Optimization of Plasma Fabric Surface Treatment by Modeling with Neural Networks

  • Radhia Abd Jelil
  • Xianyi Zeng
  • Ludovic Koehl
  • Anne Perwuelz
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 213)


Artificial neural networks (ANNs) are used to model the relationship between plasma processing parameters and woven fabric surface wetting properties. In this model, fourteen features characterizing woven structures and two plasma parameters are taken as input variables and the water contact angle cosine and capillarity height as output variables. In order to reduce the complexity of the model, a fuzzy logic–based method is used to select the most relevant parameters that are taken as inputs of the reduced neural model. Two techniques (early stopping and Bayesian regularization) are used for improving the generalization ability of neural networks. A methodology for optimizing such models is described. Moreover, a connection weight method is used to investigate the relative importance of each input variable. From the experiments, we find a good agreement between experimental and predicted data and that Bayesian regularization technique is the most suitable to achieve a good generalization.


Artificial neural networks Fuzzy logic–based selection criterion Industrial modeling Atmospheric air plasma Woven fabrics Wettability 


  1. 1.
    Cai Z, Qiu Y, Zhang C, Hwang Y, McCord M (2003) Effect of atmospheric plasma treatment on desizing of PVA on cotton. Text Res J 73:670–674CrossRefGoogle Scholar
  2. 2.
    Costa THC, Feitor MC, Alves C, Freire PB, de Bezzerra CM (2006) Effects of gas composition during plasma modification of polyester fabrics. J Mater Process Technol 173:40–43CrossRefGoogle Scholar
  3. 3.
    Hossain MM, Herrmann AS, Hegemann D (2006) Plasma hydrophilization effect on different textile structures. Plasma Process Polym 3:299–307CrossRefGoogle Scholar
  4. 4.
    Takke V, Behary N, Perwuelz A, Campagne C (2009) Studies on the atmospheric air-plasma treatment of PET (Polyethylene Terephthalate) woven fabrics: effect of process parameters and of ageing. J Appl Polym Sci 114:348–357CrossRefGoogle Scholar
  5. 5.
    Coit DW, Jackson BT, Smith AE (1998) Static neural network process models: considerations and case studies. Int J Prod Res 36:2953–2967CrossRefMATHGoogle Scholar
  6. 6.
    Yousefi MMR, Mirmomeni M, Lucas C (2007) Input variables selection using mutual information for neuro fuzzy modeling with the application to time series forecasting. In: Proceedings of international joint conference on neural networks, Orlando, Florida, USA, pp 1121–1126Google Scholar
  7. 7.
    Fleuret F (2004) Fast binary feature selection with conditional mutual information. J Mach Learn Res 5:1531–1555MathSciNetMATHGoogle Scholar
  8. 8.
    Thawonmas R, Abe S (1997) A novel approach to feature selection based on analysis of class regions. IEEE Trans Syst Man Cybern B 27:196–207CrossRefGoogle Scholar
  9. 9.
    Deng X, Vroman P, Zeng X, Koehl L (2010) Selection of relevant variables for industrial process modelling combining experimental data sensitivity and human knowledge. Eng Appl Artif Intell 23:1368–1379CrossRefGoogle Scholar
  10. 10.
    AbdJelil R, Zeng X, Koehl L, Perwuelz A (2009) Neural model of woven fabric surface modification by atmospheric air plasma. In: Intelligent textiles and mass customization international conference, Casablanca, MoroccoGoogle Scholar
  11. 11.
    Huang YL, Edgar TF, Himmelbau DM, Trachtenberg I (1994) Constructing a reliable neural network model for a plasma etching process using limited experimental data. IEEE Trans Semicond Manuf 7:333–344CrossRefGoogle Scholar
  12. 12.
    Gil P, Cardoso A, Palma L (2009) Estimating the number of hidden neurons in recurrent neural networks for nonlinear system identification. In: IEEE international symposium on industrial electronics. IEEE Press, Seoul, South Korea, pp 2053–2058Google Scholar
  13. 13.
    Lee KW, Lam HN (1995) Optimal sizing of feed forward neural networks: case studies. In: 2nd New Zealand two-stream international conference on artificial neural networks and expert systems. IEEE computer society, Dunedin, New Zealand, pp 79–82Google Scholar
  14. 14.
    Olden JD, Jackson DA (2002) Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks. Ecol Model 154:135–150CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Radhia Abd Jelil
    • 1
  • Xianyi Zeng
    • 2
  • Ludovic Koehl
    • 2
  • Anne Perwuelz
    • 2
  1. 1.Institut Supérieur des Arts et Métiers de TataouineTataouineTunisia
  2. 2.The ENSAIT Textile InstituteRoubaixFrance

Personalised recommendations