DOI QR코드

DOI QR Code

A Signal Processing Technique for Predictive Fault Detection based on Vibration Data

진동 데이터 기반 설비고장예지를 위한 신호처리기법

  • Song, Ye Won (Service Business Department, SOOSAN INT) ;
  • Lee, Hong Seong (Department of Industrial and Management Systems Engineering, Kyung Hee University) ;
  • Park, Hoonseok (Department of Industrial and Management Systems Engineering, Kyung Hee University) ;
  • Kim, Young Jin (Department of Industrial and Management Systems Engineering, Kyung Hee University) ;
  • Jung, Jae-Yoon (Department of Industrial and Management Systems Engineering, Kyung Hee University)
  • Received : 2018.03.29
  • Accepted : 2018.05.16
  • Published : 2018.05.31

Abstract

Many problems in rotating machinery such as aircraft engines, wind turbines and motors are caused by bearing defects. The abnormalities of the bearing can be detected by analyzing signal data such as vibration or noise, proper pre-processing through a few signal processing techniques is required to analyze their frequencies. In this paper, we introduce the condition monitoring method for diagnosing the failure of the rotating machines by analyzing the vibration signal of the bearing. From the collected signal data, the normal states are trained, and then normal or abnormal state data are classified based on the trained normal state. For preprocessing, a Hamming window is applied to eliminate leakage generated in this process, and the cepstrum analysis is performed to obtain the original signal of the signal data, called the formant. From the vibration data of the IMS bearing dataset, we have extracted 6 statistic indicators using the cepstral coefficients and showed that the application of the Mahalanobis distance classifier can monitor the bearing status and detect the failure in advance.

항공기 엔진, 풍력발전기, 모터 등 회전기기에서 발생하는 많은 문제들은 진동이나 소음과 같은 신호 데이터를 측정하여 이상감지를 할 수 있으며, 주파수 분석 등 여러 가지 신호처리가 데이터 전처리 단계에서 필요하다. 본 논문에서는 진동 데이터를 분석하여 설비 이상상태를 감지하는 기법을 소개한다. 정상상태 데이터를 기반으로 마할라노비스 거리를 측정하여 이상상태 유무를 모니터링 하는 방식을 사용한다. 특히 신호 데이터의 전처리 기법들을 도입하여 이상상태 감지의 성능을 개선할 수 있음을 보여준다. 전처리 단계에서 신호 데이터 수집 과정에서 발생한 누설오차(leakage)를 없애기 위해 해밍 윈도우(Hamming window)를 적용하고, 신호 데이터의 원신호인 포먼트(formant)를 분리하기 위하여 켑스트럼(cepstrum) 분석을 실시한다. IMS 베어링 진동 공개데이터를 대상으로 시간 구간별로 6가지 통계지표를 추출한 후 마할라노비스 거리 분류기를 적용하여 성능을 검증하였다. 제시된 신호처리 전처리 기법을 적용함으로써 성능이 획기적으로 향상되는 것을 실험에서 보여주었다.

Keywords

References

  1. Alejandro, D., Mejia, T., Medjaher, K., Zerhouni, N., and Tripot, G., "A Data-Driven Failure Prognostics Method Based on Mixture of Gaussians Hidden Markov Models," IEEE Transactions on Reliability, Vol. 61, No. 2, pp. 491-501, 2012. https://doi.org/10.1109/TR.2012.2194177
  2. Jeon, B. C., Jung, J. H., Youn, B. D., Kim, Y. W., and Bae, Y. C., "Evaluation of Datum Unit for Diagnostics of Journal-Bearing Systems," Transactions of the Korean Society of Mechanical Engineers, Vol. 39, No. 8, pp. 801-806, 2015. https://doi.org/10.3795/KSME-A.2015.39.8.801
  3. Lee, S. H. and Lim, G., "Performance Comparison of Mahalanobis-Taguchi System and Logistic Regression-A Case Study," Journal of the Korean Institute of Industrial Engineers, Vol. 39, No. 5, pp. 393-402, 2013. https://doi.org/10.7232/JKIIE.2013.39.5.393
  4. Lee, S. H. and Yoon, B. D., "Industry 4.0 and direction of prognostics and health management (PHM)," Vol. 25, No. 2-4, pp. 351-357, 2015.
  5. Lim, H. J., Kim, S. D., Jung, S. H., Hong, S. W., Oh, G. H., and Park, J. H., "Analysis of Vibration Signal for Failure Diagnosis of Rotating Devices," Proceedings of Korean Society of Precision Engineering Spring Conference, pp. 301-307, 1995.
  6. Paik, Y. S., Mok, Y. J., Lee, S. J., and Lee, Y. B., "Data Processing of Vibration Records and Its Application," Journal of the Korean Society of Civil Engineers, Vol. 16, Vol. 2-4, No. III-4, pp. 351-358, 1995.
  7. Park, C. S. and Youn, D. J., "A Noise Reduction Signal Processing for Online Monitoring: Minimum Variance Cepstrum," Journal of the Korean Society for Nondestructive Testing, Vol. 31, No. 6, pp. 671-676, 2011.
  8. Park, S. G., Park, W. S., Jung, J. E., Lee, Y. Y., and Oh, J. E., "A Fault Diagnosis on the Rotating Machinery Using Mahalanobis Distance," Transactions of the Korean Society of Mechanical Engineers, Vol. 32, No. 7, pp. 556-560, 2008. https://doi.org/10.3795/KSME-A.2008.32.7.556
  9. Yang, J. H. and Kwon, O. K., "Model-based Fault Diagnosis Applied to Vibration Data," Journal of Institute of Control, Robotics and Systems, Vol. 18, No. 12, pp. 1090-1095, 2012. https://doi.org/10.5302/J.ICROS.2012.18.12.1090