Skip to main content
SpringerLink
Log in

Study on Prediction of Compression Performance of Composite Laminates After Impact Based on Convolutional Neural Networks

  • Published:
Applied Composite Materials Aims and scope Submit manuscript

Abstract

This paper proposed a method for predicting composite laminates’ compressive residual strength after impact based on convolutional neural networks. Laminates made by M21E/IMA prepreg were used to introduce low-velocity impact damage and construct a non-destructive testing image dataset. The dataset images characterized the impact damage details, including dents, delamination, and matrix cracking. The convolution kernel automatically extracted and identified these complex features that could be used for classification. The model took the images as input and compressive residual strength labels as output for iterative training, and the final prediction accuracy reached more than 90%, the highest 96%. This method introduced overall damage into the model in the form of images utilizing convolution, which can quickly and accurately predicted laminates’ compression performance after impact.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

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

  1. Talreja, R., Phan, N.: Assessment of damage tolerance approaches for composite aircraft with focus on barely visible impact damage. Compos. Struct. 219, 1–7 (2019). https://doi.org/10.1016/j.compstruct.2019.03.052

    Article  Google Scholar 

  2. Shah, S.Z.H., Karuppanan, S., Megat-Yusoff, P.S.M., Sajid, Z.: Impact resistance and damage tolerance of fiber reinforced composites: A review. Compos. Struct. 217, 100–121 (2019). https://doi.org/10.1016/j.compstruct.2019.03.021

    Article  Google Scholar 

  3. Rhead, A.T., Butler, R., Baker, N.: Analysis and Compression Testing of Laminates Optimised for Damage Tolerance. Appl. Compos. Mater. 18, 85–100 (2011). https://doi.org/10.1007/s10443-010-9153-z

    Article  Google Scholar 

  4. Polimeno, U., Meo, M., Almond, D.P., Angioni, S.L.: Detecting Low Velocity Impact Damage in Composite Plate Using Nonlinear Acoustic/Ultrasound Methods. Appl. Compos. Mater. 17, 481–488 (2010). https://doi.org/10.1007/s10443-010-9168-5

    Article  Google Scholar 

  5. Meo, M., Polimeno, U., Zumpano, G.: Detecting Damage in Composite Material Using Nonlinear Elastic Wave Spectroscopy Methods. Appl. Compos. Mater. 15, 115–126 (2008). https://doi.org/10.1007/s10443-008-9061-7

    Article  CAS  Google Scholar 

  6. Sun, W., Guan, Z., Li, Z.: Simulation of Low Velocity Impact Induced Inter- and Intra-Laminar Damage of Composite Beams Based on XFEM. Appl. Compos. Mater. 24, 1459–1477 (2017). https://doi.org/10.1007/s10443-017-9598-4

    Article  CAS  Google Scholar 

  7. Ji, Z., Guan, Z., Li, Z.: A Progressive Damage Model for Predicting Permanent Indentation and Impact Damage in Composite Laminates. Appl. Compos. Mater. 24, 1029–1048 (2017). https://doi.org/10.1007/s10443-016-9572-6

    Article  Google Scholar 

  8. Tan, R., Xu, J., Sun, W., Liu, Z., Guan, Z., Guo, X.: Relationship Between Matrix Cracking and Delamination in CFRP Cross-Ply Laminates Subjected to Low Velocity Impact. Materials. 12, 3990 (2019). https://doi.org/10.3390/ma12233990

    Article  CAS  Google Scholar 

  9. Ouyang, T., Bao, R., Sun, W., Guan, Z., Tan, R.: A fast and efficient numerical prediction of compression after impact (CAI) strength of composite laminates and structures. Thin-Walled Struct. 148, 106588 (2020). https://doi.org/10.1016/j.tws.2019.106588

    Article  Google Scholar 

  10. He, W., Guan, Z., Li, X., Liu, D.: Prediction of permanent indentation due to impact on laminated composites based on an elasto-plastic model incorporating fiber failure. Compos. Struct. 96, 232–242 (2013). https://doi.org/10.1016/j.compstruct.2012.08.054

    Article  Google Scholar 

  11. Aoki, Y., Suemasu, H., Ishikawa, T.: Damage propagation in CFRP laminates subjected to low velocity impact and static indentation. Adv. Compos. Mater. 16, 45–61 (2007). https://doi.org/10.1163/156855107779755318

    Article  CAS  Google Scholar 

  12. Topac, O.T., Gozluklu, B., Gurses, E., Coker, D.: Experimental and computational study of the damage process in CFRP composite beams under low-velocity impact. Compos. Pt. A-Appl. Sci. Manuf. 92, 167–182 (2017). https://doi.org/10.1016/j.compositesa.2016.06.023

    Article  CAS  Google Scholar 

  13. Hyung Yun Choi, Chang, F.K.: A Model for Predicting Damage in Graphite/Epoxy Laminated Composites Resulting from Low-Velocity Point Impact. J. Compos. Mater. 26, 2134–2169 (1992). https://doi.org/10.1177/002199839202601408

  14. Yang, L., Wu, Z., Gao, D., Liu, X.: Microscopic damage mechanisms of fibre reinforced composite laminates subjected to low velocity impact. Comput. Mater. Sci. 111, 148–156 (2016). https://doi.org/10.1016/j.commatsci.2015.09.039

    Article  Google Scholar 

  15. Ding, J.C., Xu, W.: Determination of mode I interlaminar fracture toughness of composite by a wedge-insert double cantilever beam and the nonlinear J integral. Compos. Sci. Technol. 206, 108674 (2021). https://doi.org/10.1016/j.compscitech.2021.108674

    Article  CAS  Google Scholar 

  16. Bouvet, C., Rivallant, S., Barrau, J.J.: Low velocity impact modeling in composite laminates capturing permanent indentation. Compos. Sci. Technol. 72, 1977–1988 (2012). https://doi.org/10.1016/j.compscitech.2012.08.019

    Article  CAS  Google Scholar 

  17. Hongkarnjanakul, N., Bouvet, C., Rivallant, S.: Validation of low velocity impact modelling on different stacking sequences of CFRP laminates and influence of fibre failure. Compos. Struct. 106, 549–559 (2013). https://doi.org/10.1016/j.compstruct.2013.07.008

    Article  Google Scholar 

  18. Bull, D.J., Spearing, S.M., Sinclair, I.: Investigation of the response to low velocity impact and quasi-static indentation loading of particle-toughened carbon-fibre composite materials. Compos. Pt. A-Appl. Sci. Manuf. 74, 38–46 (2015). https://doi.org/10.1016/j.compositesa.2015.03.016

    Article  CAS  Google Scholar 

  19. Sztefek, P., Olsson, R.: Tensile stiffness distribution in impacted composite laminates determined by an inverse method. Compos. Pt. A-Appl. Sci. Manuf. 39, 1282–1293 (2008). https://doi.org/10.1016/j.compositesa.2007.10.005

    Article  CAS  Google Scholar 

  20. Sztefek, P., Olsson, R.: Nonlinear compressive stiffness in impacted composite laminates determined by an inverse method. Compos. Pt. A-Appl. Sci. Manuf. 40, 260–272 (2009). https://doi.org/10.1016/j.compositesa.2008.12.002

    Article  CAS  Google Scholar 

  21. Craven, R., Sztefek, P., Olsson, R.: Investigation of impact damage in multi-directional tape laminates and its effect on local tensile stiffness. Compos. Sci. Technol. 68, 2518–2525 (2008). https://doi.org/10.1016/j.compscitech.2008.05.008

    Article  CAS  Google Scholar 

  22. Suemasu, H., Ichiki, M.: Analytical study on low compressive strength of composite laminates with impact damage. Compos. Struct. 104, 169–175 (2013). https://doi.org/10.1016/j.compstruct.2013.04.017

    Article  Google Scholar 

  23. Nyman, T., Bredberg, A., Schon, J.: Equivalent Damage and Residual Strength for Impact Damaged Composite Structures. J. Reinf. Plast. Compos. 19(6), 428–448 (2000). https://doi.org/10.1177/073168440001900601

    Article  CAS  Google Scholar 

  24. Romano, F., Di Caprio, F., Mercurio, U.: Compression after Impact Analysis of Composite Panels and Equivalent Hole Method. Procedia Engineering. 167, 182–189 (2016). https://doi.org/10.1016/j.proeng.2016.11.686

    Article  Google Scholar 

  25. Puhui, C., Zhen, S., Junyang, W.: A New Method for Compression After Impact Strength Prediction of Composite Laminates. J. Compos Mater. 36, 589–610 (2002). https://doi.org/10.1177/0021998302036005497

    Article  Google Scholar 

  26. Tan, W., Falzon, B.G., Chiu, L.N.S., Price, M.: Predicting low velocity impact damage and Compression-After-Impact (CAI) behaviour of composite laminates. Compos. Pt. A-Appl. Sci. Manuf. 71, 212–226 (2015). https://doi.org/10.1016/j.compositesa.2015.01.025

    Article  CAS  Google Scholar 

  27. Maio, L., Monaco, E., Ricci, F., Lecce, L.: Simulation of low velocity impact on composite laminates with progressive failure analysis. Compos. Struct. 103, 75–85 (2013). https://doi.org/10.1016/j.compstruct.2013.02.027

    Article  Google Scholar 

  28. Horton, P.E., Whitehead, R.: Damage Tolerance of Composites, Vol. I and II, Air Force Wright Aeronautical Laboratories, AFWAL TR 87, 3030 (1988)

  29. Hosur, M.V., Murthy, C., Ramurthy, T.S.: Compression after impact testing of carbon fiber reinforced plastic laminates. J. Compos. Tech. Res. 21(2), 51–64 (1999)

    Article  CAS  Google Scholar 

  30. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539

    Article  CAS  Google Scholar 

  31. Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybernetics. 36, 193–202 (1980). https://doi.org/10.1007/BF00344251

    Article  CAS  Google Scholar 

  32. LeCun, Y. and Bengio, Y.: Convolutional Networks for Images, Speech, and Time-Series. In: Arbib, M.A., Eds., The Handbook of Brain Theory and Neural Networks, MIT Press, Cambridge (1995)

  33. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM. 60, 84–90 (2012).https://doi.org/10.1145/3065386

  34. Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556  [cs]. (2015)

  35. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going Deeper with Convolutions. arXiv:1409.4842 [cs]. (2014)

  36. Ioffe, S., Szegedy, C.: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv:1502.03167 [cs]. (2015)

  37. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception Architecture for Computer Vision. arXiv:1512.00567 [cs]. (2015)

  38. Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv:1602.07261 [cs]. (2016)

  39. He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs]. (2015)

  40. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely Connected Convolutional Networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2261–2269. IEEE, Honolulu, HI (2017)

  41. Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-Excitation Networks. arXiv:1709.01507 [cs]. (2019)

  42. Agrawal, A., Choudhary, A.: Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science. APL Mater. 4(5), 053208 (2016)

    Article  Google Scholar 

  43. Li, D., Li, Y., Zhou, J., Zhao, Z.: A Novel Method to Improve Temperature Uniformity in Polymer Composites Microwave Curing Process through Deep Learning with Historical Data. Appl. Compos. Mater. 27, 1–17 (2020). https://doi.org/10.1007/s10443-019-09791-5

    Article  CAS  Google Scholar 

  44. Erkan, Ö., Işık, B., Çiçek, A., Kara, F.: Prediction of Damage Factor in end Milling of Glass Fibre Reinforced Plastic Composites Using Artificial Neural Network. Appl. Compos. Mater. 20, 517–536 (2013). https://doi.org/10.1007/s10443-012-9286-3

    Article  Google Scholar 

  45. Yang, C., Kim, Y., Ryu, S., Gu, G.X.: Prediction of composite microstructure stress-strain curves using convolutional neural networks. Mater. Des. 189, 108509 (2020). https://doi.org/10.1016/j.matdes.2020.108509

    Article  Google Scholar 

  46. Nasiri, M.R., Mahjoob, M.J., Aghakasiri, A.: Damage Detection in a Composite Plate Using Modal Analysis and Artificial Intelligence. Appl. Compos. Mater. 18, 513–520 (2011). https://doi.org/10.1007/s10443-011-9231-x

    Article  Google Scholar 

  47. Xu, D., Liu, P.F., Li, J.G., Chen, Z.P.: Damage mode identification of adhesive composite joints under hygrothermal environment using acoustic emission and machine learning. Compos. Struct. 211, 351–363 (2019). https://doi.org/10.1016/j.compstruct.2018.12.051

    Article  Google Scholar 

  48. Zenzen, R., Khatir, S., Belaidi, I., Le Thanh, C., Abdel Wahab, M.: A modified transmissibility indicator and Artificial Neural Network for damage identification and quantification in laminated composite structures. Compos. Struct. 248, 112497 (2020). https://doi.org/10.1016/j.compstruct.2020.112497

    Article  Google Scholar 

  49. Abueidda, D.W., Almasri, M., Ammourah, R., Ravaioli, U., Jasiuk, I.M., Sobh, N.A.: Prediction and optimization of mechanical properties of composites using convolutional neural networks. Compos. Struct. 227, 111264 (2019). https://doi.org/10.1016/j.compstruct.2019.111264

    Article  Google Scholar 

  50. Rong, Q., Wei, H., Huang, X., Bao, H.: Predicting the effective thermal conductivity of composites from cross sections images using deep learning methods. Compos. Sci. Technol. 184, 107861 (2019). https://doi.org/10.1016/j.compscitech.2019.107861

    Article  CAS  Google Scholar 

  51. Bang, H.T., Park, S., Jeon, H.: Defect identification in composite materials via thermography and deep learning techniques. Compos. Struct. 246, 112405 (2020). https://doi.org/10.1016/j.compstruct.2020.112405

    Article  Google Scholar 

  52. Califano, A.: Damage Detection in Composites by Artificial Neural Networks Trained by Using in Situ Distributed Strains. Appl. Compos. Mater. 27, 657–671 (2020).https://doi.org/10.1007/s10443-020-09829-z

  53. Ripley, B.D.: Pattern recognition and neural networks. Cambridge University Press, Cambridge, New York (1996)

    Book  Google Scholar 

  54. Heaton, J.: Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning. Genet Program Evolvable Mach. 19, 305–307 (2018). https://doi.org/10.1007/s10710-017-9314-z

    Article  Google Scholar 

  55. Yarotsky, D.: Error bounds for approximations with deep ReLU networks. Neural Netw. 94, 103–114 (2017)

    Article  Google Scholar 

  56. Boureau, Y.L., Bach, F., LeCun, Y., Ponce, J.: Learning mid-level features for recognition. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 2559–2566. IEEE, San Francisco, CA, USA (2010)

  57. Khosravani, M.R.: Composite Materials Manufacturing Processes. AMM. 110(116), 1361–1367 (2011). https://doi.org/10.4028/www.scientific.net/AMM.110-116.1361

  58. Narnhofer, M., Schledjewski, R., Mitschang, P., Perko, L.: Simulation of the Tape-Laying Process for Thermoplastic Matrix Composites. Adv. Polym. Technol. 32, E705–E713 (2013). https://doi.org/10.1002/adv.21312

    Article  CAS  Google Scholar 

  59. ASTM D7136/D7136M-12: Standard Test Method for Measuring the Damage Resistance of a Fiber-Reinforced Polymer Matrix Composite to a Drop-Weight Impact Event, ASTM International, West Conshohocken, PA, 19428–2959, USA (2012)

  60. SAE International: CMH-17 Composite Materials Handbook volume 3. polymer matrix composites mate-rials usage, design, and analysis. Warrendale, PA, USA (2012)

  61. ASTM D7137/D7137M-12: Standard Test Method for Compressive Residual Strength Properties of Damaged Polymer Matrix Composite Plates, ASTM International, West Conshohocken, PA, 19428–2959, USA (2012).

  62. Aymerich, F., Dore, F., Priolo, P.: Simulation of multiple delaminations in impacted cross-ply laminates using a finite element model based on cohesive interface elements. Composi. Sci. Technol. 69, 1699–1709 (2009). https://doi.org/10.1016/j.compscitech.2008.10.025

    Article  CAS  Google Scholar 

  63. Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861–874 (2006). https://doi.org/10.1016/j.patrec.2005.10.010

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Aeronautic Science and Engineering, Beihang University, Beijing, China

    Fengyang Jiang, Zhidong Guan, Xiaodong Wang, Zengshan Li & Riming Tan

  2. Department of Mechanical and Aerospace Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong

    Cheng Qiu

Authors
  1. Fengyang Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhidong Guan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaodong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zengshan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Riming Tan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Cheng Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaodong Wang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, F., Guan, Z., Wang, X. et al. Study on Prediction of Compression Performance of Composite Laminates After Impact Based on Convolutional Neural Networks. Appl Compos Mater 28, 1153–1173 (2021). https://doi.org/10.1007/s10443-021-09904-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10443-021-09904-z

Keywords

Search

Navigation