An “intelligent” approach based on side-by-side cascade-correlation neural networks for estimating thermophysical properties from photothermal responses

Stéphane Grieu 1 Olivier Faugeroux 1 Adama Traoré 1 Bernard Claudet 1 Jean-Luc Bodnar 2
1 PROMES - Procédés, Matériaux et Energie Solaire
2 GRESPI - Groupe de Recherche en Sciences Pour l'Ingénieur - EA 4694
Abstract : In the present paper, an artificial-intelligence-based approach dealing with the estimation of thermophysical properties is designed and evaluated. This new and “intelligent” approach makes use of photothermal responses obtained when subjecting materials to a light flux. So, the main objective of the present work was to estimate simultaneously both the thermal diffusivity and conductivity of materials, from front-face or rear-face photothermal responses to pseudo random binary signals. To this end, we used side-by-side feedforward neural networks trained with the cascade-correlation algorithm. In addition, computation time was a key point to consider. That is why the developed algorithms are computationally tractable.
Type de document :
Article dans une revue
European Physical Journal: Applied Physics, EDP Sciences, 2015, 69 (1), 8 p. 〈10.1051/epjap/2014140254〉
Liste complète des métadonnées
https://hal-univ-perp.archives-ouvertes.fr/hal-01175565
Contributeur : Olivier Savoyat <>
Soumis le : vendredi 10 juillet 2015 - 16:08:30
Dernière modification le : jeudi 25 janvier 2018 - 01:01:46

Lien texte intégral

istex

Identifiants

Collections

UNIV-PERP | PROMES | URCA | GRESPI | SFRCONDORCET

Citation

Stéphane Grieu, Olivier Faugeroux, Adama Traoré, Bernard Claudet, Jean-Luc Bodnar. An “intelligent” approach based on side-by-side cascade-correlation neural networks for estimating thermophysical properties from photothermal responses. European Physical Journal: Applied Physics, EDP Sciences, 2015, 69 (1), 8 p. 〈10.1051/epjap/2014140254〉. 〈hal-01175565〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

106

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD