RT info:eu-repo/semantics/article
T1 Direct quality prediction in resistance spot welding process: Sensitivity, specificity and predictive accuracy comparative analysis
A1 Pereda, María
A1 Santos Martín, José Ignacio
A1 Martín, Óscar
A1 Galán Ordax, José Manuel
K1 Resistance spot welding
K1 Classification
K1 Pattern recognition
K1 Quality control
K1 Support vector machines
K1 Random forest
K1 Artificial neural networks
K1 Empresas-Gestión
K1 Industrial management
AB In this work, several of the most popular and state-of-the-art classification methods are compared as pattern recognition tools for classificationof resistance spot welding joints. Instead of using the result of a non-destructivetesting technique as input variables, classifiers are trained directly with therelevant welding parameters, i.e. welding current, welding time and the type ofelectrode (electrode material and treatment). The algorithms are compared interms of accuracy and area under the receiver operating characteristic (ROC)curve metrics, using nested cross-validation. Results show that although there is not a dominant classifier for every specificity/sensitivity requirement, support vector machines using radial kernel, boosting and random forest techniques obtain the best performance overall
PB Maney Publishing
SN 1362-1718
YR 2015
FD 2015-11
LK http://hdl.handle.net/10259/3928
UL http://hdl.handle.net/10259/3928
LA eng
NO Spanish MICINN Project CSD2010-00034 (SimulPast CONSOLIDER-INGENIO 2010) and by the Junta de Castilla y León GREX251-2009
DS Repositorio Institucional de la Universidad de Burgos
RD 20-abr-2024