Impact Detection on Composite Plates Based on Convolution Neural Network

Abstract:

This paper presents a novel Convolutional Neural Network (CNN) based metamodel for impact detection and characterization for a Structural Health Monitoring (SHM) application. The signals recorded by PZT sensors during various impact events on a composite plate is used as inputs to CNN to detect and locate impact events. The input of the metamodel consists of 2D images, constructed from the signals recorded from a network of sensors. The developed meta-model was then developed and tested on a composite plate. The results show that the CNN-based metamodel is capable of detecting impacts with more than 98% accuracy. In addition, the network was capable of detecting impacts in the other regions of the panel, which was not trained with but had similar geometric configuration. The accuracy in this case was also above 98%, showing the scalability of this method for large complex structures of repeating zones such as composite stiffened panel.

• Periodical: Key Engineering Materials (Volume 827)
• Pages: 476-481
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.827.476
• Online since: December 2019
• Authors: I. Tabian*, H. Fu, Zahra Sharif Khodaei
• Keywords: Machine Learning, Neural Network, Passive Sensing, PZT Sensors, SHM

References

[1] Ostachowicz, W. and A. Güemes, New trends in structural health monitoring. Vol. 542. 2013: Springer Science & Business Media.

[2] Aliabadi, M.H. and Z.S. Khodaei, Structural Health Monitoring for Advanced Composite Structures Computational and Experimental Methods in Structures, ed. M.H. Aliabadi; and Z.S. Khodaei. Vol. Volume 8. 2018: World Scientific Publishing Europe Ltd. 288.

DOI: 10.1142/q0114

[3] Fu, H., Z.S. Khodaei, and M.F. Aliabadi, An Event-Triggered Energy-Efficient Wireless Structural Health Monitoring System for Impact Detection in Composite Airframes. IEEE Internet of Things Journal, (2018).

DOI: 10.1109/jiot.2018.2867722

[4] Seno, A.H., Z.S. Khodaei, and M.F. Aliabadi, Passive sensing method for impact localisation in composite plates under simulated environmental and operational conditions. Mechanical Systems and Signal Processing, 2019. 129: pp.20-36.

DOI: 10.1016/j.ymssp.2019.04.023

[5] Morse, L., Z.S. Khodaei, and M. Aliabadi, Reliability based impact localization in composite panels using Bayesian updating and the Kalman filter. Mechanical Systems and Signal Processing, 2018. 99: pp.107-128.

DOI: 10.1016/j.ymssp.2017.05.047

[6] Ghajari, M., et al., Identification of impact force for smart composite stiffened panels. Smart Materials and Structures, 2013. 22(8): p.085014.

DOI: 10.1088/0964-1726/22/8/085014

[7] Sharif-Khodaei, Z., M. Ghajari, and M. Aliabadi, Determination of impact location on composite stiffened panels. Smart Materials and Structures, 2012. 21(10): p.105026.

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

[8] Fu, H., Z. Sharif-Khodaei, and M.F. Aliabadi, An energy-efficient cyber-physical system for wireless on-board aircraft structural health monitoring. Mechanical Systems and Signal Processing, 2019. 128: pp.352-368.

DOI: 10.1016/j.ymssp.2019.03.050

[9] Dafydd, I. and Z.S. Khodaei. Damage severity assessment in composite structures using ultrasonic guided waves with chirp excitation. in Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018. 2018. International Society for Optics and Photonics.

DOI: 10.1117/12.2299647

[10] Sharif Khodaei, Z. and M. Aliabadi, A Multi-Level Decision Fusion Strategy for Condition Based Maintenance of Composite Structures. Materials, 2016. 9(9): p.790.

DOI: 10.3390/ma9090790

[11] Bekas, D.G., Z. Sharif-Khodaei, and M.H.F. Aliabadi, An Innovative Diagnostic Film for Structural Health Monitoring of Metallic and Composite Structures. Sensors, 2018. Special issue (18, 2084).

DOI: 10.3390/s18072084

[12] Mallardo, V., M. Aliabadi, and Z. Sharif Khodaei, Optimal sensor positioning for impact localization in smart composite panels. Journal of Intelligent Material Systems and Structures, 2012: p. 1045389X12464280.

DOI: 10.1177/1045389x12464280

[13] Mallardo, V., Z. Sharif Khodaei, and F.M. Aliabadi, A Bayesian Approach for Sensor Optimisation in Impact Identification. Materials, 2016. 9(11): p.946.

DOI: 10.3390/ma9110946

[14] Yue, N. and Z.S. Khodaei, Assessment of Impact Detection Techniques for Aeronautical Application: ANN vs. LSSVM. Journal of Multiscale Modelling, 2016: p.1640005.

DOI: 10.1142/s1756973716400059

[15] Kang, F., et al., Concrete dam deformation prediction model for health monitoring based on extreme learning machine. Structural Control and Health Monitoring, 2017. 24(10): p. e1997.

DOI: 10.1002/stc.1997

[16] de Oliveira, M., et al., Use of savitzky–golay filter for performances improvement of SHM systems based on neural networks and distributed PZT sensors. Sensors, 2018. 18(1): p.152.

DOI: 10.3390/s18010152

[17] Khan, S. and T. Yairi, A review on the application of deep learning in system health management. Mechanical Systems and Signal Processing, 2018. 107: pp.241-265.

DOI: 10.1016/j.ymssp.2017.11.024

[18] Zhao, R., et al., Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 2019. 115: pp.213-237.

DOI: 10.1016/j.ymssp.2018.05.050

[19] de Oliveira, M., A. Monteiro, and J. Vieira Filho, A New Structural Health Monitoring Strategy Based on PZT Sensors and Convolutional Neural Network. Sensors, 2018. 18(9): p.2955.

DOI: 10.3390/s18092955

[20] Gu, J., et al., Recent advances in convolutional neural networks. Pattern Recognition, 2018. 77: pp.354-377.

[21] al., F.C.e. https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py. (2015).