RT info:eu-repo/semantics/preprint
T1 Tool wear monitoring using an online, automatic and low cost system based on local texture
A1 García Ordás, María Teresa
A1 Alegre Gutiérrez, Enrique
A1 Alaiz Rodríguez, Rocío
A1 González Castro, Víctor
A2 Ingenieria de Sistemas y Automatica
K1 Ingeniería de sistemas
K1 Tool wear
K1 Texture description
K1 Patches
K1 Wear region
K1 3306 Ingeniería y Tecnología Eléctricas
K1 3310.03 Procesos Industriales
AB [EN] In this work we propose a new online, low cost and fast approach basedon computer vision and machine learning to determine whether cutting toolsused in edge pro le milling processes are serviceable or disposable based ontheir wear level. We created a new dataset of 254 images of edge pro le cuttingheads which is, to the best of our knowledge, the  rst publicly availabledataset with enough quality for this purpose. All the inserts were segmentedand their cutting edges were cropped, obtaining 577 images of cutting edges:301 functional and 276 disposable. The proposed method is based on (1)dividing the cutting edge image in di erent regions, called Wear Patches(WP), (2) characterising each one as worn or serviceable using texture descriptorsbased on di erent variants of Local Binary Patterns (LBP) and (3)determine, based on the state of these WP, if the cutting edge (and, therefore,the tool) is serviceable or disposable. We proposed and assessed  vedi erent patch division con gurations. The individual WP were classi edby a Support Vector Machine (SVM) with an intersection kernel. The bestpatch division con guration and texture descriptor for the WP achieves anaccuracy of 90.26% in the detection of the disposable cutting edges. Theseresults show a very promising opportunity for automatic wear monitoring inedge pro le milling processes.Keywords: Tool wear, texture description
PB Elsevier
SN 0888-3270
LK https://hdl.handle.net/10612/17635
UL https://hdl.handle.net/10612/17635
NO García-Ordás, M. T., Alegre-Gutiérrez, E., Alaiz-Rodríguez, R., & González-Castro, V. (2018). Tool wear monitoring using an online, automatic and low cost system based on local texture. Mechanical Systems and Signal Processing, 112, 98-112. https://doi.org/10.1016/J.YMSSP.2018.04.035
DS BULERIA. Repositorio Institucional de la Universidad de León
RD Jul 11, 2024