A Comparative Study of Impact Localisation in Composite Structures Using Neural Networks under Environmental and Operational Variations

Abstract:

In this study we compare the effectiveness of the Normalised Smoothed Envelope (NSET) method for Artificial Neural Network (ANN) based impact localisation under simulated environmental and operational conditions with respect to other ANN based localisation methods developed by other studies. It is shown that when the testing and training impact case is the same, most studies give comparably good accuracy of localisation irrespective of feature extraction method or structure geometry. However, when the testing and training impact cases are not the same, only the NSET method is able to negate the variations caused by various impact cases and provide good localisation accuracy for an ANN trained using only a single impact case thus allowing for smaller training data set size requirements and increasing feasibility for real life application.

• Periodical: Key Engineering Materials (Volume 827)
• Pages: 410-415
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.827.410
• Online since: December 2019
• Authors: Aldyandra Hami Seno*, M.H. Aliabadi
• Keywords: Composite Material, Environmental Conditions, Impact Localisation, Operational Conditions, Passive Sensing, Structural Health Monitoring

References

[1] Abrate S. Impact on composite structures. Cambridge university press; (2005).

[2] Fu H, Sharif Khodaei Z, Aliabadi MHF. An Event-Triggered Energy-Efficient Wireless Structural Health Monitoring System for Impact Detection in Composite Airframes. IEEE Internet of Things Journal. 2019;6:1183–1192.

DOI: 10.1109/jiot.2018.2867722

[3] Seno AH, Sharif Khodaei Z, Aliabadi MHF. Passive sensing method for impact localisation in composite plates under simulated environmental and operational conditions. Mechanical Systems and Signal Processing. 2019;129:20–36.

DOI: 10.1016/j.ymssp.2019.04.023

[4] Sharif Khodaei Z, Ferri Aliabadi MH. Impact Detection and Identification with Piezoceramic Sensors: Passive Sensing. Computational and Experimental Methods in Structures [Internet]. WORLD SCIENTIFIC (EUROPE); 2018 [cited 2018 Apr 11]. p.215–265. Available from: http://www.worldscientific.com/doi/abs/10.1142/9781786343932_0007.

DOI: 10.1142/9781786343932_0007

[5] Sharif Khodaei Z, Ghajari M, Aliabadi MH. Determination of impact location on composite stiffened panels. Smart Materials and Structures. 2012;21:105026.

DOI: 10.1088/0964-1726/21/10/105026

[6] Yue N, Sharif Khodaei Z. Assessment of Impact Detection Techniques for Aeronautical Application: ANN vs. LSSVM. Journal of Multiscale Modelling. 2016;07:1640005.

DOI: 10.1142/s1756973716400059

[7] Morse L, Sharif Khodaei Z, Aliabadi MH. Reliability based impact localization in composite panels using Bayesian updating and the Kalman filter. Mechanical Systems and Signal Processing. 2018;99:107–128.

DOI: 10.1016/j.ymssp.2017.05.047

[8] Jang B-W, Lee Y-G, Kim J-H, et al. Real-time impact identification algorithm for composite structures using fiber Bragg grating sensors: REAL-TIME IMPACT IDENTIFICATION ALGORITHM FOR COMPOSITE STRUCTURES. Struct. Control Health Monit. 2012;19:580–591.

DOI: 10.1002/stc.1492

[9] Park CY, Jang B-W, Kim JH, et al. Bird strike event monitoring in a composite UAV wing using high speed optical fiber sensing system. Composites Science and Technology. 2012;72:498–505.

DOI: 10.1016/j.compscitech.2011.12.008

[10] Park CY, Kim JH, Jun S-M, et al. Localizations and force reconstruction of low-velocity impact in a composite panel using optical fiber sensors. Advanced Composite Materials. 2012;21:357–369.

DOI: 10.1080/09243046.2012.736346

[11] Sung D-U, Oh J-H, Kim C-G, et al. Impact Monitoring of Smart Composite Laminates Using Neural Network and Wavelet Analysis. Journal of Intelligent Material Systems and Structures. 2000;11:180–190.

DOI: 10.1106/n5e7-m37y-3mar-2kfh

[12] Fu T, Zhang Z, Liu Y, et al. Development of an artificial neural network for source localization using a fiber optic acoustic emission sensor array. Structural Health Monitoring. 2015;14:168–177.

DOI: 10.1177/1475921714568406

[13] Schindler PM, May RG, Claus RO, et al. Location of impacts on composite panels by embedded fiber optic sensors and neural network processing. In: Spillman, Jr. WB, editor. San Diego, CA; 1995 [cited 2019 May 26]. p.481–489. Available from: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=996158.

DOI: 10.1117/12.207698

[14] Caprino G, Lopresto V, Leone C, et al. Acoustic emission source location in unidirectional carbon-fiber-reinforced plastic plates with virtually trained artificial neural networks. J. Appl. Polym. Sci. 2011;122:3506–3513.

DOI: 10.1002/app.34758

[15] Mallardo V, Aliabadi MH, Khodaei ZS. Optimal sensor positioning for impact localization in smart composite panels. Journal of Intelligent Material Systems and Structures. 2013;24:559–573.

DOI: 10.1177/1045389x12464280