PNN and GRNN Approach for Fault Diagnosis of Steam Turbine

Abstract:

The artificial neural networks have received wide research efforts in fault diagnostics in recent years. This study proposes two types of feedforward neural networks (PNN and GRNN) for diagnosing the fault of the steam turbine. The eigenvectors of the vibration signals in steam turbine can be extracted by the time-domain analysis after the wavelet packet decomposition and reconstruction. Depending on these eigenvectors, we developed the fault diagnosis program with the PNN and GRNN approach for the steam turbine in Matlab, and diagnosed two common faults of steam turbine (mass unbalance and oil whirl). The diagnostic accuracy is up to 94.44%, and the diagnostic time is short. The results demonstrate that the diagnostic approach is able to identify the common faults of steam turbine quickly and efficiently.

• Periodical: Applied Mechanics and Materials (Volumes 271-272)
• Pages: 1592-1596
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.271-272.1592
• Online since: December 2012
• Authors: Rui Yu, Zhi Wu Ke, Xian Ling Li, Ke Long Zhang, Xin Wan
• Keywords: Fault Diagnosis, GRNN, PNN, Steam Turbine

References

[1] H. Li, C.X. Sun, X. S Hu: Transactions of China Electrotechnical Society, Vol. 15(3) (2000), p.57.

[2] Q.L. Guo: Proc. International Joint Conference on Neural Networks (2008), p.25.

[3] K. Salahshoor, M. Kordestani, M. Khoshro: Energy Vol. 35(12) (2010), p.5472.

[4] Donald F. Specht: Neural Networks Vol. 3(1) (1990), p.109.

[5] Parzen E: Annual Math Statist Vol. 33(3) (1962), p.1065.

[6] Donald F. Specht: IEEE Trans Neural Network Vol. 2(6) (1991), p.568.

[7] C.R. Wei, S.L. Liu: Mining & Processing Equipment Vol. 33(8) (2005), p.88 (In Chinese).