org/10.1016/j.ymssp.2010.07.017
  7. Siegel D., Lee J. and Canh L.(2011), "Methodology and framework for predicting rolling element helicopter bearing failure," Prognostics and Health Management (PHM), 2011 IEEE Conference on. IEEE.
  8. Siew W. S., Smith W. A., Peng Z. and Randall R. B.(2015), "Fault Severity Trending in Rolling Element Bearings," Acoustics 2015 Hunter Valley.
  9. Sutrisno E., Oh H., Vasan A. S. S. and Pecht M.(2012), "Estimation of remaining useful life of ball bearings using data driven methodologies," In Prognostics and Health Management (PHM), 2012 IEEE Conference on, IEEE, pp.1-7.
  10. Wang T.(2012), "Bearing life prediction based on vibration signals: A case study and lessons learned". In Prognostics and Health Management (PHM), 2012 IEEE Conference on, IEEE, pp.1-7.
  11. Yan W., Qiu H. and Iyer N.(2008), "Feature extraction for bearing prognostics and health management," (phm)-a survey (preprint) (No. AFRL-RX-WP-TP-2008-4309). AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH MATERIALS AND MANUFACTURING DIRECTORATE.

Cited by

  1. 원심주조방식과 레이저 클래딩 증착법을 통한 화이트메탈의 기계 및 마찰특성 비교 vol.34, pp.3, 2018, https://doi.org/10.9725/kts.2018.34.3.84
  2. 탈수소 열처리 공정에 의한 원심주조 메탈베어링의 제조 시스템 vol.19, pp.5, 2017, https://doi.org/10.14775/ksmpe.2020.19.05.111
  3. Mechanical Properties of White Metal on SCM440 Alloy Steel by Laser Cladding Treatment vol.11, pp.6, 2017, https://doi.org/10.3390/app11062836