Vibration Fault Diagnosis for Wind Turbine Based on Enhanced Supervised Locally Linear Embedding

Abstract:

Fault diagnosis for wind turbine is an important task for reducing their maintenance cost. However, the non-stationary dynamic operating conditions of wind turbines pose a challenge to fault diagnosis for wind turbine. Fault diagnosis is essentially a kind of pattern recognition. In this paper, a novel fault diagnosis method based on enhanced supervised locally linear embedding is proposed for wind turbine. The approach first performs the recently proposed manifold learning algorithm locally linear embedding on the high-dimensional fault signal samples to learn the intrinsic embedded multiple manifold features corresponding to different fault modes. Enhanced supervised locally linear embedding not only can map them into a low-dimensional embedded space to achieve fault feature extraction, but also can deal with new fault samples. Finally fault classification is carried out in the embedded manifold space. The wind turbine gearbox ball bearing vibration fault signals are used to validate the proposed fault diagnosis method. The results indicate that the proposed approach obviously improves the fault classification performance and outperforms the other traditional approaches.

• Periodical: Advanced Materials Research (Volumes 1008-1009)
• Pages: 983-987
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1008-1009.983
• Online since: August 2014
• Authors: Xiang Wang*, Yuan Zheng
• Keywords: Fault Diagnosis, Manifold Learning, Supervised Locally Linear Embedding, Vibration Signal

References

[1] Kusiak A, Li WY: Renewable Energy. 36, pp.16-23(2011).

[2] B.W. Li, Y. Zhang: Mech. Syst and Signal Process. 25, pp.3125-3134(2011).

[3] I.T. Jolliffe: Principal Component Analysis, Springer, (1986).

[4] K. Fuknaga: Introduction to Statistical Pattern Recognition, Academic Press, (1990).

[5] A.M. Martinez, A.C. Kak: IEEE Trans. Pattern Anal. Mach. Intell. 23(2) pp.228-233(2001).

[6] H.S. Seung, D.L. Daniel: Science 290, pp.2268-2269(2000).

[7] S.T. Roweis, L.K. Saul: Science 290, pp.2323-2326(2000).

[8] J.B. Tenenbaum, V.D. Silva, J.C. Langford: Science 290, pp.2319-2323 (2000).

[9] K. Samuel, D.L. Martin: Comput. Vision Image Understanding. pp.1-20 (2006).

[10] D.D. Ridder, O. Kouropteva, and O. Okun: in: Proceedings of the Joint International Conference, Springer, Heidelberg, pp.333-341 (2003).

[11] D. Lian, J. Yang, Z. Zheng, et al: Pattern Recognition Letters. 26, pp.2373-2389 (2005).

[12] S.Q. Zhang: Pattern Recognition Letters. 30 (2009) 1208-1218.

[13] Rafiee, J., Arvani, F., et al: Mech. Syst and Signal Process. 21, pp.1746-1754. (2007).