Intelligent Fault Diagnosis in Power Plant Using Empirical Mode Decomposition, Fuzzy Feature Extraction and Support Vector Machines

Abstract:

In this paper, a novel intelligent fault diagnosis method based on empirical mode decomposition (EMD), fuzzy feature extraction and support vector machines (SVM) is proposed. The method consists of two stages. In the first stage, intrinsic mode components are obtained with EMD from original signals and converted into fuzzy feature vectors, and then the mechanical fault can be detected. In the second stage, these extracted fuzzy feature vectors are input into the multi-classification SVM to identify the different abnormal cases. The proposed method is applied to the classification of a turbo-generator set under three different operating conditions. Testing results show that the classification accuracy of the proposed model is greatly improved compared with the multi-classification SVM without feature extraction and the multi-classification SVM with extracting the fuzzy feature from wavelet packets, and the faults of steam turbo-generator set can be correctly and rapidly diagnosed using this model.

• Periodical: Key Engineering Materials (Volumes 293-294)
• Pages: 373-382
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.293-294.373
• Online since: September 2005
• Authors: Qiao Hu, Zheng Jia He, Yanyang Zi, Zhou Suo Zhang, Yaguo Lei
• Keywords: Empirical Mode Decomposition (EMD), Fuzzy Feature Extraction, Intelligent Fault Diagnosis, Power Plant, Support Vector Machine (SVM)

References

[1] M. Ge, R. Du, G.C. Zhang and Y.S. Xu: Mechanical System and Signal Processing Vol. 18 (2004), p.143.

[2] Z.J. He: Study on condition diagnostic technologies for complex-structured rotating machinery (Kyushu Institute of Technology, Japan 1998).

[3] N.E. Huang et al: Proceedings of the Royal Society of London A Vol. 454 (1998), p.903.

[4] Z.J. He, J.Y. Zhao, Y.B. He and Q.F. Meng: Proceedings of The IEEE International Conference on Industrial Thchnology. 1996, p.724.

[5] D.J. Yu, J.S. Cheng, Y. Yang: Mechanical System and Signal Processing. Vol. 19 (2005), p.259.

[6] J.F. Gao, W.G. Shi, J.X. Tan and F.J. Zhong: IEEE Canadian Conference on an Electrical Computer Engineering. IEEE Inc, 2002, p.1622.

[7] Q. Hu, Z.S. Zhang and Z.Z. He: Proceedings of the International Conference on Frontiers of Design and Manufacturing. Science Press USA Inc, 2004, p.87.

[8] J. Chu, Q. Gai and H.Y. Zhang: Proceedings of the International Symposium on Test and Measurement. Vol. 3(2003), p. (2039).

[9] C.J.C. Burges: Data Mining and Knowledge Discovery. Vol. 2 (2) (1998), p.955.

[10] V.N. Vapnik: IEEE Transactions on Neural Networks. Vol. 10 (5) (1999), p.988.

[11] C.W. Hsu and C.J. Lin: IEEE Transactions on Neural Networks. Vol. 13(2) (2002), p.415.

[12] L.J. Li and Z.S. Zhang and Z.J. He: Proceedings of International Conference on Intelligent Maintenance Systems. 2003, p.52.