• Aucun résultat trouvé

Reconstitution of complex defects with themethodof neural network: Application for thenondestructiveevaluation

N/A
N/A
Info
Télécharger
Protected

Academic year: 2021

Partager "Reconstitution of complex defects with themethodof neural network: Application for thenondestructiveevaluation"

Copied!
1
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

7th African Conference on Non Destructive Testing ACNDT 2016 & the 5th International Conference on NDT and Materials Industry and Alloys (IC-WNDT-MI)

2016

Reconstitution of complex defects with the methodof neural network: Application for the

nondestructiveevaluation

Amirouche Harouz, Hassane Mohellebi, Meziane Hamel

Abstract : in this work, we propose a reconstitution of complex defects starting from the results obtained during a nondestructive testing by eddy currents carried out on aconducting plate by using the neural network. We provided tothe neural network the values of impedance of the differential sensor calculated using a modeling by finite elements.The values of impedance are injected at the input of the neural network and the depth of the defect is recovered in its output, we used the gradient of the error propagation algorithm for performing learning of the neural network.

Keywords : Neural Network, eddy currents, impedance, complex defect, nondestruction evaluation

Centre de Recherche en Technologies Industrielles - CRTI - www.crti.dz

Powered by TCPDF (www.tcpdf.org)

Références

Télécharger maintenant ( PDF - 1 Page - 7.69 KB )

Documents relatifs

A neural network approach for the diagnosis of the continuous pulp digester

Moisture content (a) and Carbohydrate density (b): normalized variations introduced (solid) and neural network response (dashed) in trained conditions.. Moisture content (a)

The Application Research of Neural Network in Embedded Intelligent Detection

In the application of neural network, we need to input a large number of training data and output the training process and the training results, which requires a higher demand of

Bayesian neural network priors at the level of units

The documents may come from teaching and research institutions in France or abroad, or from public or private research centers.. L’archive ouverte pluridisciplinaire HAL, est

Analysis of the influence of a network on the values of its nodes : the use of spatial indexes.

This simple example illustrates the fact that the use of a weighted or a non weighted graph for the join count statistics can have a strong influence on the result, depending on

Reconstitution of complex defects with the method of neural networ: Application for the nondestructive evaluation

Fig.5 and fig.9 provide the results of the reconstitution made by the neuron network; we superimposed the desired output (given training of the network) with the output of

The ultrametric organization of memories in a neural network

We do not discuss the problem of storage capability but compare our results on retrieval of spurious state with the ones derived in the Hopfield.. model

From Psychoacoustics to Brain Waves: A Longitudinal Approach to Novel Word Learning

Taken together, these results are in line with the phonetic –phonological–lexical continuity and cascading hypothesis (Besson et al., 2017; Dittinger et al., 2016; Cooper &