Fault Diagnosis for Speed-Up and Speed-Down Process of Rotor-Bearing System Based on Volterra Series Model and Neighborhood Rough Sets

Abstract:

For the purpose of addressing non-stationary, poor repeatability, abundant information in the speed-up and speed-down process of a rotor-bearing system, combining with volterra series (VS) and neighborhood rough sets (NRS), a new hybrid intelligent diagnosis method is proposed. The VS is a type of nonparametric model of a nonlinear system, it can model a wide range of nonlinear systems, and can get the volterra kernel that includes the related characteristics of the system through identification. The NRS extracts useful information based only on the data itself, and is used for redundant attributes reduction to make the selected features more objective. In this paper, speed signal and vibration peak-peak value were selected as input and output signals, identified volterra kernels were applied as fault features first, then the NRS was applied for feature selection, and finally support vector machine(SVM) was used as a classifier to recognize faults of the speed-up and speed-down process. The experiment results demonstrate the proposed model not only identifies the fault type, but also identifies the fault severity.

• Periodical: Advanced Materials Research (Volume 411)
• Pages: 567-571
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.411.567
• Online since: November 2011
• Authors: Xiao Ran Zhu, You Yun Zhang, Gao Liang Zhang, Zhi Zhou
• Keywords: Fault Diagnosis, Feature Selection, Neighborhood Rough Sets, Volterra Series

References

[1] Z.N. Li, Z.T. Wu, Y.Y. He, F.l. Chu. Hidden Markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery. Mechanical System and Signal Processing 19(2)(2005) 329-339.

DOI: 10.1016/j.ymssp.2004.01.001

[2] Z.N. Li, Y.Y. He, F.l. Chu, J. Han, W. Hao. Fault recognition method for speed-up and speed-down process of rotating machinery based on independent component analysis and Factorial Hidden Markov Model. Journal of Sound and Vibration 291(1-2)(2006) 60-71.

DOI: 10.1016/j.jsv.2005.05.020

[3] A.J. Hoffman, N.T. Van der Merwe. The application of neural networks to vibrational diagnostics for multiple fault conditions. Computer Standards & Interfaces 24(2)(2002)139-149

DOI: 10.1016/s0920-5489(02)00014-4

[4] P. Marzocca, J.M. Nichols, A. Milanese, M. Seaver, S.T. Trickey. Second-order spectra for quadratic nonlinear systems by volterra functional series: Analytical description and numerical simulation. Mechanical System and Signal Processing 22(8)(2008) 1882-1895.

DOI: 10.1016/j.ymssp.2008.02.002

[5] Yoshinobu Kajikawa, The Adaptive volterra Filter: Its present and Future. Electronics and Communications in Japan (Part III: Fundamental Electronic Science) 83(12)(2000)51-61

DOI: 10.1002/1520-6440(200012)83:12<51::aid-ecjc6>3.0.co;2-k

[6] R.W. Swiniarski, A. Skowron. Rough set methods in feature selection and recognition. Pattern Recognition Letters 24(6)(2003)833-849.

DOI: 10.1016/s0167-8655(02)00196-4

[7] R .Jensen, Q. Shen. Semantics-preserving dimensionality reduction: rough and fuzzy-rough-based approaches. IEEE Transactions on Knowledge and Data Engineering 16(12) (2004)1457-1471.

DOI: 10.1109/tkde.2004.96

[8] Q.H. Hu, D.R. Yu, Z.X. Xie. Numerical attribute reduction based on neighborhood granulation and rough approximation. Journal of Software 19(3)( 2008)640-649.

DOI: 10.3724/sp.j.1001.2008.00640

[9] Hao.Xin. Application of Nonlinear System Identification Based on volterra Series Model to Rotor-Bearing System Fault Diagnosis, Master's Thesis, Department of Mechanical Engineer, Xi'an Jiaotong University, Xi'an, China, 2006.