Abstract
This study presents an artificial neural network (ANN) model for predicting the residual strength of carbon fibre reinforced composites (CFRCs) after low-velocity impact. First, a finite element (FE) model was developed addressing intra-laminar damage and inter-laminar delamination, to estimate low-velocity impact (LVI) and compression-after-impact (CAI) responses of CFRCs. The FE results in terms of load–displacement curves, damage patterns, and residual strengths were found to be essentially in agreement with those by experiments. An ANN model was developed using back-propagation learning algorithm and was trained using the FE results to establish a nonlinear relationship between LVI parameters (i.e. impact energy and impactor diameter) and CFRC residual strength. Twelve sets of additional CAI simulations were carried out to validate the proposed ANN-based residual strength prediction model. A good agreement was achieved between the residual strengths predicted by ANN model and the FE results with errors less than 5%, demonstrating the effectiveness of the present ANN model. The established ANN-based model can effectively reduce the experimental costs and computational time.
Similar content being viewed by others
Data Availability
The data that support the findings of this study are available from the corresponding author upon reasonable request.
References
Shi, Y., Swait, T., Soutis, C.: Modelling damage evolution in composite laminates subjected to low velocity impact. Compos. Struct. 94(9), 2902–2913 (2012)
Prentzias, V., Tsamasphyros, G.: Simulation of low velocity impact on CFRP aerospace structures: simplified approaches, numerical and experimental results. Appl. Compos. Mater. 26(3), 835–856 (2019)
Wu, Z.Y., Ying, Z.P., Hu, X.D., et al.: Low-velocity impact performance of hybrid 3D carbon/glass woven orthogonal composite: Experiment and simulation. Compos. B Eng. 196, 108098 (2020)
Qiu, A., Fu, K., Lin, W., et al.: Modelling low-speed drop-weight impact on composite laminates. Mater. Des. 60, 520–531 (2014)
Davies, G.A.O., Olsson, R.: Impact on composite structures. Aeronaut. J. 108(1089), 541–563 (2004)
Chen, Y., Hou, S., Fu, K., et al.: Low-velocity impact response of composite sandwich structures: modelling and experiment. Compos. Struct. 168, 322–334 (2017)
Schwab, M., Todt, M., Wolfahrt, M., et al.: Failure mechanism based modelling of impact on fabric reinforced composite laminates based on shell elements. Compos. Sci. Technol. 128, 131–137 (2016)
Thorsson, S.I., Waas, A.M., Rassaian, M., et al.: Low-velocity impact predictions of composite laminates using a continuum shell based modeling approach part A: Impact study. Int. J. Solids Struct. 185–200 (2018)
Cheng, Z., Xiong, J.: Progressive damage behaviors of woven composite laminates subjected to LVI, TAI and CAI. Chinese J. Aeronaut. 33(10), 2807–2823 (2020)
Patel, S., Vusa, V.R., Soares, C.G., et al.: Crashworthiness analysis of polymer composites under axial and oblique impact loading. Int. J. Mech. Sci. 156, 221–234 (2019)
Lou, X., Cai, H., Yu, P., et al.: Failure analysis of composite laminate under low-velocity impact based on micromechanics of failure. Compos. Struct. 163, 238–247 (2017)
Sun, X.C., Hallett, S.R.: Failure mechanisms and damage evolution of laminated composites under compression after impact (CAI): Experimental and numerical study. Compos. A Appl. Sci. Manuf. 104, 41–59 (2018)
Debski, H., Rozylo, P., Gliszczynski, A.: Effect of low-velocity impact damage location on the stability and post-critical state of composite columns under compression. Compos. Struct. 184, 883–893 (2018)
Sun, W., Guan, Z., Ouyang, T., et al.: Effect of stiffener damage caused by low velocity impact on compressive buckling and failure modes of T-stiffened composite panels. Compos. Struct. 184, 198–210 (2018)
Liu, H.B,. Liu, J., Dear, J.P., et al.: Effects of impactor geometry on the low-velocity impact behaviour of fibre-reinforced composites: an experimental and theoretical investigation. Appl. Compos. Mater. 27, 533–553 (2020)
Liu, D., Bai, R., Lei, Z., et al.: Experimental and numerical study on compression-after-impact behavior of composite panels with foam-filled hat-stiffener. Ocean Eng. 198(15), 106991 (2020)
Aryal, B., Morozov, E.V., Shankar, K., et al.: Effects of ballistic impact damage on mechanical behaviour of composite honeycomb sandwich panels. J. Sandw. Struct. Mater. (2020)
Moumen, A.E., Tarfaoui, M., Hassoon, O.H., et al.: Experimental study and numerical modelling of low velocity impact on laminated composite reinforced with thin film made of carbon nanotubes. Appl. Compos. Mater. 25(2), 309–320 (2018)
Liu, H., Falzon, B.G., Tan, W.: Predicting the Compression-After-Impact (CAI) strength of damage-tolerant hybrid unidirectional/woven carbon-fibre reinforced composite laminates. Compos. A Appl. Sci. Manuf. 105, 189–202 (2018)
Liu, H., Falzon, B.G., Tan, W.: Experimental and numerical studies on the impact response of damage-tolerant hybrid unidirectional/woven carbon-fibre reinforced composite laminates. Compos. B Eng. 136, 101–118 (2018)
Caminero, M.A., García-Moreno, I., Rodríguez, G.P.: Experimental study of the influence of thickness and ply-stacking sequence on the compression after impact strength of carbon fibre reinforced epoxy laminates. Polym. Testing 66, 360–370 (2018)
González, E.V., Maimí, P., Camanho, P.P., et al.: Simulation of drop-weight impact and compression after impact tests on composite laminates. Compos. Struct. 94(11), 3364–3378 (2012)
Rivallant, S., Bouvet, C., Hongkarnjanakul, N.: Failure analysis of CFRP laminates subjected to compression after impact: FE simulation using discrete interface elements. Compos. A Appl. Sci. Manuf. 55, 83–93 (2013)
Habibi, M., Laperriere, L., Hassanabadi, H.M., et al.: Influence of low-velocity impact on residual tensile properties of nonwoven flax/epoxy composite. Compos. Struct. 186, 175–182 (2018)
Tuo, H., Lu, Z., Ma, X., et al.: An experimental and numerical investigation on low-velocity impact damage and compression-after-impact behavior of composite laminates. Compos. B Eng. 167, 329–341 (2019)
Zhang, Z., Friedrich, K.: Artificial neural networks applied to polymer composites: A review. Compos. Sci. Techonol. 63(14), 2029–2044 (2003)
Fan, H., Wang, H.: Predicting the open-hole tensile strength of composite plates based on probabilistic neural network. Appl. Compos. Mater. 21(6), 827–840 (2014)
Altabey, W.A., Noori, M.: Fatigue life prediction for carbon fibre/epoxy laminate composites under spectrum loading using two different neural network architectures. International Journal of Sustainable Materials and Structural Systems 3(1), 53–78 (2017)
Stamopoulos, A.G., Tserpes, K.I., Dentsoras, A.J.: Quality assessment of porous CFRP specimens using X-ray Computed Tomography data and Artificial Neural Networks. Compos. Struct. 192(10), 327–335 (2018)
Balokas, G., Czichon, S., Rolfes, R., et al.: Neural network assisted multiscale analysis for the elastic properties prediction of 3D braided composites under uncertainty. Compos. Struct. 183(1), 550–562 (2018)
Vineela, M.G., Dave, A., Chaganti, P.K., et al.: Artificial neural network based prediction of tensile strength of hybrid composites. Materials Today: Proceedings 5(9), 19908–19915 (2018)
Chen, G., Wang, H., Bezold, A., et al.: Strengths prediction of particulate reinforced metal matrix composites (PRMMCs) using direct method and artificial neural network. Compos. Struct. 223(17), 110951 (2019)
Hashin, Z.: Failure criteria for unidirectional fiber composites. J. Appl. Mech. 47(2), 329–334 (1980)
Hashin, Z., Rotem, A.: A fatigue failure criterion for fiber reinforced materials. J. Compos. Mater. 7(4), 448–464 (1973)
ASTM D7137/D7137M - 12 standard test method for compressive residual strength properties of damaged polymer matrix composite.
ASTM D7136/D7136M-15 standard test method for measuring the damage resistance of a fiber-reinforced polymer matrix composite to a drop-weight impact event.
Camanho, P.P., Dávila, C.G.: Mixed-mode decohesion finite elements for the simulation of delamination in composite materials. NASA/TM, No. 211737 (2002)
Faggiani, A., Falzon, B.G.: Predicting low-velocity impact damage on a stiffened composite panel. Compos. A Appl. Sci. Manuf. 41(6), 737–749 (2010)
Jumahat, A., Soutis, C., Hodzic, A.: A graphical method predicting the compressive strength of toughened unidirectional composite laminates. Appl. Compos. Mater. 18(1), 65–83 (2011)
Shahid, I., Chang, F.K.: An accumulative damage model for tensile and shear failures of laminated composite plates. J. Compos. Mater. 29(7), 926–981 (1995)
Pinho, S.T., Robinson, P., Iannucci, L.: Fracture toughness of the tensile and compressive fibre failure modes in laminated composites. Compos. Sci. Technol. 66(13), 2069–2079 (2006)
Shi, Y., Soutis, C.: Modelling low velocity impact induced damage in composite laminates. Mech. Adv. Mater. Mod. Process. 3(1), 14 (2017)
Schön, J.: Coefficient of friction of composite delamination surfaces. Wear 237(1), 77–89 (2000)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall, NJ (1999)
Demuth, H., Beale, M.: Neural network toolbox for the use with Matlab. User’s guide, version 4 The MathWorks (2002)
Hertz, J., Krogh, A., Palmer, R.G., et al.: Introduction to the theory of neural computation. Phys. Today 44, 70 (1991)
Barzegar, R., Sattarpour, M., Nikudel, M.R., et al.: Comparative evaluation of artificial intelligence models for prediction of uniaxial compressive strength of travertine rocks, case study: Azarshahr area, NW Iran. Model. Earth Syst. Environ. 2(2), 76 (2016)
Ochiai, K., Usui S.: Improved kick out learning algorithm with delta-bar-delta-bar rule, IEEE International Conference on Neural Networks. 269–274 (1993)
Sun, X.C., Hallett, S.R.: Barely visible impact damage in scaled composite laminates: experiments and numerical simulations. Int. J. Impact Eng. 109, 178–195 (2017)
Ouyang, T., Bao, R., Sun, W., et al.: A fast and efficient numerical prediction of compression after impact (CAI) strength of composite laminates and structures. Thin-Walled Struct. 148, 106588 (2020)
Pernas-Sánchez, J., Artero-Guerrero, J.A., Varas, D., et al.: Experimental analysis of ice sphere impacts on unidirectional carbon/epoxy laminates. Int. J. Impact Eng. 96, 1–10 (2016)
Liu, P.F., Liao, B.B., Jia, L.Y., et al.: Finite element analysis of dynamic progressive failure of carbon fiber composite laminates under low velocity impact. Compos. Struct. 149, 408–422 (2016)
Acknowledgements
The authors are grateful for the support from the Shanghai Pujiang Program (grant number: 19PJ1410000), the National Science Fund for Distinguished Young Scholars (grant number: 11625210), the Fund of State Key Laboratory for Strength and Vibration of Mechanical Structures (grant number: SV2019-KF-04), the Fund of National Postdoctoral Program for Innovative Talents (BX20200244), and the fellowship of China Postdoctoral Science Foundation (2020M671224).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
In this study, a minimum of two LVI/CAI tests were repeated for each impact energy to ensure the reliability of test data. Figure 18 compares CAI test reproducibility of the CFRCs subjected to initial 33 J LVI. It is clear in the Fig. 18 that two CFRCs showed similar impact damage pattern, compressive load–displacement responses, and peak compressive loads at failure.
Rights and permissions
About this article
Cite this article
Yang, B., Fu, K., Lee, J. et al. Artificial Neural Network (ANN)-Based Residual Strength Prediction of Carbon Fibre Reinforced Composites (CFRCs) After Impact. Appl Compos Mater 28, 809–833 (2021). https://doi.org/10.1007/s10443-021-09891-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10443-021-09891-1