Data quality strategies in gas metal arc welding production for machine learning applications
- Author
- Jorge Iván Rodríguez Echeverría (UGent) , Evans Doe Ocansey, Roxana-Maria Holom, Tomasz Piotr Michno, Hannes Hinterbichler, Pauline Meyer-Heye and Sidharta Gautama (UGent)
- Organization
- Project
- Abstract
- Amidst the advent of Industry 4.0, the manufacturing industry is exploring AI methodologies and other data-driven approaches for the understanding and optimization of gas metal arc welding (GMAW) processes. Various data sources such as process data logs and image data are available to the users of modern welding systems. However, to make good use of the data for machine learning, data sets of different quality and information density have to be fused. In this paper, we propose strategies for improving the dataset quality of time series process data and image data from the GMAW process. We explore resampling strategies to ensure the harmonization of time series data. Additionally, ideas for improving image quality from welding process cameras are discussed.
- Keywords
- GMAW, Data Quality, Image Processing, Time Series, Data Augmentation
Downloads
-
DCAI'24 submission 57 paper v1.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 1.15 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01J6CGKMKDTN5EN820ZYCFDCVZ
- MLA
- Rodríguez Echeverría, Jorge Iván, et al. “Data Quality Strategies in Gas Metal Arc Welding Production for Machine Learning Applications.” DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE, vol. 1198, Springer Cham, 2025, pp. 83–94, doi:10.1007/978-3-031-76459-2_8.
- APA
- Rodríguez Echeverría, J. I., Ocansey, E. D., Holom, R.-M., Michno, T. P., Hinterbichler, H., Meyer-Heye, P., & Gautama, S. (2025). Data quality strategies in gas metal arc welding production for machine learning applications. DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE, 1198, 83–94. https://doi.org/10.1007/978-3-031-76459-2_8
- Chicago author-date
- Rodríguez Echeverría, Jorge Iván, Evans Doe Ocansey, Roxana-Maria Holom, Tomasz Piotr Michno, Hannes Hinterbichler, Pauline Meyer-Heye, and Sidharta Gautama. 2025. “Data Quality Strategies in Gas Metal Arc Welding Production for Machine Learning Applications.” In DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE, 1198:83–94. Springer Cham. https://doi.org/10.1007/978-3-031-76459-2_8.
- Chicago author-date (all authors)
- Rodríguez Echeverría, Jorge Iván, Evans Doe Ocansey, Roxana-Maria Holom, Tomasz Piotr Michno, Hannes Hinterbichler, Pauline Meyer-Heye, and Sidharta Gautama. 2025. “Data Quality Strategies in Gas Metal Arc Welding Production for Machine Learning Applications.” In DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE, 1198:83–94. Springer Cham. doi:10.1007/978-3-031-76459-2_8.
- Vancouver
- 1.Rodríguez Echeverría JI, Ocansey ED, Holom R-M, Michno TP, Hinterbichler H, Meyer-Heye P, et al. Data quality strategies in gas metal arc welding production for machine learning applications. In: DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE. Springer Cham; 2025. p. 83–94.
- IEEE
- [1]J. I. Rodríguez Echeverría et al., “Data quality strategies in gas metal arc welding production for machine learning applications,” in DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE, Salamanca, Spain, 2025, vol. 1198, pp. 83–94.
@inproceedings{01J6CGKMKDTN5EN820ZYCFDCVZ,
abstract = {{Amidst the advent of Industry 4.0, the manufacturing industry is exploring AI methodologies and other data-driven approaches for the understanding and optimization of gas metal arc welding (GMAW) processes. Various data sources such as process data logs and image data are available to the users of modern welding systems. However, to make good use of the data for machine learning, data sets of different quality and information density have to be fused. In this paper, we propose strategies for improving the dataset quality of time series process data and image data from the GMAW process. We explore resampling strategies to ensure the harmonization of time series data. Additionally, ideas for improving image quality from welding process cameras are discussed.}},
author = {{Rodríguez Echeverría, Jorge Iván and Ocansey, Evans Doe and Holom, Roxana-Maria and Michno, Tomasz Piotr and Hinterbichler, Hannes and Meyer-Heye, Pauline and Gautama, Sidharta}},
booktitle = {{DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE, SPECIAL SESSIONS I, 21ST INTERNATIONAL CONFERENCE}},
isbn = {{9783031764585}},
issn = {{2367-3370}},
keywords = {{GMAW,Data Quality,Image Processing,Time Series,Data Augmentation}},
language = {{eng}},
location = {{Salamanca, Spain}},
pages = {{83--94}},
publisher = {{Springer Cham}},
title = {{Data quality strategies in gas metal arc welding production for machine learning applications}},
url = {{http://doi.org/10.1007/978-3-031-76459-2_8}},
volume = {{1198}},
year = {{2025}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: