Dictionary learning approach to monitoring of wind turbine drivetrain bearings

Condition monitoring is central to the efficient operation of wind farms due to the challenging operating conditions, rapid technology development and large number of aging wind turbines. In particular, predictive maintenance planning requires the early detection of faults with few false positives. Achieving this type of detection is a challenging problem due to the complex and weak signatures of some faults, particularly the faults that occur in some of the drivetrain bearings. Here, we investigate recently proposed condition monitoring methods based on unsupervised dictionary learning using vibration data recorded over 46 months under typical industrial operations. Thus, we contribute novel test results and real world data that are made publicly available. The results of former studies addressing condition monitoring tasks using dictionary learning indicate that unsupervised feature learning is useful for diagnosis and anomaly detection purposes. However, these studies are based on small sets of labeled data from test rigs operating under controlled conditions that focus on classification tasks, which are useful for quantitative method comparisons but gives little insight into how useful these approaches are in practice. In this study, dictionaries are learned from gearbox vibrations in six different turbines, and the dictionaries are subsequently propagated over a few years of monitoring data when faults are known to occur. We perform the experiment using two different sparse coding algorithms to investigate if the algorithm selected affects the features of abnormal conditions. We calculate the dictionary distance between the initial and propagated dictionaries and find the time periods of abnormal dictionary adaptation starting six months before a drivetrain bearing replacement and one year before the resulting gearbox replacement.

[1]  Sanjay H Upadhyay,et al.  A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings , 2016 .

[2]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[3]  Yixiang Huang,et al.  Adaptive feature extraction using sparse coding for machinery fault diagnosis , 2011 .

[4]  Rémi Gribonval,et al.  Learning Co-Sparse Analysis Operators With Separable Structures , 2015, IEEE Transactions on Signal Processing.

[5]  Pierre Vandergheynst,et al.  A low complexity Orthogonal Matching Pursuit for sparse signal approximation with shift-invariant dictionaries , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Jin Chen,et al.  Detection and diagnosis of bearing faults using shift-invariant dictionary learning and hidden Markov model , 2016 .

[7]  Ashley Crowther,et al.  Sources of time‐varying contact stress and misalignments in wind turbine planetary sets , 2011 .

[8]  S. J. Lacey,et al.  An Overview of Bearing Vibration Analysis , 2008 .

[9]  Fredrik Sandin,et al.  Dictionary learning with equiprobable matching pursuit , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[10]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[11]  Mrityunjay Kumar,et al.  Sparse Image and Signal Processing: Wavelets, Curvelets, Morphological Diversity, by Jean-Luc Starck, Fionn Murtagh, and Jalal M. Fadili , 2007 .

[12]  Michael Elad,et al.  From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images , 2009, SIAM Rev..

[13]  Jerker Delsing,et al.  Exploratory analysis of acoustic emissions in steel using dictionary learning , 2016, 2016 IEEE International Ultrasonics Symposium (IUS).

[14]  Nadège Bouchonneau,et al.  A review of wind turbine bearing condition monitoring: State of the art and challenges , 2016 .

[15]  Haifeng Tang,et al.  Sparse representation based latent components analysis for machinery weak fault detection , 2014 .

[16]  Fredrik Sandin,et al.  Towards zero-configuration condition monitoring based on dictionary learning , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[17]  H.O.A. Ahmed,et al.  Intelligent condition monitoring method for bearing faults from highly compressed measurements using sparse over-complete features , 2018 .

[18]  Kjersti Engan,et al.  Learned dictionaries for sparse image representation: properties and results , 2011, Optical Engineering + Applications.

[19]  Han Zhang,et al.  Compressed sensing based on dictionary learning for extracting impulse components , 2014, Signal Process..

[20]  Mayorkinos Papaelias,et al.  Condition monitoring of wind turbines: Techniques and methods , 2012 .

[21]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[22]  Michael Elad,et al.  Theoretical Foundations of Deep Learning via Sparse Representations: A Multilayer Sparse Model and Its Connection to Convolutional Neural Networks , 2018, IEEE Signal Processing Magazine.

[23]  Fredrik Sandin,et al.  Online feature learning for condition monitoring of rotating machinery , 2017, Eng. Appl. Artif. Intell..

[24]  Stéphane Mallat,et al.  A Wavelet Tour of Signal Processing - The Sparse Way, 3rd Edition , 2008 .

[25]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[26]  Michael Elad,et al.  Sparse and Redundant Representations - From Theory to Applications in Signal and Image Processing , 2010 .

[27]  Michael S. Lewicki,et al.  Efficient auditory coding , 2006, Nature.

[28]  Michael S. Lewicki,et al.  Efficient Coding of Time-Relative Structure Using Spikes , 2005, Neural Computation.

[29]  Yann LeCun,et al.  Convolutional Matching Pursuit and Dictionary Training , 2010, ArXiv.

[30]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[31]  S. M. Muyeen,et al.  Methods for Advanced Wind Turbine Condition Monitoring and Early Diagnosis: A Literature Review , 2018 .

[32]  Miao He,et al.  Wind turbine planetary gearbox feature extraction and fault diagnosis using a deep-learning-based approach , 2019 .

[33]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[34]  W. Y. Liu,et al.  A review on wind turbine noise mechanism and de-noising techniques , 2017 .

[35]  Robert B. Randall,et al.  Rolling element bearing diagnostics—A tutorial , 2011 .

[36]  Kim Albertsson,et al.  FPGA prototype of machine learning analog-to-feature converter for event-based succinct representation of signals , 2013, 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

[37]  Mike E. Davies,et al.  Gradient Pursuits , 2008, IEEE Transactions on Signal Processing.

[38]  Tianshuai Liu,et al.  Shift invariant sparse coding ensemble and its application in rolling bearing fault diagnosis , 2015 .