Journal of the Korean Society for Precision Engineering (한국정밀공학회지)

Korean Society for Precision Engineering (한국정밀공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Health Monitoring of a Refrigerator Compressor Based on Higher Order Time-Frequency Analysis and Artificial Neural Network

고차 시간-주파수 해석과 신경망 회로를 이용한 냉장고 압축기의 건전성 연구

  • Received : 2012.03.27
  • Accepted : 2012.09.15
  • Published : 2012.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Condition monitoring of the reciprocating compressor is important task. As a traditional method, health monitoring system of refrigerator depends on decision of a skilled person based on his experience. However, the skilled person cannot monitor all the compressors completely. If a sampled compressor is faulty, thousands of compressors manufactured at that place are regarded as faulty compressors. Therefore it is necessary to monitor all compressors in the production line. In the paper real time health monitoring system is developed based on high order time frequency method and artificial neural network. The system is installed in the mass production line. The result of the application has been very successful, and currently the system is working very well on the production line.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Key, M., "Modern Spectra Estimation Theory & Application," Prentice Hall, 1988.
  2. Dyer, D. and Stewart, R. M., "Detection of Rolling Element Bearing Damage by Statistical Vibration Analysis," Journal of Mechanical Design, Vol. 100, pp. 229-235, 1978. https://doi.org/10.1115/1.3453905
  3. Randall, R., "B&K Application Note," Technical Report, pp. 13-150, 1981.
  4. Lee, S. K. and White, P. R., "Two-Stage Adaptive Line Enhancer and Sliced Wigner Trispectrum for the Characterization of Faults from Gear Box Vibration Data," Journal of Vibration and Acoustics, Vol. 121, pp. 488-494, 1999. https://doi.org/10.1115/1.2894007
  5. Zhuge, Q., "Non-stationary modeling of vibration signals for monitoring the condition of machinery," Mechanical Systems and Signal Processing, Vol. 4, pp. 355-365, 1990. https://doi.org/10.1016/0888-3270(90)90020-L
  6. Wang, Y., He, Z., and Zi, Y., "Enhancement of signal denoising and multiple fault signatures detecting in rotating machinery using dual-tree complex wavelet transform," Mechanical Systems and Signal Processing, Vol. 8, pp. 119-137, 2010.
  7. McFadden, P. D., "Examination of a Technique for the Early Detection of Failure in Gears by Signal Processing of the Time Domain Average of the Meshing Vibration," Mechanical Systems and Signal Processing, Vol. 1, pp. 177-183, 1987.
  8. Lee, S. K. and White, P. R., "Higher-Order Time- Frequency Analysis and Its Application to Fault Detection in Rotating Machinery," Mechanical Systems and Signal Processing, Vol. 11, pp. 637-650, 1997. https://doi.org/10.1006/mssp.1997.0098
  9. Meegan, G. M., Nelson, H. R., Barlrt, M. L., and Wilson, G. R., "Fault detection in engines through higher order spectral analysis of acoustic signatures," Journal of the Acoustical Society of America, Vol. 106, pp. L1-L6, 1999. https://doi.org/10.1121/1.427611
  10. Wyk, P. V. and Hoffnan, A. J., "Detecting long-term trends in turbo-generator stator end-winding vibrations through neural network modelling," Journal of Sound and Vibration, Vol. 253, pp. 529-544, 2002. https://doi.org/10.1006/jsvi.2000.3486
  11. Lee, S. K., "A New Method of Smoothing Non- Oscillation Cross-Terms in Sliced Wigner Fourth Order Moment," Mechanical Systems and Signal Processing, Vol. 15, pp. 1023-1029, 2001. https://doi.org/10.1006/mssp.2001.1402
  12. Matrn, H., "Neural Network Design," PWS Publishing Company, 1996.

Cited by

  1. A Study on Oil Path Design in the Journal Bearing of a Reciprocating Compressor vol.30, pp.8, 2013, https://doi.org/10.7736/KSPE.2013.30.8.839
  2. Signal Analysis of Inverter-Type Outdoor Unit for Detecting Operation Changes of Commercial Refrigerator vol.33, pp.6, 2016, https://doi.org/10.7736/KSPE.2016.33.6.517