2026-05-31T22:10:23Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/116082026-05-14T06:41:42Zcom_10259_4219com_10259_5086com_10259_2604col_10259_4220

Maestro Prieto, José Alberto Gil del Val, Alain Bustillo Iglesias, Andrés 2026-05-12T08:14:18Z 2026-05-12T08:14:18Z 2025-09 0268-3768 https://hdl.handle.net/10259/11608 10.1007/s00170-025-16491-x 1433-3015 The tapping of metal components is a manufacturing task with great potential for automation, because the conditions affecting the industrial components are of limited variability. However, automation encounters two main problems: both the human- and the time-related costs associated with the manual classification of threads are excessive, and thread quality can vary greatly, due to tapping tool wear. In this study, the use of semi-supervised algorithms is proposed to improve the performance of machine learning–based models trained on real industrial datasets. The strategy was validated on a dataset of more than 7000 threads produced with 36 different tapping tools under the same working conditions involving nodular cast iron workpieces. Several algorithms were trained using datasets with different features and data processing. The best results were obtained with datasets using linear regression in which sinusoidal fluctuations in the raw signals were replaced by linear regressions and the slope of an 11-element rolling window was applied to extend the raw dataset. Algorithms were trained with different percentages of labeled datasets. The co-training-based algorithms almost systematically obtained the best results, yielding better results than the reference algorithms using a 100% labeled dataset. Besides, the proposed solution also achieved higher performance with 50% of labeled instances in the training dataset, drastically reducing the costs of manual labeling for that sort of industrial dataset. Open access funding provided by FEDER European Funds and the Junta de Castilla y León under the Research and Innovation Strategy for Smart Specialization (RIS3) of Castilla y León 2021-2027. This work was supported by the Junta de Castilla y León through project BU055P20 (JCyL/FEDER, UE), the Spanish Ministry of Science and Innovation through project PID2020-119894GBI00/AEI/10.13039/501100011033, and it was co-financed through European Union FEDER funds. The authors acknowledge Basque Government financing through the ECOVERSO project, the ELKARTEK 2024 program (KK2024/00095), the ORLEGI project, and the ELKARTEK 2024 program (KK2024/00005), and funding from the European Commission through the REINFORCE project, GRANT_NUMBER: 101104204 URL: https://app.dimensions.ai/details/grant/grant.13717357 Open access funding provided by FEDER European Funds and the Junta De Castilla y León under the Research and Innovation Strategy for Smart Specialization (RIS3) of Castilla y León 2021-2027 application/pdf eng Springer The International Journal of Advanced Manufacturing Technology. 2025 https://doi.org/10.1007/s00170-025-16491-x Atribución 4.0 Internacional http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Semi-supervised learning Fault detection Tapping Wear Inteligencia artificial Industria Artificial intelligence Industry Semi-supervised tapping wear detection in nodular cast iron workpieces under real industrial conditions info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion The International Journal of Advanced Manufacturing Technologyhttps://ror.org/051jb1k20Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE)hybrid-oa12300,08 EUR36568439Springer Nature2025-07-292025-11-142025-01-012027-12-31https://doi.org/10.1007/s00170-025-16491-x