dc.creatorde Padua, Germano X.
dc.creatorda Silva, Romeu R.
dc.creatorMery, Domingo
dc.creatorSiqueira, Marcio H. S.
dc.creatorRebello, Joao M. A.
dc.creatorCaloba, Luiz P.
dc.date.accessioned2024-01-10T12:38:17Z
dc.date.available2024-01-10T12:38:17Z
dc.date.created2024-01-10T12:38:17Z
dc.date.issued2007
dc.identifier0025-5327
dc.identifierhttps://repositorio.uc.cl/handle/11534/77019
dc.identifierWOS:000250492800008
dc.description.abstractRadiographic testing of weld joints is of great importance for verifying and maintaining weld quality. This work presents a new technique for the development Of an automatic or semiautomatic system for radiographic weld analysis. This technique uses gray level profiles transversal to weld beads in radiographic patterns. These profiles were processed to aid in the setup of nonlinear pattern classifiers developed by neural networks with algorithms by backpropagation of error. The classification accuracy was estimated via the average correctness of 10 randomly chosen test sets. The results presented a general accuracy of classification correctness of around 95% for the class patterns in the profiles that were used.
dc.languageen
dc.publisherAMER SOC NONDESTRUCTIVE TEST
dc.rightsregistro bibliográfico
dc.subjecttransversal gray level profiles
dc.subjectnonlinear classifier
dc.subjectweld discontinuities
dc.subjectradiography
dc.subjectnondestructive testing
dc.subjectDEFECTS
dc.subjectINSPECTION
dc.subjectSYSTEM
dc.titleDetection and classification of weld discontinuities in radiographic images (Part I: Supervised learning)
dc.typeartículo


Este ítem pertenece a la siguiente institución