Discontinuity Detection in the Shield Metal Arc Welding Process

Abstract

This work proposes a new methodology for the detection of discontinuities in the weld bead applied in Shielded Metal Arc Welding (SMAW) processes. The detection system is based on two sensors—a microphone and piezoelectric—that acquire acoustic emissions generated during the welding. The feature vectors extracted from the sensor dataset are used to construct classifier models. The approaches based on Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers are able to identify with a high accuracy the three proposed weld bead classes: desirable weld bead, shrinkage cavity and burn through discontinuities. Experimental results illustrate the system’s high accuracy, greater than 90% for each class. A novel Hierarchical Support Vector Machine (HSVM) structure is proposed to make feasible the use of this system in industrial environments. This approach presented 96.6% overall accuracy. Given the simplicity of the equipment involved, this system can be applied in the metal transformation industries.

Analysis of Wrist Hand Motion for Monitoring of Basic Welder Training using Wearable Sensors

“…4. Incomplete Fusion (IF) is an unwanted welding result due to imperfections in the joining process between the weld metal and the base metal [6]. This type of welding defect is due to the high welding speed.…”

In-Process Monitoring of Lack of Fusion in Ultra-Thin Sheets Edge Welding Using Machine Vision

“…During processes of arc welding and laser welding, various types of sources can provide online information relevant to the weld quality, such as arc voltage [ 14 ], welding current [ 15 ], audible sound [ 16 ], acoustic emissions [ 17 , 18 , 19 ], as well as the optical or thermal radiation that is generated from electric arc, molten pool, plasma plume, and metallic vapor [ 20 , 21 , 22 , 23 ]. A promising approach is to use machine vision to the in-process weld pool monitoring, as this provides an access to abundant and direct-viewing information about the process dynamics that closely related to weld bead formation and some defects [ 24 , 25 , 26 , 27 ].…”