The acoustic emission test has distinguished relevance in non-destructive testing and, therefore, existing research abound at present aiming at the improvement of the reliability of their results. In this work, the methodologies and the results obtained in a study performed are presented to implement pattern classifiers by using artificial neural networks, aiming at the propagation of existing defects in pressurized pipes by means of Acoustic Emission testing (AE). Parameters that are characteristic of AE signals were used as input data for the classifiers. Several tests were performed and the classification performances were in the range of 92% for most of the instances analyzed. Studies of parameter relevance were also performed and showed that only a few of the parameters are actually important for the separation of classes of signals corresponding to No Propagation (NP) of defects and Propagation (P) of defects. The results obtained are pioneering in this type of research and encouraged the present publication.

This content is only available via PDF.
You do not currently have access to this content.