Burr Detection Using Image Processing in Milling Workpieces
- Virginia Riego del Castillo 1
- Lidia Sánchez-González 1
- Laura Fernández-Robles 1
- Manuel Castejón-Limas 1
-
1
Universidad de León
info
- Álvaro Herrero (coord.)
- Carlos Cambra (coord.)
- Daniel Urda (coord.)
- Javier Sedano (coord.)
- Héctor Quintián (coord.)
- Emilio Corchado (coord.)
Editorial: Springer Suiza
ISBN: 978-3-030-57801-5, 978-3-030-57802-2
Año de publicación: 2021
Páginas: 751-759
Congreso: International Conference on Soft Computing Models in Industrial and Environmental Applications SOCO (15. 2020. Burgos)
Tipo: Aportación congreso
Resumen
Manufacturing processes require to satisfy quality standards in the produced parts. In particular, the edge finishing must be burr-free, avoiding that it yields different problems such as wasting time removing them what increases the production cost and time. A burr can be noticed microscopically, but it can contain imperfections or evidence of poor piece design. In order to detect automatically this imperfections and to evaluate the quality of the edge finishing, this paper proposes a complete vision based method using image processing and linear regression. With the calculated function, the slope is isolated and compared to obtain quality assessment thresholds. Results validate the good performance of the proposed method to differenciate three types of burrs.