2025
Maestro-Prieto, José Alberto; Gil-Del-Val, Alain; Bustillo, Andrés
Semi-supervised tapping wear detection in nodular cast-iron workpieces under real industrial condition Journal Article
In: International Journal of Advanced Manufacturing Technology , 2025, ISSN: 0268-3768.
Abstract | Links | BibTeX | Tags: fault detection, Semi-supervised learning, tapping, Wear
@article{maestro-prieto2025b,
title = {Semi-supervised tapping wear detection in nodular cast-iron workpieces under real industrial condition},
author = {José Alberto Maestro-Prieto and Alain Gil-Del-Val and Andrés Bustillo},
url = {https://link.springer.com/article/10.1007/s00170-025-16491-x},
doi = {10.1007/s00170-025-16491-x},
issn = {0268-3768},
year = {2025},
date = {2025-09-19},
urldate = {2025-09-19},
journal = {International Journal of Advanced Manufacturing Technology },
abstract = {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.},
keywords = {fault detection, Semi-supervised learning, tapping, Wear},
pubstate = {published},
tppubtype = {article}
}
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.
2022
Cruz, David Checa; Saucedo-Dorantes, Juan José; Ríos, Roque Alfredo Osorno; Antonio-Daviu, José Alfonso; Bustillo, Andrés
Virtual Reality Training Application for the Condition-Based Maintenance of Induction Motors Journal Article
In: Applied Sciences, vol. 12, no. 1, pp. 414, 2022, ISSN: 2076-3417.
Abstract | Links | BibTeX | Tags: eye tracking, fault detection, FFT, induction motors, SELECTED, Virtual Reality
@article{Cruz2022,
title = {Virtual Reality Training Application for the Condition-Based Maintenance of Induction Motors},
author = {David Checa Cruz and Juan José Saucedo-Dorantes and Roque Alfredo Osorno Ríos and José Alfonso Antonio-Daviu and Andrés Bustillo},
url = {https://www.mdpi.com/2076-3417/12/1/414},
doi = {10.3390/app12010414},
issn = {2076-3417},
year = {2022},
date = {2022-01-01},
journal = {Applied Sciences},
volume = {12},
number = {1},
pages = {414},
abstract = {The incorporation of new technologies as training methods, such as virtual reality (VR), facilitates instruction when compared to traditional approaches, which have shown strong limitations in their ability to engage young students who have grown up in the smartphone culture of continuous entertainment. Moreover, not all educational centers or organizations are able to incorporate specialized labs or equipment for training and instruction. Using VR applications, it is possible to reproduce training programs with a high rate of similarity to real programs, filling the gap in traditional training. In addition, it reduces unnecessary investment and prevents economic losses, avoiding unnecessary damage to laboratory equipment. The contribution of this work focuses on the development of a VR-based teaching and training application for the condition-based maintenance of induction motors. The novelty of this research relies mainly on the use of natural interactions with the VR environment and the design’s optimization of the VR application in terms of the proposed teaching topics. The application is comprised of two training modules. The first module is focused on the main components of induction motors, the assembly of workbenches and familiarization with induction motor components. The second module employs motor current signature analysis (MCSA) to detect induction motor failures, such as broken rotor bars, misalignments, unbalances, and gradual wear on gear case teeth. Finally, the usability of this VR tool has been validated with both graduate and undergraduate students, assuring the suitability of this tool for: (1) learning basic knowledge and (2) training in practical skills related to the condition-based maintenance of induction motors.},
keywords = {eye tracking, fault detection, FFT, induction motors, SELECTED, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
The incorporation of new technologies as training methods, such as virtual reality (VR), facilitates instruction when compared to traditional approaches, which have shown strong limitations in their ability to engage young students who have grown up in the smartphone culture of continuous entertainment. Moreover, not all educational centers or organizations are able to incorporate specialized labs or equipment for training and instruction. Using VR applications, it is possible to reproduce training programs with a high rate of similarity to real programs, filling the gap in traditional training. In addition, it reduces unnecessary investment and prevents economic losses, avoiding unnecessary damage to laboratory equipment. The contribution of this work focuses on the development of a VR-based teaching and training application for the condition-based maintenance of induction motors. The novelty of this research relies mainly on the use of natural interactions with the VR environment and the design’s optimization of the VR application in terms of the proposed teaching topics. The application is comprised of two training modules. The first module is focused on the main components of induction motors, the assembly of workbenches and familiarization with induction motor components. The second module employs motor current signature analysis (MCSA) to detect induction motor failures, such as broken rotor bars, misalignments, unbalances, and gradual wear on gear case teeth. Finally, the usability of this VR tool has been validated with both graduate and undergraduate students, assuring the suitability of this tool for: (1) learning basic knowledge and (2) training in practical skills related to the condition-based maintenance of induction motors.