Skip to main content
SpringerLink
Log in

A Neural Network Approach to Processing Photos of Carbon-Fiber-Reinforced Polymer Microstructures for Their Further Diagnostics

  • Published:
Polymer Science, Series D Aims and scope Submit manuscript

Abstract

A neural network approach to the segmentation of photos for carbon fiber reinforced polymer structures with the purpose of qualitative and quantitative fault analysis was considered. The object of study was carbon-fiber-reinforced polymer (CFRP) based on an epoxy binder. Such a composite material was molded with an organosilicon sealant additive, which acted as a “liquid” matrix. A method of formalizing the microstructure photo segmentation problem and a method of training a neural network were presented.

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.

REFERENCES

  1. S. L. Bazhenov, A. A. Berlin, A. A. Kul’kov, and V. G. Oshmyan, Polymer Composite Materials (Intellekt, Dolgoprudny, 2010) [in Russian].

  2. A. P. Petrova and G. V. Malysheva, Glues, Adhesive Binders, Adhesive Prepregs (VIAM, Moscow, 2017) [in Russian].

    Google Scholar 

  3. Reinforced Plastics, Ed. by G. S. Golovkin (Mosk. Aviats. Inst., Moscow, 1997) [in Russian].

    Google Scholar 

  4. V. A. Nelyub, M. E. Frantsev, and A. S. Borodulin, Technology for the Production of Small-Tonnage Vessels From Composite Materials (Mosk. Gos. Tekh. Univ., 2021) [in Russian].

    Google Scholar 

  5. Technology for the Production of Products and Integral Structures from Composite Materials in Mechanical Engineering, Ed. by A. G. Bratukhin, V. S. Bogolyubov, and O. S. Sirotkin (Gotika, Moscow, 2003) [in Russian].

    Google Scholar 

  6. P. P. Maung, T. L. Htet, and G. V. Malysheva, “Simulation and optimization of vacuum assisted resin infusion process for large-sized structures made of carbon fiber-reinforced plastic,” IOP Conf. Ser.: Mater. Sci. Eng. 709, 022041 (2020).

  7. E. A. Kosenko, N. I. Baurova, and V. A. Zorin, Nature-Like Materials and Structures in Mechanical Engineering: Monograph (Mosk. Avtomob. Dorozhn. Inst., 2020) [in Russian].

    Google Scholar 

  8. C. Yangyang and G. Malysheva, “Method for determining the rational regimes of curing determining the rational regimes of curing products from polymer composite materials,” Mater. Today: Proc. 11, 128–133 (2019).

    Article  CAS  Google Scholar 

  9. N. V. Bodrykh and G. V. Malysheva, “Repair of starter storage batteries,” Polym. Sci., Ser. D 3, 70–73 (2010).

    Google Scholar 

  10. L. P. Kobets, A. S. Borodulin, and G. V. Malysheva, “Study of microcapillary impregnation of carbon fiber by epoxy binder,” Fibre Chem. 48, 311–315 (2016).

    Article  CAS  Google Scholar 

  11. A. Yu. Konoplin and N. I. Baurova, “Hardness of the near-weld zone during contact spot welding of steels using an adhesive-weld technology,” Russ. Metall. 13, 1308–1311 (2016).

    Article  Google Scholar 

  12. N. I. Baurova, “A Method of imitational modeling that permits optimizing the properties of polymeric composite materials,” Polym. Sci., Ser. D 6, 265–268 (2013).

    CAS  Google Scholar 

  13. V. A. Nelyub, B. L. Gorberg, M. V. Grishin, A. A. Berlin, and G. V. Malysheva, “Properties and technology of applying metal coatings to carbon tape,” Fibre Chem. 50, 524–527 (2019).

    Article  CAS  Google Scholar 

  14. A. I. Rudskoi and N. I. Baurova, “Technological heredity during the production and operation of structural materials,” Russ. Metall. 13, 1378–1383 (2019).

    Article  Google Scholar 

  15. Mechanical Engineering Technology. Textbook for Univ., Ed. by A. M. Dal’skii, Vol. 1 (Mosk. Gos. Tekh. Univ., 1997) [in Russian].

    Google Scholar 

  16. E. A. Kosenko, A. V. Ostroukh, and N. I. Baurova, “Prospects of applying the neural-network modeling for estimating the structure and properties of polymer-composite materials with hybrid matrices,” Polym. Sci., Ser. D 15, 452–456 (2022).

    CAS  Google Scholar 

  17. Y. Hirose, K. Yamashita, and S. Hijiya, “Back-propagation algorithm which varies the number of hidden units,” Neural Networks 4, 61–66 (1991).

    Article  Google Scholar 

  18. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (MIT, 2016; DMK Press, 2018).

  19. https://github.com/milesial/Pytorch-UNet/. Accessed February 1, 2022.

  20. Cheng Ho Kei, Tai Yu-Wing, and Tang Chi-Keung, Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion (CVPR, 2021), pp. 21–34.

    Google Scholar 

  21. A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. Kalinin, “Albumentations: fast and flexible image augmentations,” Information 11, 125 (2020).

Download references

Author information

Authors and Affiliations

  1. Bauman Moscow State Technical University, 105005, Moscow, Russia

    D. S. Tikhonova, A. Yu. Abramochkin, A. S. Borodulin, V. A. Nelyub & G. V. Malysheva

Authors
  1. D. S. Tikhonova
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. Yu. Abramochkin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. A. S. Borodulin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. V. A. Nelyub
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. G. V. Malysheva
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to G. V. Malysheva.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by E. Glushachenkova

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tikhonova, D.S., Abramochkin, A.Y., Borodulin, A.S. et al. A Neural Network Approach to Processing Photos of Carbon-Fiber-Reinforced Polymer Microstructures for Their Further Diagnostics. Polym. Sci. Ser. D 16, 307–312 (2023). https://doi.org/10.1134/S1995421223020442

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1995421223020442

Keywords:

Search

Navigation