Ajou University repository

Deep learning models for quality estimation of gas tungsten arc welding
Citations

SCOPUS

0

Citation Export

Publication Year
2022-01-01
Journal
Welding International
Publisher
Taylor and Francis Ltd.
Citation
Welding International, Vol.36 No.1, pp.17-24
Keyword
Artificial neural networkconvolutional neural networkdeep learninggas tungsten arc weldingquality estimation
Mesh Keyword
Artificial neural network modelingConsumable electrodesConvolutional neural networkDeep learningGas tungsten arc weldingGas tungsten-arc weldingLearning modelsNeural network modelQuality estimationWelding quality
All Science Classification Codes (ASJC)
Mechanics of MaterialsMechanical EngineeringMetals and Alloys
Abstract
Gas tungsten arc (GTA) welding is characterized by the use of non-consumable electrodes and shielding gas for effective welding of various metals. Welding quality can be evaluated by a visual test, but it has the disadvantage that accuracy is limited by the experience of the inspector. The quality of GTA welding can be predicted better through deep learning models that use machine vision, image processing, and welding data such as voltage, current, and feeding speed. In this study, artificial neural network (ANN) models and convolutional neural network (CNN) models are developed for estimating welding quality using v-groove GTA welding experiments. The GTA welding system comprises welding equipment and a vision system. After completing the welding experiments, 21 features and 1 label are collected from the welding data. The observations are then normalized, shuffled, and divided into training data and test data. ANN and CNN models are developed with varied architectures, then verified by calculating root mean squared error, mean absolute error, and accuracy. Abstracted ANN models are developed by applying the relative weight and product measure methods to the original ANN models. The abstract ANN models show similar or better accuracy with fewer features.
ISSN
1754-2138
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/32529
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85124358738&origin=inward
DOI
https://doi.org/2-s2.0-85124358738
Journal URL
http://www.tandf.co.uk/journals/titles/09507116.asp
Type
Article
Funding
This work was supported by the National Research Foundation [NRF-2020R1A2C1004544] grant by the Korean Government (MSIT); and the Institute for Information and Communications Technology Promotion [IITP-2021000292] grant funded by the Korean Government (MSIT).
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Park, Kiejin  Image
Park, Kiejin 박기진
Department of Industrial Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.