Wire electrical discharge machining (WEDM) is a thermoelectrical machining process capable of accurately machining parts with varying hardness or intricate shapes. Improvement of the process productivity by avoiding wire breakage is one of the main research fields in wire-cut EDM. In a wire-cut EDM, the electrode is the only element that requires frequent changes due to failure. In order to replace the wire electrode in time, there is an essential need to keep a watch on the condition of the wire electrode during the machining process. Texture of the machined surface is dramatically affected by the worn electrode. Electrode status monitoring can be done by analyzing the surface of machined component. The measurements of surface roughness by traditional devices are time consuming and also obtained by scratching the surface of components. Consequently, these problems can be overcome by the vision system. In this work, to determine the surface roughness of the WEDM components, a machine vision system has been utilized. In order to check the effectiveness of the vision-based results, various surface roughnesses were produced on WEDM using Design of Experiments technique. Stylus-based parameter Ra was acquired and compared with vision-based parameter (Ga). The experimental result indicates that with a reasonable accuracy and by using vision system, surface roughness could be predicted. Results clearly indicate that wire electrode status monitoring in WEDM can be successfully carried out by analyzing the image of surfaces.
[1]
G. Dilli Babu,et al.
Evaluation of surface roughness using machine vision
,
2010,
INTERACT-2010.
[2]
Srinagalakshmi Nammi,et al.
Effect of surface lay in the surface roughness evaluation using machine vision
,
2014
.
[3]
M. Murali Krishna,et al.
On Line Surface Roughness Measurement Using Image Processing and Machine Vision
,
2007,
World Congress on Engineering.
[4]
Gürcan Samtaş,et al.
Measurement and evaluation of surface roughness based on optic system using image processing and artificial neural network
,
2014
.
[5]
M. B. Kiran,et al.
Evaluation of 3D Surface Roughness Parameters of EDM Components Using Vision System
,
2014
.
[6]
Bijan Shirinzadeh,et al.
An evaluation of surface roughness parameters measurement using vision-based data
,
2007
.