Vision Based Surface Roughness Characterization of Flat Surfaces Machined with EDM. 2019-28-0148
Controlling and measuring the surface roughness is an important issue in quality manufacturing. Conventional method of measuring the surface roughness using stylus instrument is an intrusive and contact type hence it is not suitable for online measurement which result, there is an increasing need for a reliable, non-contact method of surface roughness measurement. Over the few years, advances in image processing techniques have provided the basis for developing image based surface roughness measuring techniques.
In this investigation, a vision system and image processing tools were used to develop reliable surface roughness characterization technique for Electrical Discharge Machined surfaces. A CMOS camera fitted with zoom 6000 lens system having optical magnification up to 45X and red LED light source were used for capturing images of machined surfaces with different surface roughness values. A signal vector can be generated from image pixel intensity and can be processed using MATLAB software. From the signal vector, the mean and the standard deviations were obtained. The mean of the images signal vector correlates well with the stylus measured roughness parameters Ra, Rda and Rdq. Hence the technique may be preferred for online surface roughness characterization of Electrical Discharge Machined surfaces.