Weld Defect Categorization from Welding Current using Principle Component Analysis

Abstract

Real time welding quality control still remains a challenging task due to the dynamic characteristic of welding. Welding current of gas metal arc welding possess valuable information that can be analyzed for weld quality assessment purposes. On-line monitoring of motor current can be provided information about the welding. In this study, current signals obtained during welding in the short- circuit metal transfer mode were used for real-time categorization of deliberately induced weld defects and good welds. A hall-effect current sensor was employed on the ground wiring of the welding machine to acquire the welding current signals during the welding process. Vector reduction of the current signals in time domain was achieved by principle component analysis. The reduced vector was then classified by various classification techniques such as support vector machines, decision trees and nearest neighbor to categorize the arc weld defects or pass it as a good weld. The proposed technique has proved to be successful with accurate classification of the welding categories using all three classifiers. The classification technique is fast enough so it can be used for real time weld quality control as all the signal processing is carried out in the time domain.

Authors and Affiliations

Hayri Arabaci, Salman Laving

Keywords

Related Articles

Comparative Analysis between a Photovoltaic System with Two-Axis Solar Tracker and One with a Fixed Base

In this article, the comparative analysis of the stored energies between a photovoltaic system with a two-axis solar tracker, controlled by Arduino with respect to the energy stored by a fixed-base photovoltaic system is...

An approach for Teaching of National Languages and Cultures through ICT in Cameroon

This article describes the input of ICT to the modernization of teaching national languages and cultures in order to promote cultural diversity as well as dissemination of scientific knowledge through national languages....

Multispectral Image Analysis using Decision Trees

Many machine learning algorithms have been used to classify pixels in Landsat imagery. The maximum likelihood classifier is the widely-accepted classifier. Non-parametric methods of classification include neural networks...

Auto-Scaling Approach for Cloud based Mobile Learning Applications

In the last decade, mobile learning applications have attracted a significant amount of attention. Huge investments have been made to develop educational applications that can be implemented on mobile devices. However, m...

Efficient Verification-Driven Slicing of UML/OCL Class Diagrams

Model defects are a significant concern in the Model-Driven Development (MDD) paradigm, as model trans-formations and code generation may propagate errors present in the model to other notations where they are harder to...

Download PDF file
  • EP ID EP596748
  • DOI 10.14569/IJACSA.2019.0100628
  • Views 109
  • Downloads 0

How To Cite

Hayri Arabaci, Salman Laving (2019). Weld Defect Categorization from Welding Current using Principle Component Analysis. International Journal of Advanced Computer Science & Applications, 10(6), 204-211. https://europub.co.uk/articles/-A-596748