Identifying Health Status of Wind Turbines by Using Self Organizing Maps and Interpretation-Oriented Post-Processing Tools

Background: Identifying the health status of wind turbines becomes critical to reduce the impact of failures on generation costs (between 25–35%). This is a time-consuming task since a human expert has to explore turbines individually. Methods: To optimize this process, we present a strategy based on Self Organizing Maps, clustering and a further grouping of turbines based on the centroids of their SOM clusters, generating groups of turbines that have similar behavior for subsystem failure. The human expert can diagnose the wind farm health by the analysis of a small each group sample. By introducing post-processing tools like Class panel graphs and Traffic lights panels, the conceptualization of the clusters is enhanced, providing additional information of what kind of real scenarios the clusters point out contributing to a better diagnosis. Results: The proposed approach has been tested in real wind farms with different characteristics (number of wind turbines, manufacturers, power, type of sensors, ...) and compared with classical clustering. Conclusions: Experimental results show that the states healthy, unhealthy and intermediate have been detected. Besides, the operational modes identified for each wind turbine overcome those obtained with classical clustering techniques capturing the intrinsic stationarity of the data.

[1]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Miguel A. Sanz-Bobi,et al.  Behavior Anomaly Indicators Based on Reference Patterns—Application to the Gearbox and Electrical Generator of a Wind Turbine , 2018 .

[3]  Lutgarde M. C. Buydens,et al.  Self- and Super-organizing Maps in R: The kohonen Package , 2007 .

[4]  Alejandro Blanco-M.,et al.  Impact of target variable distribution type over the regression analysis in wind turbine data , 2017, 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI).

[5]  John E. Moody,et al.  Data Visualization and Feature Selection: New Algorithms for Nongaussian Data , 1999, NIPS.

[6]  T. Caliński,et al.  A dendrite method for cluster analysis , 1974 .

[7]  Teuvo Kohonen,et al.  The 'neural' phonetic typewriter , 1988, Computer.

[8]  F. Fleuret Fast Binary Feature Selection with Conditional Mutual Information , 2004, J. Mach. Learn. Res..

[9]  Jarkko Venna,et al.  Analysis and visualization of gene expression data using Self-Organizing Maps , 2002, Neural Networks.

[10]  Bart Baesens,et al.  Failure prediction with self organizing maps , 2006, Expert Syst. Appl..

[11]  Li Zhao,et al.  Application of SOM neural network in fault diagnosis of wind turbine , 2015 .

[12]  J. H. Ward Hierarchical Grouping to Optimize an Objective Function , 1963 .

[13]  Karina Gibert,et al.  Post-processing: Bridging the gap between modelling and effective decision-support. The profile assessment grid in human behaviour , 2013, Mathematical and computer modelling.

[14]  Lior Rokach,et al.  Data Mining And Knowledge Discovery Handbook , 2005 .

[15]  Christian D. Klose,et al.  Self-organizing maps for geoscientific data analysis: geological interpretation of multidimensional geophysical data , 2006 .

[16]  Yong Shi,et al.  A Modified Clustering Method Based on Self-Organizing Maps and Its Applications , 2012, ICCS.

[17]  Melody Y. Kiang,et al.  Extending the Kohonen self-organizing map networks for clustering analysis , 2002 .

[18]  Gianluca Bontempi,et al.  On the Use of Variable Complementarity for Feature Selection in Cancer Classification , 2006, EvoWorkshops.

[19]  Karina Gibert,et al.  aTLP: A color-based model of uncertainty to evaluate the risk of decisions based on prototypes , 2015, AI Commun..

[20]  Karina Gibert,et al.  ASSISTING THE END-USER IN THE INTERPRETATION OF PROFILES FOR DECISION SUPPORT. AN APPLICATION TO WASTEWATER TREATMENT PLANTS , 2012 .

[21]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[22]  Lina Bertling,et al.  An Approach for Condition-Based Maintenance Optimization Applied to Wind Turbine Blades , 2010, IEEE Transactions on Sustainable Energy.

[23]  Miquel Sànchez-Marrè,et al.  A survey on pre-processing techniques: Relevant issues in the context of environmental data mining , 2016, AI Commun..

[24]  Mohammad Khalilia,et al.  Topology Preservation in Fuzzy Self-Organizing Maps , 2013, WCSC.

[25]  Belén Carro,et al.  Classification and Clustering of Electricity Demand Patterns in Industrial Parks , 2012 .

[26]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[27]  Fionn Murtagh,et al.  Methods of Hierarchical Clustering , 2011, ArXiv.

[28]  Jouko Lampinen,et al.  Overtraining and model selection with the self-organizing map , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[29]  Aleks Jakulin Machine Learning Based on Attribute Interactions , 2005 .

[30]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[31]  Karina Gibert,et al.  Knowledge Discovery on the response to neurorehabilitation treatment of patients with Traumatic Brain Injury through an AI&Stats and graphical hybrid methodology , 2008, CCIA.

[32]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Qing He,et al.  A SCADA data based anomaly detection method for wind turbines , 2016, 2016 China International Conference on Electricity Distribution (CICED).

[34]  Zhi-Hua Zhou,et al.  SOM Ensemble-Based Image Segmentation , 2004, Neural Processing Letters.

[35]  David McMillan,et al.  Quantification of Condition Monitoring Benefit for Offshore Wind Turbines , 2007 .

[36]  Alfred Ultsch,et al.  U *-Matrix : a Tool to visualize Clusters in high dimensional Data , 2004 .

[37]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[38]  Yong Wang,et al.  Conditional Mutual Information‐Based Feature Selection Analyzing for Synergy and Redundancy , 2011, ETRI Journal.

[39]  Karina Gibert,et al.  Pre and Postprocessing in KLASS , 2008 .

[40]  Andrés Bustillo,et al.  An SVM-Based Solution for Fault Detection in Wind Turbines , 2015, Sensors.

[41]  P. Rousseeuw Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .