Gas Turbine Blades Fault Diagnosis Method with EMD Energy Entropy and Related Vector Machine

In this paper, we use the temperature of the gas turbine blades for failure analysis, because in the real life it is difficult for us to measure the failure temperature data of the gas turbine blade, and therefore we require a basic understanding of gas turbine blade structure and working principle to simulate the fault data of the gas turbine blade. Then do the gas turbine fault diagnosis of turbine blades based on empirical mode decomposition and relevance vector machine. First decompose failure non-stationary signals into several stationary signals by EMD method, which is the sum of intrinsic mode function. When the turbine blade is broken down, the energy of the signal in different frequency bands change, therefore, its energy entropy can be calculated to determine whether it is the failure.

[1]  Jing Lin,et al.  Feature Extraction Based on Morlet Wavelet and its Application for Mechanical Fault Diagnosis , 2000 .

[2]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Liu Long,et al.  IETM technology research in the Integrated Diagnostics of the Equipment System , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[4]  Jeng-Shyang Pan,et al.  A Tabu Seach Based Maximum Descent Algorithm for VQ Codebook Design , 2001, J. Inf. Sci. Eng..

[5]  Daniel Belega,et al.  Amplitude Estimation by a Multipoint Interpolated DFT Approach , 2009, IEEE Transactions on Instrumentation and Measurement.

[6]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[7]  Louis A. Urban,et al.  Gas Path Analysis Applied to Turbine Engine Condition Monitoring , 1973 .

[8]  D. C. Rife,et al.  Use of the discrete fourier transform in the measurement of frequencies and levels of tones , 1970, Bell Syst. Tech. J..

[9]  A. M. Birk,et al.  Development of Fault Diagnosis and Failure Prediction Techniques for Small Gas Turbine Engines , 2001 .

[10]  Hans R. Depold,et al.  The Application of Expert Systems and Neural Networks to Gas Turbine Prognostics and Diagnostics , 1998 .

[11]  Jeng-Shyang Pan,et al.  Vector quantization based on genetic simulated annealing , 2001, Signal Process..

[12]  Samuel C. Rainey,et al.  The Interactive Electronic Technical Manual: Requirements, Current Status, and Implementation. Strategy Considerations. , 1991 .

[13]  Zhongxing Geng,et al.  The algorithm of interpolating windowed FFT for harmonic analysis of electric power system , 2001 .

[14]  F. Harris.  On the use of windows for harmonic analysis with the discrete Fourier transform , 1978, Proceedings of the IEEE.

[15]  K. Sluka,et al.  Descending facilitatory pathways from the RVM initiate and maintain bilateral hyperalgesia after muscle insult , 2008, PAIN.

[16]  K. K. Botros,et al.  A demonstration of artificial neural-networks-based data mining for gas-turbine-driven compressor stations , 2002 .

[17]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[18]  Riti Singh,et al.  Gas Turbine Engine and Sensor Fault Diagnosis Using Optimization Techniques , 2002 .

[19]  Yoshiki Uchikawa,et al.  On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm , 1992, IEEE Trans. Neural Networks.