Anomaly detection and event mining in cold forming manufacturing processes
- Author
- Diego Nieves Avendano (UGent) , Daniel Caljouw, Dirk Deschrijver (UGent) and Sofie Van Hoecke (UGent)
- Organization
- Project
- Abstract
- Predictive maintenance is one of the main goals within the Industry 4.0 trend. Advances in data-driven techniques offer new opportunities in terms of cost reduction, improved quality control, and increased work safety. This work brings data-driven techniques for two predictive maintenance tasks: anomaly detection and event prediction, applied in the real-world use case of a cold forming manufacturing line for consumer lifestyle products by using acoustic emissions sensors in proximity of the dies of the press module. The proposed models are robust and able to cope with problems such as noise, missing values, and irregular sampling. The detected anomalies are investigated by experts and confirmed to correspond to deviations in the normal operation of the machine. Moreover, we are able to find patterns which are related to the events of interest.
- Keywords
- ACOUSTIC-EMISSION, Predictive maintenance, Anomaly detection, Association rule mining, Multivariate data, Matrix profile
Downloads
-
7785.pdf
- full text (Published version)
- |
- open access
- |
- |
- 3.26 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8680095
- MLA
- Nieves Avendano, Diego, et al. “Anomaly Detection and Event Mining in Cold Forming Manufacturing Processes.” INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, vol. 115, no. 3, 2021, pp. 837–52, doi:10.1007/s00170-020-06156-2.
- APA
- Nieves Avendano, D., Caljouw, D., Deschrijver, D., & Van Hoecke, S. (2021). Anomaly detection and event mining in cold forming manufacturing processes. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 115(3), 837–852. https://doi.org/10.1007/s00170-020-06156-2
- Chicago author-date
- Nieves Avendano, Diego, Daniel Caljouw, Dirk Deschrijver, and Sofie Van Hoecke. 2021. “Anomaly Detection and Event Mining in Cold Forming Manufacturing Processes.” INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 115 (3): 837–52. https://doi.org/10.1007/s00170-020-06156-2.
- Chicago author-date (all authors)
- Nieves Avendano, Diego, Daniel Caljouw, Dirk Deschrijver, and Sofie Van Hoecke. 2021. “Anomaly Detection and Event Mining in Cold Forming Manufacturing Processes.” INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 115 (3): 837–852. doi:10.1007/s00170-020-06156-2.
- Vancouver
- 1.Nieves Avendano D, Caljouw D, Deschrijver D, Van Hoecke S. Anomaly detection and event mining in cold forming manufacturing processes. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY. 2021;115(3):837–52.
- IEEE
- [1]D. Nieves Avendano, D. Caljouw, D. Deschrijver, and S. Van Hoecke, “Anomaly detection and event mining in cold forming manufacturing processes,” INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, vol. 115, no. 3, pp. 837–852, 2021.
@article{8680095,
abstract = {{Predictive maintenance is one of the main goals within the Industry 4.0 trend. Advances in data-driven techniques offer new opportunities in terms of cost reduction, improved quality control, and increased work safety. This work brings data-driven techniques for two predictive maintenance tasks: anomaly detection and event prediction, applied in the real-world use case of a cold forming manufacturing line for consumer lifestyle products by using acoustic emissions sensors in proximity of the dies of the press module. The proposed models are robust and able to cope with problems such as noise, missing values, and irregular sampling. The detected anomalies are investigated by experts and confirmed to correspond to deviations in the normal operation of the machine. Moreover, we are able to find patterns which are related to the events of interest.}},
author = {{Nieves Avendano, Diego and Caljouw, Daniel and Deschrijver, Dirk and Van Hoecke, Sofie}},
issn = {{0268-3768}},
journal = {{INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY}},
keywords = {{ACOUSTIC-EMISSION,Predictive maintenance,Anomaly detection,Association rule mining,Multivariate data,Matrix profile}},
language = {{eng}},
number = {{3}},
pages = {{837--852}},
title = {{Anomaly detection and event mining in cold forming manufacturing processes}},
url = {{http://doi.org/10.1007/s00170-020-06156-2}},
volume = {{115}},
year = {{2021}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: