Journal of the Korean Society for Aeronautical & Space Sciences (한국항공우주학회지)

The Korean Society for Aeronautical and Space Sciences (한국항공우주학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Feasibility of Defect Diagnosis using Principal Component Analysis on Aircraft Vibration Data

항공기 진동 데이터 수집 및 주성분 분석을 통한 결함 진단 가능성 연구

  • Jeong, Sang-gyu (3rd Aeronautical systems team, Defense Agency for Technology and Quality) ;
  • Seo, Young-jin (3rd Aeronautical systems team, Defense Agency for Technology and Quality) ;
  • Kim, Young-mok (3rd Aeronautical systems team, Defense Agency for Technology and Quality) ;
  • Jun, Byung-kyu (3rd Aeronautical systems team, Defense Agency for Technology and Quality)
  • Received : 2018.05.30
  • Accepted : 2018.08.07
  • Published : 2018.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

In many cases, modern aircraft are equipped with data acquisition system which checks the structural integrity of the aircraft. The analysis of the vibration data collected with the system is generally performed in dependence on a skilled expert who is familiar with aircraft design. Therefore, it is difficult to provide a representative and objective defect identification standard for general users. In this paper, we shows that it is possible to identify the type of maneuvers and faults by using the Principal Component Analysis(PCA) method in the vast vibration data collected during aircraft operation without using the existing aircraft design analysis. We classified the ROK Army aircraft vibration data for maneuvers and faults types, and applied the PCA to the classified data. Our result shows that it is possible to develop an objective maneuver/fault identification method without design analysis for general users.

최신 항공기에는 항공기의 건전성을 확인하기 위한 진동데이터 수집 장비가 장착되는 경우가 많다. 이러한 장비를 통해 수집되는 진동 데이터의 분석은 항공기 설계에 정통한 전문가에 의존하는 것이 일반적이며, 설계 분석을 통해 일반 사용자를 위한 대표적이고 객관적인 결함식별 기준을 제시하는 것은 쉽지 않다. 본 논문에서 우리는 기존의 항공기 설계분석 방법이 아닌, 운용 중 수집되는 방대한 양의 진동 데이터에 주성분 분석을 적용하는 방식으로 기동 및 결함유형 식별이 가능한지를 확인하였다. 이를 위해 국내 육군에서 실운용중인 항공기의 진동 데이터를 실측하여 기동 및 결함 유형별로 분류하였고, 분류된 데이터에 주성분 분석 기법을 적용하였다. 그 결과 설계 분석을 하지 않고도 운용 데이터 분석만을 통하여 일반 사용자들을 위한 기동/결함유형 식별 도구의 개발이 가능함이 확인되었다.

Keywords

References

  1. Sohn, H., A Review of Structural Health Monitoring Literature 1996-2001. No. LA-UR- 02-2095, Los Alamos National Laboratory, Los Alamos, NM, 2002, pp.91-95.
  2. Tumer, I., "A survey of aircraft engine health monitoring systems," Proceeding of The 35th Joint Propulsion Conference and Exhibit, June, 1999, pp.2528.
  3. Wold, S., "Principal component analysis," Journal of The Chemometrics and Intelligent Laboratory Systems, Vol. 2, No. 1, 1987, pp.37-52. https://doi.org/10.1016/0169-7439(87)80084-9
  4. Abdi, H., "Principal component analysis," Journal of The Computational Statistics, Vol. 2, No. 4, 2010, pp.433-459.
  5. Du, Q., "Hyperspectral image compression using JPEG2000 and principal component analysis," Journal of The Geoscience and Remote sensing letters, Vol. 4, No. 2, 2007, pp.201-205. https://doi.org/10.1109/LGRS.2006.888109
  6. Yang, J., "Two-dimensional PCA: a new approach to appearance-based face representation and recognition," Journal of The Pattern Analysis and Machine Intelligence, Vol. 26, No. 1, 2004, pp.131-137. https://doi.org/10.1109/TPAMI.2004.1261097
  7. Rai, V., "Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert- Huang transform," Journal of The Mechanical Systems and Signal Processing, Vol. 21, No. 6, 2007, pp.2607-2615. https://doi.org/10.1016/j.ymssp.2006.12.004
  8. Zhao, W., Discriminant analysis of principal components for face recognition, Springer, Heidelberg, Berlin, 1998, pp.73-85.
  9. Golub, G., "Singular value decomposition and least squares solutions," Journal of The Numerische mathematik, Vol. 14, No. 5, 1970, pp.403-420. https://doi.org/10.1007/BF02163027
  10. Berrar, D., A Practical Approach to Microarray Data Analysis, Springer, Boston, MA, 2003, pp.91-109.