Resumo

BENITEZ-PEREZ, H.  e  MEDINA-GOMEZ, L.. Diverse Time-Frequency Distributions Integrated to an ART2 Network for Non-Destructive Testing. J. appl. res. technol [online]. 2008, vol.6, n.1, pp.14-32. ISSN 2448-6736.

The use of several techniques for non-destructive testing is a common strategy for detecting and classifying flaws in aluminium material. Techniques like multiresolution data analysis and data classifiers are valuable for obtaining as much information as possible from the flaws. The combination of both techniques allows the clear definition of several characteristics like localization, size and form. In this study, localization using Time-Frequency Distribution feature extraction and an ART2 neural network as a classifier is the main goal.

Palavras-chave : Non-destructive Testing; Neural Networks; Time Frequency Distribution Approach.

        · texto em Inglês     · Inglês ( pdf )