Fault Detection of Reciprocating Compressor for Small-Type Refrigerators Using ART-Kohonen Networks and Wavelet Analysis

  • Yang, Bo-Suk (School of Mechanical Engineering, Pukyong National University) ;
  • Lee, Soo-Jong (School of Mechanical Engineering, Pukyong National University) ;
  • Han, Tian (School of Mechanical Engineering, University of Science and Technology Beijing)
  • Published : 2006.12.01

Abstract

This paper proposes a condition classification system using wavelet transform, feature evaluation and artificial neural networks to detect faulty products on the production line of reciprocating compressors for refrigerators. The stationary features of vibration signals are extracted from statistical cumulants of the discrete wavelet coefficients and root mean square values of band-pass frequencies. The neural networks are trained by the sample data, including healthy or faulty compressors. Based on training, the proposed system can be used on the automatic mass production line to classify product quality instead of people inspection. The validity of this system is demonstrated by the on-site test at LG Electronics, Inc. for reciprocating compressors. According to different products, this system after some modification may be useful to increase productivity in different types of production lines.

Keywords

References

  1. Altmann, J. and Mathew, J., 1999, 'Automated DWPA Feature Extraction of Fault Information from Low Speed Rolling Element Bearing,' Proc. A-PVC '99, pp. 637-641
  2. Carpenter, G. A. and Grossberg, S., 1987, 'ART2: Self-Organization of Stable Category Recognition Codes for Analog Input Patterns,' Applied Optics, Vol. 26, No. 23, pp.217-231
  3. Carpenter, G. A. and Grossberg, S., 1988, 'The AR T of Adaptive Pattern Recognition by a Self-Organizing Neural Network,' IEEE Trans. on Computer, Vol. 21, No.3, pp. 77-88 https://doi.org/10.1109/2.33
  4. Carpenter, G. A. and Grossberg, S., 1991, 'ART3: Hierarchical Search Using Chemical Transmitters in Self-Organizing Pattern Recognition Architectures,' Neural Networks, Vol. 4, No.3, pp. 129-152
  5. Carpenter, G. A. and Grossberg, S., 1992, 'A Self-Organizing Neural Network,' IEEE Communications Magazine, Vol. 30, No.9, pp.38-49 https://doi.org/10.1109/35.156802
  6. Daubechies, I., 1988, 'Orthonormal Bases of Compactly Supported Wavelets,' Communications on Pure and Applied Mathematics, Vol. 41, pp.909-996 https://doi.org/10.1002/cpa.3160410705
  7. Daubechies, I., 1992, Ten Lectures on Wavelets, SIAM, Pennsylvania, USA
  8. Dickie, J. R., 1995, An Investigation into Second- and Higher-Order Statistical Signal Processing Tools for Machine Condition Monitoring, PhD thesis, University of Strathclyde
  9. Gardner, J. W., Hines, E. L. and Pang, C., 1996, 'Detection of Vapours and Odours from a Multi sensor Array Using Pattern Recognition: Self-Organizing Adaptive Resonance Techniques,' Measurement and Control, Vol. 29, pp. 172-177 https://doi.org/10.1177/002029409602900603
  10. Kohonen, T., 1992, LVQ_PAK- The Learning Vector Quantization Program Package, Department of Technical, Physics, Helsinki University of Technology
  11. Kohonen, T., 1995, Self-Organizlng Maps, Springer-Verlag, Berlin
  12. Kohonen, T., 1996, 'Engineering Application of the Self-Organizing Map,' Proc. IEEE, Vol. ?84, No. 10, pp. 1358-1384 https://doi.org/10.1109/5.537105
  13. Lim, D. S., An, J. L., Yang, B. S. and Kim, D. J., 2001, 'Intelligent Condition Classification System of Rotating Machinery Using Wavelet Transform, Feature Evaluation Index and LVQ,' Proc. 8th Int. Congress on Sound and Vibration, pp.2371-2378
  14. Liobet, E., 1999, 'Fuzzy ARTMAP Based Electronic Nose Data Analysis,' Sensors and Actuators B, Vol. 61, pp. 183-190 https://doi.org/10.1016/S0925-4005(99)00288-9
  15. Mallat, S. G., 1989, 'A Theory for Multiresolution Signal Decomposition: the Wavelet Representation,' IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 11, No.7, pp.674-693 https://doi.org/10.1109/34.192463
  16. Nandi, A. K. and Dickie, J. R., 1994, 'A New Approach to Condition Monitoring Using Higher-Order Statistics,' Proc. COMADEM-94, pp. 197-203
  17. Tahk, K. M. and Shin, K. H., 2002, 'A Study on the Fault Diagnosis of Roller-Shape Using Frequency Analysis of Tension Signals and Artificial Neural Networks Based Approach in a Web ?Transport System,' KSME International Journal, Vol. 16, No. 12, pp. 1604-1612
  18. Yang, B. S., Lim, D. S., Seo, S. Y. and Kim, M. H., 2000, 'Defect Diagnostics of Rotating Machinery Using SOFM and LVQ,' Proc. 7th Int. Congress on Sound and Vibration, pp. 567 - 574
  19. Yang, B. S., Kim, K. and Rao, Raj B. K. N., 2002, 'Condition Classification of Reciprocating Compressors Using RBF Neural Network,' International Journal of COMADEM, Vol. 5, No.4, pp. 12-20
  20. Yang, B. S., Han, T. and An, J. L., 2004, 'ARTKohonen Neural Network for Fault Diagnostics of Rotating Machinery,' Mechanical Systems and Signal Processing, Vol. 18, No.3, pp.645-657 https://doi.org/10.1016/S0888-3270(03)00073-6
  21. Yang, B. S., Hwang, W. W., Kim, D. J. and Tan, A. C., 2005, 'Condition Classification of Small Reciprocating Compressors for Refrigerators Using Artificial Neural Networks and Support Vector Machines,' Mechanical Systems and Signal Processing, Vol. 19, No.2, pp. 371-390 https://doi.org/10.1016/j.ymssp.2004.06.002