Research on Fault Recognition for Centrifugal Compressor Using Entropy Weight-Based Gray Relational Analysis

Abstract:

A new fault recognition method for centrifugal compressor was proposed by using entropy weight-based gray relational analysis (EW-GRA). Firstly, the weight values of all fault features were calculated objectively by the entropy method to avoid the influence of subjective factors. Secondly, an improved local gray relational coefficient (LGRC) formula with weight measures was designed to reflect the contributions of different fault features. Thirdly, according to the relationship between similarity degree and Euclidean distance, the local gray relational distances (LGRD), the global gray relational distances (GGRD) and the global gray relational grades (GGRG) were calculated, and consequently, the fault recognition result was obtained by using the max membership degree principle. Finally, the engineering practicability and validity of the EW-GRA method was demonstrated by a centrifugal compressor fault diagnosis example, and the results show that the EW-GRA method is more effective and accurate than the traditional gray relational analysis (T-GRA) method and the weighted gray relational analysis (W-GRA) method.

• Periodical: Applied Mechanics and Materials (Volumes 29-32)
• Pages: 685-690
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.29-32.685
• Online since: August 2010
• Authors: Lan Yun Li, Zhuan Zhao Yang, Xiao Li, Zhi He
• Keywords: Centrifugal Compressor, Entropy Weight, Fault Recognition, Grey Relational Analysis (GRA)

References

[1] G. Petela, R. Motriuk, M. Betz, V. Stokung: Centrifugal Compressor Health Diagnostics Based on Internal Noise Spectrum. Proceedings of the 2002 International Conference on Noise and Vibration Engineering, (2002), pp.1507-1518.

[2] P. Wang. The Research of Intelligent Methods on Fault Diagnosis for Centrifugal compressor. Daqing Pettoleum Institute, (2006), pp.21-37.

[3] Q. S. Zeng, X. J. Wang: Fault Diagnosis of Centrifugal Compressor Vibration Based on Wavelet Power Spectrum and Rough Set Theory. Journal of Central South University (Science and Technology), Vol. 40, No. 3 (2009), pp.706-710.

[4] Y. Li, W. M. Wang, J. J. Gao, S. X. Li: An Experimental Study on the Self-recovery Regulation System of Centrifugal Compressor Axial Displacement Fault. WSEAS Transactions on Systems, Vol. 8, No. 11 (2009), pp.1217-1227.

[5] X. He, J. N. Liu, S. X. Li: Applications of Case-based Reasoning Based on Grey Relational Theory in Fault Intelligent Diagnosis System. China Mechanical Engineering, Vol. 15, No. 22 (2004), p.2022-(2026).

[6] R. W. Liu, X. Z. Guo: Gray Correlation Analysis Method of On-line Faults Diagnosis in Drilling. Drilling and Production Technology, Vol. 27, No. 6 (2004), pp.17-25.

[7] Z. W. Chen, D. Mi, Z. S. Xu: Application of Correlation Degree Analysis of Oil Spectral Data in Condition Monitoring of Engine. Lubrication Engineering, Vol. 12, No. 6 (2006), pp.107-109.