Artificial neural network based on wavelet transform and feature extraction for a wind turbine diagnosis system

This paper presents a Wavelet Transform (WT) based Artificial Neural Network (ANN) input data pre-processing scheme and outlines the results of localized rotor angular speed defect of a wind turbine system by employing this proposed methodology. The methodology consists of calculating Daubechies 4-order (DAUB-4) dilation WTs with the Multi-Resolution Analysis (MRA) of the data, and then extracting predominant wavelet coefficients distributed to certain levels of these WTs using the Parseval's theorem. The features extracted from the dominant wavelet coefficients are used as inputs to ANN classifier to evaluate its performance. The simulation results show that the backpropagation network trained with a reasonably small number of training sets is able to recognize and classify signals of residues efficiently and can achieve high accuracy rate under various test cases.

[1]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[2]  A. Y. Chikhani,et al.  Power quality detection and classification using wavelet-multiresolution signal decomposition , 1999 .

[3]  S. N. Singh,et al.  AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network , 2012, IEEE Transactions on Sustainable Energy.

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

[5]  Witold Kinsner,et al.  Wavelet modelling of transients in power systems , 1997, IEEE WESCANEX 97 Communications, Power and Computing. Conference Proceedings.

[6]  J. Jonkman,et al.  Definition of a 5-MW Reference Wind Turbine for Offshore System Development , 2009 .

[7]  Silvio Simani.  Application of a Data-Driven Fuzzy Control Design to a Wind Turbine Benchmark Model , 2012, Adv. Fuzzy Syst..

[8]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[9]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[10]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[11]  Shen Yan-xia,et al.  Fault diagnosis for wind turbine gearbox based on wavelet analysis , 2012, 2012 24th Chinese Control and Decision Conference (CCDC).

[12]  C. Aubrun,et al.  Fault detection in wind turbine system using wavelet transform: Multi-resolution analysis , 2015, 2015 IEEE 12th International Multi-Conference on Systems, Signals & Devices (SSD15).

[13]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[14]  Silvio Simani,et al.  Data—Driven Approach for Wind Turbine Actuator and Sensor Fault Detection and Isolation , 2011 .

[15]  Yanyang Zi,et al.  Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals , 2016 .

[16]  Suzanne Lesecq,et al.  Fault Isolation Based on Wavelets Transform , 2007 .

[17]  C. Aubrun,et al.  Qualitative diagnosis of wind turbine system based on wavelet transform , 2014, 2014 15th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA).

[18]  Wenyi Liu,et al.  Wind turbine fault diagnosis based on Morlet wavelet transformation and Wigner-Ville distribution , 2010 .

[19]  Kathryn E. Johnson,et al.  Wind turbine fault detection and fault tolerant control - An enhanced benchmark challenge , 2013, 2013 American Control Conference.

[20]  Sandy Butterfield,et al.  Feasibility of Floating Platform Systems for Wind Turbines: Preprint , 2004 .

[21]  Joao P. S. Catalao,et al.  Short-term wind power forecasting in Portugal by neural networks and wavelet transform , 2011 .

[22]  Peter Fogh Odgaard,et al.  Wavelet Based Feed Forward Wind Gust Control of Wind Turbines , 2013 .

[23]  Peter Fogh Odgaard,et al.  Observer Based Detection of Sensor Faults in Wind Turbines , 2009 .

[24]  Peter Tavner,et al.  Condition monitoring and fault diagnosis of a wind turbine synchronous generator drive train , 2009 .