arrow
Volume 8, Issue 2
Modeling Plasma Fabric Surface Treatment Using Fuzzy Logic and Artificial Neural Networks

Radhia Abd Jelil , Xianyi Zeng Ludovic Koehl and Anne Perwuelz

J. Info. Comput. Sci. , 8 (2013), pp. 141-152.

Export citation
  • Abstract
In this paper, Artificial Neural Networks (ANNs) are used to model the effect of atmospheric air-plasma treatment on fabric surfaces with various structures. In order to reduce the complexity of the models and increase the knowledge and comprehension of the underlying process, a fuzzy sensitivity variation criterion is used to select the most relevant parameters which are taken as inputs of the reduced neural models. The model outputs are the water contact angle and the capillarity of woven fabrics, characterizing the change of fabric surfaces. The early stopping and Bayesian regularization techniques are used for improving the network’s generalization capability. Two different network configurations are studied. One deals with two networks having each one output layer neuron and another with a single network combining the two outputs. Obtained results showed that the first configuration combined with the Bayesian regularization approach is the most suitable to achieve a good prediction accuracy.
  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JICS-8-141, author = {Radhia Abd Jelil , Xianyi Zeng Ludovic Koehl and Anne Perwuelz}, title = {Modeling Plasma Fabric Surface Treatment Using Fuzzy Logic and Artificial Neural Networks}, journal = {Journal of Information and Computing Science}, year = {2024}, volume = {8}, number = {2}, pages = {141--152}, abstract = { In this paper, Artificial Neural Networks (ANNs) are used to model the effect of atmospheric air-plasma treatment on fabric surfaces with various structures. In order to reduce the complexity of the models and increase the knowledge and comprehension of the underlying process, a fuzzy sensitivity variation criterion is used to select the most relevant parameters which are taken as inputs of the reduced neural models. The model outputs are the water contact angle and the capillarity of woven fabrics, characterizing the change of fabric surfaces. The early stopping and Bayesian regularization techniques are used for improving the network’s generalization capability. Two different network configurations are studied. One deals with two networks having each one output layer neuron and another with a single network combining the two outputs. Obtained results showed that the first configuration combined with the Bayesian regularization approach is the most suitable to achieve a good prediction accuracy. }, issn = {1746-7659}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/jics/22623.html} }
TY - JOUR T1 - Modeling Plasma Fabric Surface Treatment Using Fuzzy Logic and Artificial Neural Networks AU - Radhia Abd Jelil , Xianyi Zeng Ludovic Koehl and Anne Perwuelz JO - Journal of Information and Computing Science VL - 2 SP - 141 EP - 152 PY - 2024 DA - 2024/01 SN - 8 DO - http://doi.org/ UR - https://global-sci.org/intro/article_detail/jics/22623.html KW - neural networks, fuzzy selection criterion, modelling, atmospheric plasma, woven fabric AB - In this paper, Artificial Neural Networks (ANNs) are used to model the effect of atmospheric air-plasma treatment on fabric surfaces with various structures. In order to reduce the complexity of the models and increase the knowledge and comprehension of the underlying process, a fuzzy sensitivity variation criterion is used to select the most relevant parameters which are taken as inputs of the reduced neural models. The model outputs are the water contact angle and the capillarity of woven fabrics, characterizing the change of fabric surfaces. The early stopping and Bayesian regularization techniques are used for improving the network’s generalization capability. Two different network configurations are studied. One deals with two networks having each one output layer neuron and another with a single network combining the two outputs. Obtained results showed that the first configuration combined with the Bayesian regularization approach is the most suitable to achieve a good prediction accuracy.
Radhia Abd Jelil , Xianyi Zeng Ludovic Koehl and Anne Perwuelz. (2024). Modeling Plasma Fabric Surface Treatment Using Fuzzy Logic and Artificial Neural Networks. Journal of Information and Computing Science. 8 (2). 141-152. doi:
Copy to clipboard
The citation has been copied to your clipboard