Xq. Li et al., Intelligent tool wear identification based on optical scattering image andhybrid artificial intelligence techniques, P I MEC E B, 213(2), 1999, pp. 191-196
Citations number
21
Categorie Soggetti
Engineering Management /General
Journal title
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE
Tool wear monitoring is crucial for an automated machining system to mainta
in consistent quality of machined parts and prevent damage to the parts dur
ing the machining operation. A vision-based approach is presented for tool
wear identification in finish turning using an adaptive resonance theory (A
RT2) neural network embedded with fuzzy classifiers. The proposed approach
is established upon the fact that the optical scattering image of a turned
surface is related to the wear of the cutting tool. By applying the techniq
ue of the ART2 neural network embedded with fuzzy classifiers, the state of
wear of the turning tool is determined from captured images obtained by la
ser scattering from the machined surfaces of the workpiece. This approach i
s not unlike the visual inspection of the surface of a machined workpiece t
o determine the state of wear of a cutting tool by an expert machinist. How
ever, experimental results indicate that the conventional technique of meas
uring surface finish does not give values that correlate well with tool wea
r. On the other hand, the laser scattering image provides a good indication
of the tool wear as it is not readily affected by buildup edge or cold-wel
ded material, scratches and other disruptive defects on the turned surface
as the tool wears. In this paper, the theory on the laser scattering image
and the principle of tool wear identification are described. Based on the s
cattering images, the proposed approach can correctly identify the conditio
n of 'significant wear' prior to the rapid tool wear stage for the cutting
tool.