Modeling and Prediction of Gearbox Faults With Data-Mining Algorithms

A data-driven approach for analyzing faults in wind turbine gearbox is developed and tested. More specifically, faults in a ring gear are predicted in advance. Time-domain statistical metrics, such as jerk, root mean square (RMS), crest factor (CF), and kurtosis, are investigated to identify faulty components of a wind turbine. The components identified are validated with the fast Fourier transformation (FFT) of vibration data. Fifty neural networks (NNs) with different parameter settings are trained to obtain the best performing model. Models based on original vibration data, and transformed jerk data are constructed. The jerk model based on multisensor data outperforms the other models and therefore is used for testing and validation of previously unseen data. Short-term predictions of up to 15 time intervals, each representing 0.1 s, are performed. The prediction accuracy varies from 91.68% to 94.78%.

[1]  Miguel A. Sanz-Bobi,et al.  SIMAP: Intelligent System for Predictive Maintenance: Application to the health condition monitoring of a windturbine gearbox , 2006, Comput. Ind..

[2]  Liuchen Chang,et al.  Cogging torque of permanent magnet electric machiens: An overview , 2009, 2009 Canadian Conference on Electrical and Computer Engineering.

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

[4]  Yuji Matsumoto,et al.  A Boosting Algorithm for Classification of Semi-Structured Text , 2004, EMNLP.

[5]  Andrew Kusiak,et al.  Constraint-Based Control of Boiler Efficiency: A Data-Mining Approach , 2007, IEEE Transactions on Industrial Informatics.

[6]  H. Zheng,et al.  GEAR FAULT DIAGNOSIS BASED ON CONTINUOUS WAVELET TRANSFORM , 2002 .

[7]  Luis Romeral,et al.  Fault Detection in Induction Machines Using Power Spectral Density in Wavelet Decomposition , 2008, IEEE Transactions on Industrial Electronics.

[8]  Andrew Kusiak,et al.  Combustion efficiency optimization and virtual testing: a data-mining approach , 2006, IEEE Transactions on Industrial Informatics.

[9]  C. G. Broyden.  The Convergence of a Class of Double-rank Minimization Algorithms 2. The New Algorithm , 1970 .

[10]  Marko Robnik-Sikonja,et al.  An adaptation of Relief for attribute estimation in regression , 1997, ICML.

[11]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[12]  D. Goldfarb.  A family of variable-metric methods derived by variational means , 1970 .

[13]  David Siegel,et al.  A Systematic Methodology for Gearbox Health Assessment and Fault Classification , 2009 .

[14]  Larry Nazareth,et al.  A family of variable metric updates , 1977, Math. Program..

[15]  Yahya H. Zweiri,et al.  A three-term backpropagation algorithm , 2003, Neurocomputing.

[16]  Sung-Hoon Ahn,et al.  Condition monitoring and fault detection of wind turbines and related algorithms: A review , 2009 .

[17]  Marc Thomas,et al.  "TALAF" and "THIKAT" as innovative time domain indicators for tracking BALL bearings , 2006 .

[18]  DeLiang Wang,et al.  Unsupervised Learning: Foundations of Neural Computation , 2001, AI Mag..

[19]  Jose Mathew,et al.  Bearing Signature Analysis as a Medium for Fault Detection: A Review , 2008 .

[20]  Peter Tavner,et al.  Review of condition monitoring of rotating electrical machines , 2008 .

[21]  Peter W. Tse,et al.  Wavelet Analysis and Envelope Detection For Rolling Element Bearing Fault Diagnosis—Their Effectiveness and Flexibilities , 2001 .

[22]  R. Fletcher,et al.  A New Approach to Variable Metric Algorithms , 1970, Comput. J..

[23]  Andrew Kusiak,et al.  Data-mining-based system for prediction of water chemistry faults , 2006, IEEE Transactions on Industrial Electronics.

[24]  D. Shanno.  Conditioning of Quasi-Newton Methods for Function Minimization , 1970 .

[25]  Lianfen Qian,et al.  Regularized Radial Basis Function Networks: Theory and Applications , 2002, Technometrics.

[26]  Wenxian Yang,et al.  Cost-Effective Condition Monitoring for Wind Turbines , 2010, IEEE Transactions on Industrial Electronics.

[27]  Brian D. Larder,et al.  An Analysis of HUMS Vibration Diagnostic Capabilities , 1997 .

[28]  C. G. Broyden.  The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations , 1970 .

[29]  Andrew Kusiak,et al.  Analysis of wind turbine vibrations based on SCADA data , 2010 .

[30]  Wei Li,et al.  Real-Time Simulation of a Wind Turbine Generator Coupled With a Battery Supercapacitor Energy Storage System , 2010, IEEE Transactions on Industrial Electronics.