Journal of Materials Science

, Volume 50, Issue 1, pp 420–426 | Cite as

Formulation optimization for thermoplastic sizing polyetherimide dispersion by quantitative structure–property relationship: experiments and artificial neural networks

  • A. Malho Rodrigues
  • S. Franceschi
  • E. Perez
  • J.-C. Garrigues
Original Paper


The main function of a sizing in a composite is to fill interface between fibre and polymer matrix. This coating process contributes to increase adhesion between fibre and matrix, and therefore improve mechanical properties of the composites. The aim of this study was to optimize sizing formulations by identifying the experimental parameters influencing the particle size, distribution size and stability of various aqueous emulsions, used in the coating process of carbon fibres with polyetherimide as thermoplastic sizing polymer. A quantitative structure–property relationship (QSPR) method with artificial neural networks was used to determine the main parameters involved in the different formulation steps. The results indicated three recurrent parameters: stirring speed, surfactant concentration and type of reactor which control the particle size, stability and distribution size of the dispersions. With a reduced dataset constituted of 36 entries, this QSPR method was able to predict the stability of the aqueous dispersion of polymer and the particle size with an accuracy of 200 nm for an average diameter ranging from 330 to 2700 nm. The distribution size could be predicted with an accuracy of 0.047 for an experimental size distribution of 0.2.


Artificial Neural Network Carbon Fibre Aqueous Dispersion Photon Correlation Spectroscopy Short Carbon Fibre 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors would like to acknowledge Isabelle Giraud for her upstream work and MACOTHEC Unique Interministerial Fund for the financing of this project.


  1. 1.
    Marston C et al (1997) Measurement of stress concentration around fibre breaks in carbon-fibre/epoxy-resin composite tows. Compos Sci technol 57:913–923CrossRefGoogle Scholar
  2. 2.
    Marston C, Galiotis C (1998) On the failure of unidirectional carbon-epoxy composites Part I: the effect of fibre sizing upon filament fracture and damage evolution. J Mater Sci 33:5311–5325. doi: 10.1023/A:1004433930232 CrossRefGoogle Scholar
  3. 3.
    Broyles NS et al (1998) Fatigue performance of carbon fibre/vinyl ester composites: the effect of two dissimilar polymeric sizing agents. Polymer 39:3417–3424CrossRefGoogle Scholar
  4. 4.
    Chung DDL (1994) Carbon Fiber Composites. Butterworth-Heinemann, NewtonGoogle Scholar
  5. 5.
    Bergerat J-M et al. (2011) Novel stable aqueous dispersions of high performance thermoplastic polymer nanoparticles and their uses as film generating agents, US patent 20110300381 A1, Airbus operations S.A.S and Centre National de la Recherche Scientifique, USAGoogle Scholar
  6. 6.
    Giraud I et al (2013) Preparation of aqueous dispersion of thermoplastic sizing agent for carbon fiber by emulsion/solvent evaporation. Appl Surf Sci 266:94–99CrossRefGoogle Scholar
  7. 7.
    Cern A et al (2012) Quantitative structure - property relationship modeling of remote liposome loading of drugs. J Control Release 160:147–157CrossRefGoogle Scholar
  8. 8.
    Amani A et al (2008) Determination of factors controlling the particle size in nanoemulsions using Artificial Neural Networks. Eur J Pharm Sci 35:42–51CrossRefGoogle Scholar
  9. 9.
    Fan T et al (2004) Formulation Optimization of Paclitaxel Carried by PEGylated Emulsions based on Artificial Neural Network. Pharmaceut Res 21:1692–1697CrossRefGoogle Scholar
  10. 10.
    Herrmann J et al (2013) Development of a rheological prediction model for food suspensions and emulsions. J Food Eng 115:481–485CrossRefGoogle Scholar
  11. 11.
    Velten K, Reinicke R, Friedrich K (2000) Wear volume prediction with artificial neural networks. Tribol Int 33:731–736CrossRefGoogle Scholar
  12. 12.
    Zhang Z, Friedrich K, Velten K (2002) Prediction on tribological properties of short fibre composites using artificial neural networks. Wear 252:668–675CrossRefGoogle Scholar
  13. 13.
    Zhang Z, Klein P, Friedrich K (2002) Dynamic mechanical properties of PTFE based short carbon fibre reinforced composites: experiment and artificial neural network prediction. Compos Sci Technol 62:1001–1009CrossRefGoogle Scholar
  14. 14.
    Fazilat H et al (2012) Predicting the mechanical properties of glass fiber reinforced polymers via artificial neural network and adaptive neuro-fuzzy inference system. Comp Mater Sci 58:31–37CrossRefGoogle Scholar
  15. 15.
    Bheemreddy V et al (2013) Modeling of fiber pull-out in continuous fiber reinforced ceramic composites using finite element method and artificial neural networks. Comp Mater Sci 79:663–673CrossRefGoogle Scholar
  16. 16.
    Jelvehgari M, Montazam SH (2012) Comparison of microencapsulation by emulsion-solvent extraction/evaporation technique using derivatives cellulose and acrylate-methacrylate copolymer as carriers. Jundishapur J Nat Pharm Prod 7:144–152CrossRefGoogle Scholar
  17. 17.
    Laroui H (2007) Nanospheres polymeres à couverture dehyaluranate pour la délivrance ciblée de molécules actives dans le traitement des affections du cartilage. Nancy-MetzUniversité Henri Poincaré, NancyGoogle Scholar
  18. 18.
    Li M, Rouaud O, Poncelet D (2008) Microencapsulation by solvent evaporation: state of the art for process engineering approaches. Int J Pharm 363:26–39CrossRefGoogle Scholar
  19. 19.
    Hiller SA et al (1971) Recognition of physiological activity of chemical compounds on perceptron with random adaptation of structure. Dokl Akad Nauk SSSR 199:851–853Google Scholar
  20. 20.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536CrossRefGoogle Scholar
  21. 21.
    Pai TY et al (2007) Grey and neural network prediction of suspended solids and chemical oxygen demand in hospital wastewater treatment plant effluent. Comput Chem Eng 31:1272–1281CrossRefGoogle Scholar
  22. 22.
    Ochoa-Estopier LM, Jobson M, Smith R (2013) Operational optimization of crude oil distillation systems using artificial neural networks. Comput Chem Eng 59:178–185CrossRefGoogle Scholar
  23. 23.
    Verma S et al (2011) Modeling of trihalomethanes (THMS) in drinking water by artificial neural network. Poll Res. 30:7–11Google Scholar
  24. 24.
    Brag CC, Dias MS (2002) Application of neural networks for unfolding neutron spectra measured by means of Bonner spheres. Nucl Instrum Meth A 476:252–255CrossRefGoogle Scholar
  25. 25.
    Zheng XM et al (2004) Correction for crosstalk contaminations in dual radionuclide 99mTc and 123I images using artificial neural network. IEEE T nucl sci 51:2649–2653CrossRefGoogle Scholar
  26. 26.
    King D et al (2003) An optical fibre ethanol concentration sensor utilizing Fourier transform signal processing analysis and artificial neural network pattern cognition. J Opt A 5:S69–S75CrossRefGoogle Scholar
  27. 27.
    Prouillac C et al (2009) Evaluation of new thiadiazoles and benzothiazoles as potential radioprotectors: free radical scavenging activity in vitro and theoretical studies (QSAR, DFT). Free Radical Bio Med 46:1139–1148CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • A. Malho Rodrigues
    • 1
  • S. Franceschi
    • 1
  • E. Perez
    • 1
  • J.-C. Garrigues
    • 1
  1. 1.Laboratoire des I.M.R.C.P, UMR 5623 CNRSUniversité Paul SabatierToulouse Cedex 09France

Personalised recommendations