Machine Learning Applications for a Wind Turbine Blade under Continuous Fatigue Loading

Abstract:

Structural health monitoring (SHM) systems will be one of the leading factors in the successful establishment of wind turbines in the energy arena. Detection of damage at an early stage is a vital issue as blade failure would be a catastrophic result for the entire wind turbine. In this study the SHM analysis will be based on experimental measurements of vibration analysis, extracted of a 9m CX-100 blade under fatigue loading. For analysis, machine learning techniques utilised for failure detection of wind turbine blades will be applied, like non-linear Neural Networks, including Auto-Associative Neural Network (AANN) and Radial Basis Function (RBF) networks models.

• Periodical: Key Engineering Materials (Volume 588)
• Pages: 166-174
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.588.166
• Online since: October 2013
• Authors: Nikolaos Dervilis, M. Choi, Ifigeneia Antoniadou, K.M. Farinholt, S.G. Taylor, Rob J. Barthorpe, G. Park, Charles R. Farrar, Keith Worden
• Keywords: Auto-Associative Neural Networks, Damage Detection, Fatigue Test, Novelty Analysis, Radial Basis Function Networks, Wind Turbine Blade

References

[1] B. D. Agarwal, L. J. Broutman and K. Chandrashekhara, Analysis and performance of fibre composites, Wiley, 2006.

[2] Deraemaeker, K. Worden, New trends in vibration based structural health monitoring, CISM Courses and Lectures, Vol.520, Springer-Verlag, 2010.

[3] K. Worden, G. Manson, N. R. Fieller, Damage detection using outlier analysis, Journal of Sound and Vibration, 229, 647–667, 1999.

DOI: 10.1006/jsvi.1999.2514

[4] C. M. Bishop, Neural networks for pattern recognition, Oxford University Press, 1995.

[5] C. M. Bishop, Pattern recognition and machine learning, Springer Press, 2006.

[6] M. A. Kramer, Nonlinear principal component analysis using auto-associative neural networks. AIChE Journal, 37(2):233–243, 1991.

DOI: 10.1002/aic.690370209

[7] K. Worden, Structural fault detection using a novelty measure, Journal of Sound and Vibration, 201(1), pp.85-101, 1997.

DOI: 10.1006/jsvi.1996.0747

[8] L. Tarassenko, A. Nairac, N. Townsend, I. Buxton, Z. Cowley, Novelty detection for the identification of abnormalities, International Journal of Systems Science, 31(11), pp.1427-1439, 2000.

DOI: 10.1080/00207720050197802

[9] H. Sohn, K. Worden, C.F. Farrar, Novelty detection under changing environmental conditions, SPIE's Eighth Annual International Symposium on Smart Structures and Materials, Newport Beach, CA. (LA-UR-01-1894), 2001.

DOI: 10.1117/12.434110

[10] N. Dervilis, R. Barthorpe, I. Antoniadou, W. J. Staszewski, K. Worden, Damage detection in carbon composite material typical of wind turbine blades using Auto-Associative Neural Networks, SPIE's Annual International Symposium on Smart Structures and Materials, 8348, 2012.

DOI: 10.1117/12.914710

[11] M. Scholz and R. Vig´ario. Nonlinear PCA: a new hierarchical approach. In M. Verleysen, editor, Proceedings ESANN, pages 439–444, 2002.

[12] Bourlard, H., & Kamp, Y., Auto-association by multilayer perceptrons and singular value decomposition. Biological Cybernetics, 59, 291–294, 1988.

DOI: 10.1007/bf00332918

[13] Cottrell, G. W., & Munro, P., Principal component analysis of images via back propagation. In Proceedings of the Society of Photo-Optical Instrumentation Engineers. Cambridge, MA, 1988.

[14] N. Japkowicz, S.J. Hanson, M.A. Gluck, Nonlinear autoassociation is not equivalent to PCA, Neural Computation 12, 531-545, Massachusetts Institute of Technology, 2000.

DOI: 10.1162/089976600300015691

[15] G. Manson, K. Worden, D. J. Allman. Experimental validation of a structural health monitoring methodology: Part III. Novelty detection on an aircraft wing, Journal of Sound and Vibration, 259 , 345–363, 2003.

DOI: 10.1006/jsvi.2002.5167

[16] P. Filzmoser, A multivariate outlier detection method, Proceedings of the 7th International Conference on Computer Data Analysis and Modeling, Minsk, Belarus,18-22, 2004.

[17] N. M. M. Maia, J. M. M Silva, Theoretical and experimental modal analysis, Research Studies Press, 1998.

[18] G. Manson, K.Worden, D. J. Allman, Experimental validation of a structural health monitoring methodology: Part II. Novelty detection on an aircraft wing, Journal of Sound and Vibration. 259, 345–363, 2003.

DOI: 10.1006/jsvi.2002.5167

[19] K. Worden, G. Manson, D. J. Allman, Experimental validation of a structural health monitoring methodology: Part I. Novelty detection on a laboratory structure, Journal of Sound and Vibration, 259, 323–343, 2003.

DOI: 10.1006/jsvi.2002.5168

[20] Stuart G. Taylor et al., Full-scale fatigue tests of CX-100 wind turbine blades. Part II: analysis, SPIE's Annual International Symposium on Smart Structures and Materials, 8348, 2012.

DOI: 10.1117/12.917493

[21] Kevin M. Farinholt et al., Full-scale fatigue tests of CX-100 wind turbine blades. Part I: testing, SPIE's Annual International Symposium on Smart Structures and Materials, 8343, 2012.

DOI: 10.1117/12.917493

[22] N Dervilis et al., Novelty detection applied to vibration data from a CX-100 wind turbine blade under fatigue loading, J. Phys.: Conf. Ser. 382 012047, 2012.

DOI: 10.1088/1742-6596/382/1/012047

[23] Ian T. Nabkey, Netlab algorithms for pattern recognition, Springer, 2004.