RT info:eu-repo/semantics/article
T1 Glass-box modeling for quality assessment of resistance spot welding joints in industrial applications
A1 Santos Martín, José Ignacio
A1 Martín, Óscar
A1 Ahedo García, Virginia
A1 Tiedra, Pilar de
A1 Galán Ordax, José Manuel
K1 Explainable boosting machine
K1 Pattern recognition
K1 Quality assessment
K1 Resistance spot welding
K1 AISI 304 austenitic stainless steel
K1 Tensile shear load bearing capacity
K1 Ingeniería
K1 Engineering
AB Resistance spot welding (RSW) is one of the most relevant industrial processes in diferent sectors. Key issues in RSW areprocess control and ex-ante and ex-post evaluation of the quality level of RSW joints. Multiple-input–single-output methodsare commonly used to create predictive models of the process from the welding parameters. However, until now, the choiceof a particular model has typically involved a tradeof between accuracy and interpretability. In this work, such dichotomyis overcome by using the explainable boosting machine algorithm, which obtains accuracy levels in both classifcation andprediction of the welded joint tensile shear load bearing capacity statistically as good or even better than the best algorithmsin the literature, while maintaining high levels of interpretability. These characteristics allow (i) a simple diagnosis of theoverall behavior of the process, and, for each individual prediction, (ii) the attribution to each of the control variables—and/or to their potential interactions—of the result obtained. These distinctive characteristics have important implications forthe optimization and control of welding processes, establishing the explainable boosting machine as one of the referencealgorithms for their modeling.
PB Springer Nature
SN 0268-3768
YR 2022
FD 2022-11
LK http://hdl.handle.net/10259/7401
UL http://hdl.handle.net/10259/7401
LA eng
NO Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. The authors acknowledge fnancial support from the Spanish Ministry of Science, Innovation and Universities (Excellence Network RED2018‐102518‐T), the Spanish State Research Agency (PID2020-118906 GB-I00/AEI/https://doi.org/10. 13039/501100011033), and the Fundación Bancaria Caixa D. Estalvis I Pensions de Barcelona, La Caixa (2020/00062/001). In addition, we acknowledge support from the Santander Supercomputación group (University of Cantabria) that provided access to the Altamira Supercomputer—located at the Institute of Physics of Cantabria (IFCACSIC) and member of the Spanish Supercomputing Network—to perform the diferent simulations/analyses.
DS Repositorio Institucional de la Universidad de Burgos
RD 23-nov-2024