A predictive approach for enhancing outcomes performance in SAW process

Welding processes are the most common manufacturing solution that frequently complete the final steps of an industrial production. Their large use makes these techniques worth of attention of the scientific community, so that several efforts are spent for optimising and improving the way the process...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science 2023, Vol.217, p.1849-1856
Main Authors: Conte, Romina, Gabriele, Zangara, David, Rodríguez Izquierdo, Serafino, Caruso, Giuseppina, Ambrogio
Format: Article
Language:English
Subjects:
correlation analysis
machine learning
optimisation
Submerged Arc Welding
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Welding processes are the most common manufacturing solution that frequently complete the final steps of an industrial production. Their large use makes these techniques worth of attention of the scientific community, so that several efforts are spent for optimising and improving the way the processes are executed. Submerged Arc Welding is widely used in the industrial scenario being semi-automatic but it cannot be ignored that this joining technique is far from the full automatization and is still dependent by the operator expertise. In this study, an experimental investigation has been performed to build a robust data set for the subsequent application of seven machine learning classifier. The aim of the work is the definition of a suitable classifier able to detect and predict invalid process conditions which could lead to failed joint.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2022.12.385