Hybrid dynamic classifier for drift-like fault diagnosis in a class of hybrid dynamic systems: Application to wind turbine converters
作者： Houari Toubakh , Moamar Sayed-Mouchaweh
DOI: 10.1016/J.NEUCOM.2015.07.073
关键词:
摘要: Hybrid dynamic systems (HDS) combine both discrete and continuous dynamics. Discretely controlled (DCCS) is an important class of HDS in which the system switches between several modes response to control events issued by a controller. Their dynamics depend on mode is. Wind turbine converters are example DCCS. Faults may impact significantly availability production performance wind turbines. These faults can occur as gradual abnormal change values parameters describing mode. In this case, they entail drift operating conditions until failure takes over completely. Detecting early stage allows reducing power losses well unavailability maintenance costs. However, be observed only when where described affected active. Consequently, paper proposes approach based use hybrid classifier able monitor normal converter impacted parametric fault. This keeping useful patterns representative therefore detect it its stage.
elsevier.com
sci-hub.se 参考文章(45)
Indrė Žliobaitė, Combining Time and Space Similarity for Small Size Learning under Concept Drift ISMIS '09 Proceedings of the 18th International Symposium on Foundations of Intelligent Systems. pp. 412- 421 ,(2009) , 10.1007/978-3-642-04125-9_44
Biqing Wu, Michael Roemer, Frank Lewis, George Vachtsevanos, Andrew Hess, Intelligent Fault Diagnosis and Prognosis for Engineering Systems ,(2006)
Alexey Tsymbal, Seppo Puuronen, Bagging and Boosting with Dynamic Integration of Classifiers Principles of Data Mining and Knowledge Discovery. pp. 116- 125 ,(2000) , 10.1007/3-540-45372-5_12
Ryan N. Lichtenwalter, Nitesh V. Chawla, Adaptive methods for classification in arbitrarily imbalanced and drifting data streams knowledge discovery and data mining. ,vol. 5669, pp. 53- 75 ,(2009) , 10.1007/978-3-642-14640-4_5
J. M. Schumacher, Schaft A. J. van der, An Introduction to Hybrid Dynamical Systems ,(1999)
Dang-Hoan Tran, Automated Change Detection and Reactive Clustering in Multivariate Streaming Data arXiv: Databases. ,(2013)
Andrew Kusiak, Wenyan Li, The prediction and diagnosis of wind turbine faults Renewable Energy. ,vol. 36, pp. 16- 23 ,(2011) , 10.1016/J.RENENE.2010.05.014
Xiangyang You, Weijuan Zhang, Fault Diagnosis of Frequency Converter in Wind Power System Based on SOM Neural Network Procedia Engineering. ,vol. 29, pp. 3132- 3136 ,(2012) , 10.1016/J.PROENG.2012.01.453
Bruno Sielly Jales Costa, Plamen Parvanov Angelov, Luiz Affonso Guedes, Real-Time Fault Detection Using Recursive Density Estimation Journal of Control, Automation and Electrical Systems. ,vol. 25, pp. 428- 437 ,(2014) , 10.1007/S40313-014-0128-4
Houari Toubakh, Moamar Sayed-Mouchaweh, Eric Duviella, Advanced Pattern Recognition Approach for Fault Diagnosis of Wind Turbines international conference on machine learning and applications. ,vol. 2, pp. 368- 373 ,(2013) , 10.1109/ICMLA.2013.150