Transactions of the Korean Society for Noise and Vibration Engineering (한국소음진동공학회논문집)

The Korean Society for Noise and Vibration Engineering (한국소음진동공학회)
권호 표지
DOI QR코드

DOI QR Code

Fault Diagnosis for Rotating Machine Using Feature Extraction and Minimum Detection Error Algorithm

특징 추출과 검출 오차 최소화 알고리듬을 이용한 회전기계의 결함 진단

  • 정의필 (울산대학교 컴퓨터정보통신공학부) ;
  • 조상진 (울산대학교 컴퓨터정보통신공학부) ;
  • 이재열 (울산대학교 컴퓨터정보통신공학부)
  • Published : 2006.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

Fault diagnosis and condition monitoring for rotating machines are important for efficiency and accident prevention. The process of fault diagnosis is to extract the feature of signals and to classify each state. Conventionally, fault diagnosis has been developed by combining signal processing techniques for spectral analysis and pattern recognition, however these methods are not able to diagnose correctly for certain rotating machines and some faulty phenomena. In this paper, we add a minimum detection error algorithm to the previous method to reduce detection error rate. Vibration signals of the induction motor are measured and divided into subband signals. Each subband signal is processed to obtain the RMS, standard deviation and the statistic data for constructing the feature extraction vectors. We make a study of the fault diagnosis system that the feature extraction vectors are applied to K-means clustering algorithm and minimum detection error algorithm.

Keywords

References

  1. Yang, B. S., Kim, K. J. and Han, T., 2004, 'Fault Diagnosis of Induction Motors Using Data Fusion of Vibration and Current Signals', Transactions of the KSNVE, Vol.14, No. 11, pp. 1091-1100 https://doi.org/10.5050/KSNVN.2004.14.11.1091
  2. An, J. L., Hna, T., Yang, B. S., Jeon, J. J. and Kim, W. C, 2002, 'Fault Diagnostics Algorithm of Rotating Machinery Using ART-Kohonen Neural Network', Transactions of the KSNVE, Vol. 12, No. 10, pp. 799-807 https://doi.org/10.5050/KSNVN.2002.12.10.799
  3. Seo, D. W., 2000, 'A Study on the Condition Monitoring and Diagnosis of Rotating Machinery and Tools Using Wavelet Analysis', Seo-kang Univ, in Korean, MS Thesis
  4. Yang, B. S., Hwang, W. W., Kim, D. J. and Tan, A.C.C., 2003, 'Condition Classification of Small Reciprocating Compressor for Refrigerators using Artificial Neural Networks and Support Vector Machines,' Mechanical Systems and Signal Processing. Vol.19, pp. 371-390 https://doi.org/10.1016/j.ymssp.2004.06.002
  5. Kondoz, A. M., 1998, 'Digital Speech', Neural Networks for Signal Processing VIII, pp. 383-392
  6. Hideyuki W., Yuji M., Satoru T. and Shigeru K., 1998, 'Sound Monitoring based on the Generalized Probabilistic Descent Method,' Neural Networks for Signal Processing VIII, pp. 383-392
  7. Lee, C. H., 2000, 'Development of the Fault Diagnostic System on the Rotating Machinery', Han-yang Univ, in Korea, MS Thesis
  8. Juang, B. H. and Katagiri, S., 1992, 'Discriminant Learning for Minimum Error Classification,' IEEE Trans. Signal Processing, Vol. 40, No. 12, pp. 3043-3054 https://doi.org/10.1109/78.175747
  9. Hwang, W. W. and Yang. B. S., 2004, 'Fault Diagnosis -of Rotatin Machinery Using Multi-class Support Vector Machines', Transactions of the KSNVE, Vol.14, No. 12, pp. 1233-1240 https://doi.org/10.5050/KSNVN.2004.14.12.1233

Cited by

  1. Development Test for Flexible PTO Shaft Made of Ti Alloy for Aircraft vol.40, pp.8, 2016, https://doi.org/10.3795/KSME-A.2016.40.8.759