Open Access Open Access  Restricted Access Subscription Access

Artificial Neural Network (ANN)-Based Predictive Tool for Estimating Lightning Damage in Composites

DEVIN NIELSEN, TYLER LOTT, SOM DUTTA, JUHYEONG LEE

Abstract


In this study, three artificial neural network (ANN) models are developed with back propagation (BP) optimization algorithms to predict various lightning damage modes in carbon/epoxy laminates. The proposed ANN models use three input variables associated with lightning waveform parameters (i.e., the peak current amplitude, rising time, and decaying time) to predict fiber damage, matrix damage, and through-thickness damage in the composites. The data used for training and testing the networks was actual lightning damage data collected from peer-reviewed published literature. Various BP training algorithms and network architecture configurations (i.e., data splitting, the number of neurons in a hidden layer, and the number of hidden layers) have been tested to improve the performance of the neural networks. Among the various BP algorithms considered, the Bayesian regularization back propagation (BRBP) showed the overall best performance in lightning damage prediction. When using the BRBP algorithm, as expected, the greater the fraction of the collected data that is allocated to the training dataset, the better the network is trained. In addition, the optimal ANN architecture was found to have a single hidden layer with 20 neurons. The ANN models proposed in this work may prove useful in preliminary assessments of lightning damage and reduce the number of expensive experimental lightning tests.


DOI
10.12783/asc36/35819

Full Text:

PDF

References


Lee J. Experimental Studies and Finite Element Modeling of Lightning Damage to

Carbon/Epoxy Laminated and Stitched Composites. 2017.

Lee J, Lacy TE, Pittman CU. Lightning Mechanical Damage Prediction in Carbon/Epoxy

Laminates using Equivalent Air Blast Overpressure. Compos Part B Eng 2021;212:108649.

https://doi.org/10.1016/j.compositesb.2021.108649.

Hirano Y, Katsumata S, Iwahori Y, Todoroki A. Artificial Lightning Testing on

Graphite/Epoxy Composite Laminate. Compos Part A Appl Sci Manuf 2010;41:1461–70.

https://doi.org/10.1016/j.compositesa.2010.06.008.

Dong Q, Guo Y, Chen J, Yao X, Yi X, Ping L, et al. Influencing factor analysis based on

electrical-thermal-pyrolytic simulation of carbon fiber composites lightning damage.

Compos Struct 2016;140:1–10. https://doi.org/10.1016/j.compstruct.2015.12.033.

Kamiyama S, Hirano Y, Okada T, Ogasawara T. Lightning Strike Damage Behavior of

Carbon Fiber Reinforced Epoxy, Bismaleimide, and Polyetheretherketone Composites.

Compos Sci Technol 2018;161:107–14. https://doi.org/10.1016/j.compscitech.2018.04.009.

Sun J, Yao X, Tian X, Chen J, Wu Y. Damage Characteristics of CFRP Laminates Subjected

to Multiple Lightning Current Strike. Appl Compos Mater 2019;26:745–62.

https://doi.org/10.1007/s10443-018-9747-4.

Guo Y, Dong Q, Chen J, Yao X, Yi X, Jia Y. Comparison Between Temperature and

Pyrolysis Dependent Models to Evaluate the Lightning Strike Damage of Carbon Fiber

Composite Laminates. Compos Part A Appl Sci Manuf 2017;97:10–8.

https://doi.org/10.1016/j.compositesa.2017.02.022.

Gou J, Tang Y, Liang F, Zhao Z, Firsich D, Fielding J. Carbon Nanofiber Paper for

Lightning Strike Protection of Composite Materials. Compos Part B Eng 2010;41:192–8.

Feraboli P, Kawakami H. Damage of Carbon/Epoxy Composite Plates Subjected to

Mechanical Impact and Simulated Lightning. J Aircr 2010;47:999–1012.

https://doi.org/10.2514/1.46486.

Dong Q, Wan G, Ping L, Guo Y, Yi X, Jia Y. Coupled Thermal-Mechanical Damage Model

of Laminated Carbon Fiber/Resin Composite Subjected to Lightning Strike. Compos Struct

;206:185–93. https://doi.org/10.1016/J.COMPSTRUCT.2018.08.043.

Wang FS, Ji YY, Yu XS, Chen H, Yue ZF. Ablation Damage Assessment of Aircraft

Carbon Fiber/Epoxy Composite and its Protection Structures Suffered from Lightning Strike.

Compos Struct 2016;145:226–41.

Ogasawara T, Hirano Y, Yoshimura A. Coupled Thermal-Electrical Analysis for Carbon

Fiber/Epoxy Composites Exposed to Simulated Lightning Current. Compos Part A Appl Sci

Manuf 2010;41:973–81. https://doi.org/10.1016/j.compositesa.2010.04.001.

Feraboli P, Miller M. Damage Resistance and Tolerance of Carbon/Epoxy Composite

Coupons Subjected to Simulated Lightning Strike. Compos Part A Appl Sci Manuf

;40:954–67. https://doi.org/10.1016/j.compositesa.2009.04.025.

Hirano Y, Yokozeki T, Ishida Y, Goto T, Takahashi T, Qian D, et al. Lightning Damage

Suppression in a Carbon Fiber-Reinforced Polymer with a Polyaniline-Based Conductive

Thermoset Matrix. Compos Sci Technol 2016;127:1–7.

https://doi.org/10.1016/j.compscitech.2016.02.022.

Yin JJ, Chang F, Li SL, Yao XL, Sun JR, Xiao Y. Lightning Strike Ablation Damage

Influence Factors Analysis of Carbon Fiber/Epoxy Composite Based on Coupled Electrical-

Thermal Simulation. Appl Compos Mater 2016;24:1–18. https://doi.org/10.1007/s10443-

-9577-1.

Yamashita S, Sonehara T, Takahashi J, Kawabe K, Murakami T. Effect of Thin-Ply on

Damage Behaviour of Continuous and Discontinuous Carbon Fibre Reinforced

Thermoplastics Subjected to Simulated Lightning Strike. Compos Part A Appl Sci Manuf

;95:132–40. https://doi.org/10.1016/j.compositesa.2017.01.010.

Yang B, Fu K, Lee J, Li Y. Artificial Neural Network (ANN)-Based Residual Strength

Prediction of Carbon Fibre Reinforced Composites (CFRCs) After Impact. Appl Compos

Mater 2021:1–25. https://doi.org/10.1007/s10443-021-09891-1.

Muñoz R, Delgado S, González C, López-Romano B, Wang D, LLorca J. Modeling

Lightning Impact Thermo-Mechanical Damage on Composite Materials. Appl Compos

Mater 2014;21:149–64. https://doi.org/10.1007/s10443-013-9377-9.

Chen H, Wang FS, Ma XT, Yue ZF. The coupling mechanism and damage prediction of

carbon fiber/epoxy composites exposed to lightning current. Compos Struct 2018;203:436–

https://doi.org/10.1016/j.compstruct.2018.07.017.

Wang FS, Ding N, Liu ZQ, Ji YY, Yue ZF. Ablation Damage Characteristic and Residual

Strength Prediction of Carbon Fiber/Epoxy Composite Suffered from Lightning Strike.

Compos Struct 2014;117:222–33.

Lott T, Lee J, Dutta S. Optimal Design of Nanocomposite Material and Fabrication

Parameters Using Artificial Neural Network. Proc. 35th Am. Soc. Compos. Tech. Conf., vol.

, DEStech Publications; 2020. https://doi.org/10.12783/asc35/34905.

Lee J, Lacy TE, Pittman CU. Coupled Thermal Electrical and Mechanical Lightning

Damage Predictions to Carbon/Epoxy Composites During Arc Channel Shape Expansion.

Compos Struct 2021;255:112912. https://doi.org/10.1016/j.compstruct.2020.112912.

Demuth H, Beale M. Neural network toolbox for the use with Matlab. User’s guide, version

The MathWorks. 2002.

Patterson JC. Managing a Real-Time Massively-Parallel Neural Architecture 2012.

MathWorks. Deep Learning Toolbox 2021.

Lau ATC. GESD - A robust and effective technique for dealing with multiple outliers. Stand

News 2015;43:40–1.

Dixon BYWJ. Analysis of Extreme Values Author ( s ): W . J . Dixon Source : The Annals

of Mathematical Statistics , Vol . 21 , No . 4 ( Dec ., 1950 ), pp . 488-506 Published by :

Institute of Mathematical Statistics Stable URL : http://www.jstor.org/stable/2236602 .

;21:488–506.

Iglewicz B, Hoaglin DC. Volume 16: How to Detect and Handle Outliers", The ASQC Basic

References in Quality Control: Statistical Techniques. vol. 36. 1993.


Refbacks

  • There are currently no refbacks.