• Aucun résultat trouvé

Computer Code for Materials Diagnosis Using Monte Carlo Method and Neural Networks

N/A
N/A
Info
Télécharger
Protected

Academic year: 2021

Partager "Computer Code for Materials Diagnosis Using Monte Carlo Method and Neural Networks"

Copied!
1
0
0

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

Texte intégral

(1)

J Fail. Anal. and Preven. (2016) 16:931–937 DOI 10.1007/s11668-016-0175-1

Computer Code for Materials Diagnosis Using Monte Carlo Method and Neural Networks

Hocine Bendjama, Djallel Mahdi

Abstract: Non-destructive testing (NDT) is a highly valuable technique in evaluation and evolution of materials and products. X-ray imaging is an important NDT technique that is used widely in the metal industry in order to control the quality of materials. Sometimes it may be difficult to get a measurement. The simulation of X-ray imaging is often performed using computer codes. This paper presents a new simulation method for materials diagnosis.

The simulation is based primarily on the X-ray attenuation law and it is performed using a combination between Monte Carlo method and multi-layer perceptron neural network. The main goal of the proposed method is to obtain more detailed information about the state of the materials.

Keywords: Non-destructive testing, X-ray imaging, Materials diagnosis, Monte Carlo, Neural network

H. Bendjama

Research Center in Industrial Technologies CRTI, P.O.Box. 64, Cheraga, Algiers, Algeria

h.bendjama@crti.dz D. Mahdi

Department of Hydraulic, University of M’sila, M’sila, Algeria

Références

Télécharger maintenant ( PDF - 1 Page - 65.92 KB )

Documents relatifs

Parallel and interacting Markov chains Monte Carlo method

Key-words: Markov hain Monte Carlo method, Metropolis-Hastings, interating hains,..

A Randomized Quasi-Monte Carlo Method for the Simulation of Product-form Loss Networks

Unit´e de recherche INRIA Rennes, Irisa, Campus universitaire de Beaulieu, 35042 RENNES Cedex Unit´e de recherche INRIA Rhˆone-Alpes, 655, avenue de l’Europe, 38330 MONTBONNOT ST

MATHEMATICAL SIMULATION OF X-RAY OPTICAL SYSTEMS USING MONTE CARLO METHOD

The developed technique was used for computation of X-ray optical systems with double-bent crystals which are of high interest in development of X-ray spect- rometers of

A Randomized Quasi-Monte Carlo Simulation Method for Markov Chains

Unité de recherche INRIA Rennes, Irisa, Campus universitaire de Beaulieu, 35042 RENNES Cedex Unité de recherche INRIA Rhône-Alpes, 655, avenue de l’Europe, 38330 MONTBONNOT ST

Quantile Estimation Via a Combination of Conditional Monte Carlo and Randomized Quasi-Monte Carlo

As an improvement, we use conditional Monte Carlo to obtain a smoother estimate of the distribution function, and we combine this with randomized quasi-Monte Carlo to further reduce

Variance Reduction for Generalized Likelihood Ratio Method By Conditional Monte Carlo and Randomized Quasi-Monte Carlo

Variance Reduction for Generalized Likelihood Ratio Method By Conditional Monte Carlo and Randomized Quasi-Monte Carlo... Variance Reduction for Generalized Likelihood Ratio Method

Decoding Fingerprinting Using the Markov Chain Monte Carlo Method

Probabilities of errors for the single decoder: (solid) Probability of false negative, (dashed) Probability of false positive, [Down] Average number of caught colluders for the

Pd–H and Ni–H phase diagrams using cluster variation method and Monte Carlo simulation

Pd–H and Ni–H phase diagrams using cluster variation method and Monte Carlo simulation.. Natacha Bourgeois, Pierre Cenedese, Jean-Claude Crivello,