Abstract
A common technique used to decrease a cost of wind turbine maintenance is a remote monitoring. Apart from the development of several advanced diagnostic methods for wind turbines there is a need to prepare an early warning tool which would work continuously in real-time and focus the attention on potentially dangerous cases. A research using the resonance neural networks made so far by the authors gave positive results. Systems based on the ART-2 networks were able to perform a classification of operational states of a horizontal axis wind turbine. In this paper the innovative idea of using the ART-2 network is applied to data from vertical axis wind turbines. The system, which were composed by ART-2 and new signal normalization procedures based on a stereographic projection, was implemented and tested. Simulations of a system operation showed that it is capable to perform an efficient state classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hameeda Z, Honga YS, Choa TM, Ahnb SH, Son CK (2009) Condition monitoring and fault detection of wind turbines and related algorithms: a review. Renew Sustain Energy Rev 13:1–39
Shuhui L, Wunsch DC, O’Hair E, Giesselmann MG (2001) Comparative analysis of regression and artificial neural network models for wind turbine power curve estimation. J SolEnergy Eng 123:327–332
Kim YS (2010) Performance evaluation for classification methods: a comparative simulation study. Expert Syst Appl 37:2292–2306
Barszcz T, Bielecki A, Wójcik M (2010) ART-type artificial neural networks applications for classification of operational states in wind turbines. Lect Notes Artif Intell 6114:11–18
Barszcz T, Bielecki A, Wójcik M, Bielecka M (2013) “ART-2 artificial neural networks applications for classification of vibration signals and operational states of wind turbines for intelligent monitoring”. Diagnostyka 14(4):21–26
Barszcz T, Bielecka M, Bielecki A, Wójcik M (2011) Wind turbines states classification by a fuzzy-ART neural network with a stereographic projection as a signal normalization. Lect Notes Comput Sci 6594:225–234
Carpenter GA, Grossberg S (1987) ART2: self-organization of stable category recognition codes for analog input pattern. Appl Opt 26:4919–4930
Shieh MD, Yan W, Chen CH (2008) Soliciting customer requirements for product redesign based on picture sorts and ART2 neural network. Expert Syst Appl 34:194–204
Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Graph Image Process 37:54–115
Gancarzewicz J (1987) Differential geometry. PWN, Warszawa (in Polish)
Barszcz T, Bielecki A, Wójcik M (2013) Vibration signals processing by cellular automata for wind turbines intelligent monitoring. Diagnostyka 14(2):31–36
Barszcz T, Bielecka M, Bielecki A, Wójcik M (2012) Wind speed modelling using Weierstrass function fitted by a genetic algorithm. J Wind Eng Ind Aerodyn 109:68–78
Bielecki A, Barszcz T, Wójcik M (2014) Modelling of a chaotic load of wind turbines drivetrain. Mech Syst Signal Process. ISSN 0888-3270, http://dx.doi.org/10.1016/j.ymssp.2014.05.035
Bielecki A, Barszcz T, Wójcik M, Bielecka M (2014) Hybrid system of ART and RBF neural networks for classification of vibration signals and operational states of wind turbines. Lect Notes Comput Sci 8467:3–11
Acknowledgments
The paper was supported by the National Centre for Research and Development under grant no. WND-DEM-1-153/01
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Barszcz, T., Bielecki, A., Bielecka, M., Wójcik, M., Włuka, M. (2016). Vertical Axis Wind Turbine States Classification by an ART-2 Neural Network with a Stereographic Projection as a Signal Normalization. In: Chaari, F., Zimroz, R., Bartelmus, W., Haddar, M. (eds) Advances in Condition Monitoring of Machinery in Non-Stationary Operations. CMMNO 2014. Applied Condition Monitoring, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-319-20463-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-20463-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20462-8
Online ISBN: 978-3-319-20463-5
eBook Packages: EngineeringEngineering (R0)