Crack detection in a rotating shaft using artificial neural networks and PSD characterisation

The diagnosis of cracks in rotating shafts using non-destructive techniques provides a route for avoiding catastrophic failure of these common components. This study measured the dynamic response of a full-scale rotating shaft with three different crack depths. A novel non-destructive system is developed and described. The system uses vertical vibration of the system measured over time and characterises its behaviour using elements of the power spectral density (PSD) gained from a fast Fourier transform of the time-history. The PSDs were used as an input into an artificial neural network (ANN) to detect the presence of cracks using changes in the spectral content of the vibration of the system. A novel method for reducing the amount of data input into the ANN is described. The PeakPosition Component Method (PPCM) reduces data transfer by using statistical characterisation of the position of the peaks in the PSD. The peak positions represent a small fraction of the information contained in the total frequency range. The number of the PSD peaks used as input to the neural net is a small fraction of the total frequency range. The ANN was a supervised feed-forward network with Levenberg-Marquardt back-propagation algorithm acting on the PPCM results. The frequency spectrum for the three different crack lengths examined show clear shifts in the peak positions of the PSD and the results clearly demonstrate the feasibility of using the new system to detect cracks in-service.

[1]  Andrew D. Dimarogonas,et al.  Vibration of cracked structures: A state of the art review , 1996 .

[2]  Robert B. Randall,et al.  The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines , 2006 .

[3]  Andrew D. Dimarogonas,et al.  VIBRATION OF CRACKED SHAFTS IN BENDING , 1983 .

[4]  Y. Bar-Cohen,et al.  Emerging NDT technologies and challenges at the beginning of the third millennium, Part 2 , 2000 .

[5]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[6]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[7]  Mo-Yuen Chow,et al.  Neural-network-based motor rolling bearing fault diagnosis , 2000, IEEE Trans. Ind. Electron..

[8]  Janko Petrovčič,et al.  Fault diagnosis of a vacuum cleaner motor by means of sound analysis , 2004 .

[9]  Gerard Ledwich,et al.  A novel fuzzy logic approach to transformer fault diagnosis , 2000 .

[10]  Tsuyoshi Inoue,et al.  Detection of a Rotor Crack Using a Harmonic Excitation and Nonlinear Vibration Analysis , 2006 .

[11]  Chong-Won Lee,et al.  MODELLING AND VIBRATION ANALYSIS OF A SIMPLE ROTOR WITH A BREATHING CRACK , 1992 .

[12]  L. Swanson.  Linking maintenance strategies to performance , 2001 .

[13]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[14]  P. J. Griffin,et al.  A combined ANN and expert system tool for transformer fault diagnosis , 1998 .

[15]  P. D. McFadden,et al.  Model for the vibration produced by a single point defect in a rolling element bearing , 1984 .

[16]  Kevin Knight,et al.  Artificial intelligence (2. ed.) , 1991 .

[17]  Fulei Chu,et al.  Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography , 2004 .

[18]  Kshitij Gupta,et al.  Dynamics of a bowed rotor with a transverse surface crack , 2006 .

[19]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[20]  Darryll J. Pines,et al.  A review of vibration-based techniques for helicopter transmission diagnostics , 2005 .

[21]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation (3rd Edition) , 2007 .

[23]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[24]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[25]  Tejas H. Patel,et al.  Vibration response of a cracked rotor in presence of rotor–stator rub , 2008 .

[26]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[27]  S.M. Kay,et al.  Spectrum analysis—A modern perspective , 1981, Proceedings of the IEEE.

[28]  Arthur W. Lees,et al.  A non-linear study of a cracked rotor , 2007 .

[29]  Peter Tavner,et al.  Condition monitoring of electrical machines , 1987 .

[30]  Alison Carling,et al.  Introducing neural networks , 1992 .

[31]  Bo-Suk Yang,et al.  Combination of independent component analysis and support vector machines for intelligent faults diagnosis of induction motors , 2007, Expert Syst. Appl..

[32]  Giorgio Dalpiaz,et al.  Effectiveness and Sensitivity of Vibration Processing Techniques for Local Fault Detection in Gears , 2000 .