Publications
2021
1.
Fernández-Robles, Laura; Sánchez-González, Lidia; Díez-González, Javier; Castejón-Limas, Manuel; Pérez, Hilde
Use of image processing to monitor tool wear in micro milling Artículo de revista
En: Neurocomputing, vol. 452, pp. 333–340, 2021, (Publisher: Elsevier).
Resumen | Enlaces | BibTeX | Etiquetas: digital image processing, Micro Milling, Tool Breakage, Tool wear
@article{fernandez-robles_use_2021,
title = {Use of image processing to monitor tool wear in micro milling},
author = {Laura Fernández-Robles and Lidia Sánchez-González and Javier Díez-González and Manuel Castejón-Limas and Hilde Pérez},
url = {https://www.sciencedirect.com/science/article/pii/S0925231220317501},
year = {2021},
date = {2021-01-01},
journal = {Neurocomputing},
volume = {452},
pages = {333–340},
abstract = {This paper presents a digital image processing method for monitoring tool wear in micro milling, a process where tools wear quickly due to the small size and complex geometries of the machined components. Direct measurement of tool wear is not feasible due to the size of the tools, so this method uses captured images of the tool to analyze wear progression. The wear is measured in terms of flank wear, crater wear, and tool radius reduction. Several approaches, including morphological operations, k-means clustering, and the Otsu Multilevel algorithm, were compared to determine the best method for analyzing images. The results show a 5% difference between predicted and actual worn areas, meeting industrial standards. This method can be applied in industrial environments and used in collaborative robots to enhance automation and decision-making processes.},
note = {Publisher: Elsevier},
keywords = {digital image processing, Micro Milling, Tool Breakage, Tool wear},
pubstate = {published},
tppubtype = {article}
}
This paper presents a digital image processing method for monitoring tool wear in micro milling, a process where tools wear quickly due to the small size and complex geometries of the machined components. Direct measurement of tool wear is not feasible due to the size of the tools, so this method uses captured images of the tool to analyze wear progression. The wear is measured in terms of flank wear, crater wear, and tool radius reduction. Several approaches, including morphological operations, k-means clustering, and the Otsu Multilevel algorithm, were compared to determine the best method for analyzing images. The results show a 5% difference between predicted and actual worn areas, meeting industrial standards. This method can be applied in industrial environments and used in collaborative robots to enhance automation and decision-making processes.
2017
2.
Fernández-Robles, Laura; Azzopardi, George; Alegre, Enrique; Petkov, Nicolai
Machine-vision-based identification of broken inserts in edge profile milling heads Artículo de revista
En: Robotics and Computer-Integrated Manufacturing, vol. 44, pp. 276–283, 2017, (Publisher: Pergamon).
Resumen | Enlaces | BibTeX | Etiquetas: Automatic Identification, Edge Milling, machine vision, Tool Breakage
@article{fernandez-robles_machine-vision-based_2017,
title = {Machine-vision-based identification of broken inserts in edge profile milling heads},
author = {Laura Fernández-Robles and George Azzopardi and Enrique Alegre and Nicolai Petkov},
url = {https://www.sciencedirect.com/science/article/pii/S0736584515300806},
year = {2017},
date = {2017-01-01},
journal = {Robotics and Computer-Integrated Manufacturing},
volume = {44},
pages = {276–283},
abstract = {This paper presents a machine vision system designed to detect and identify broken inserts in edge milling head tools used for aggressive machining of thick plates. The system localizes inserts by detecting the screws, calculates the expected position and orientation of the cutting edge using geometrical operations, and compares it with the real edge to detect any deviations. The proposed method was evaluated on a new publicly available dataset, achieving a harmonic mean of precision and recall of 91.43%. The results indicate that the system is effective and ready for real-time implementation in monitoring machining tools.},
note = {Publisher: Pergamon},
keywords = {Automatic Identification, Edge Milling, machine vision, Tool Breakage},
pubstate = {published},
tppubtype = {article}
}
This paper presents a machine vision system designed to detect and identify broken inserts in edge milling head tools used for aggressive machining of thick plates. The system localizes inserts by detecting the screws, calculates the expected position and orientation of the cutting edge using geometrical operations, and compares it with the real edge to detect any deviations. The proposed method was evaluated on a new publicly available dataset, achieving a harmonic mean of precision and recall of 91.43%. The results indicate that the system is effective and ready for real-time implementation in monitoring machining tools.