Artificial Neural Networks for Structural Health Monitoring of Helicopter Harsh Landings

Abstract:

The aim of the current paper is to explore fuselage monitoring possibilities trough the usage of Artificial Neural Networks (ANNs), trained by the use of numerical models, during harsh landing events. A harsh landing condition is delimited between the usual operational conditions and a crash event. Helicopter structural damage due to harsh landings is generally less severe than damage caused by a crash but may lead to unscheduled maintenance events, involving costs and idle times. Structural Health Monitoring technologies, currently used in many application fields, aim at the continuous detection of damage that may arise, thereby improving safety and reducing maintenance idle times by the disposal of a ready diagnosis. A landing damage database can be obtained with relatively little effort by the usage of a numerical model. Simulated data are used to train various ANNs considering the landing parameter values as input. The influence of both the input and output noise on the system performances were taken into account. Obtained outputs are a general classification between damaged and undamaged conditions, based on a critical damage threshold, and the reconstruction of the fuselage damage state.

• Periodical: Applied Mechanics and Materials (Volume 390)
• Pages: 192-197
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.390.192
• Online since: August 2013
• Authors: Giorgio Vallone, Claudio Sbarufatti, Andrea Manes, Marco Giglio
• Keywords: Artificial Neural Network (ANN), Harsh Landing, SHM

References

[1] M. Giglio e A. Manes, «Crack propagation on helicopter panel: experimental test and analysis, » Engineering Fracture Mechanics, vol. 75, pp.866-879, (2008).

DOI: 10.1016/j.engfracmech.2007.02.024

[2] M. Giglio, A. Manes, M. Fossati, U. Mariani e C. Giani, «Comparison of fatigue crack propagation behaviour of Al 20124 and Al - Li 8090 Helicopter fuselage panels, » Journal of Testing and evaluation, vol. 38, n. 1, pp.73-82, (2010).

DOI: 10.1520/jte101909

[3] T. DeFiore e R. P. Micklos, «Encyclopedia of Structural Health Monitoring, » (2009).

[4] C. M. Bishop, Neural Networks and Pattern Recognition, Oxford University Press, (1995).

[5] C. Sbarufatti and A. M. a. M. Giglio, Sensor network optimization for damage detection on aluminium stiffened helicopter panels, in Proc. of the 4th Int. Conf. on Computational Methods for Coupled Problems in Science and Eng., (2011).

[6] G. Vallone, A. Manes e M. Giglio, «Parametric analysis of helicopter tail damage during harsh landing events, » in International Crashworthiness Conference, ICRASH 2012, Milano, (2012).

[7] F. Viganò, A. Manes and M. Giglio, Investigation on the Fatigue Life of an AI 8090 Helicopter Riveted T-Joint, Journal of Aircraft, vol. 48, no. 1, pp.315-323, (2011).

DOI: 10.2514/1.c031117

[8] A. Manes, M. Giglio and F. Viganò, Effect of riveting process parameters on the local stress field of a T-joint, International Journal of Mechanical Sciences, vol. 53, no. 12, pp.1039-1049, (2011).

DOI: 10.1016/j.ijmecsci.2011.07.013

[9] C. Sbarufatti, A. Manes e M. Giglio, «Advanced stochastic fem-based Artificial Neural Network for crack damage detection, » in Proc. of the 4th Int. Conf. on Computational Methods for Coupled Problems in Science and Eng., (2011).

[10] R. E. Pinckert e P. A. Kozel, «Improved Fatigue Life Tracking Procedures for Navy Aircraft Structures, » (1983).

DOI: 10.2514/6.1983-805

[11] M. H. Hassoun, Fundamentals of Artificial Neural Networks, MIT Press, (1995).