Notice of RetractionA study of support vector regression for surface characteristics in-process optical measurement

Notice of Retraction

After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.

We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.

The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.

This paper aims to introduce a new model into surface characteristics in-process optical measurement in machining process. The opaque property of the coolants would be a problem for in-process measurement of workpiece surface characteristics using optical methods during grinding operations. A transparent window method that can produce an optically clean zone on the surface is employed to solve this problem. The surface scattered images of specimens in the clean zone are captured and some features are extracted from the images. A machine learning technique called support vector regression (SVR) is proposed to establish the relationship between these features, optical measurement system and surface roughness, and consequently determine surface roughness. Flow rate of the transparent fluid, the thickness of the fluid layer, scattering feature along the main direction of the scattering stripe, standard deviation perpendicular to the main direction of the scattering stripe and gray feature of the scattered image are supplied as input parameters to the SVR model and the surface roughness is predicted. Experiments have been carried out on some standard specimens with different surface roughness values, and the results show that the new model could estimate the surface roughness with an average percentage deviation of 0.6145%. Therefore, the SVR model is suitable for in-process optical measurement of surface characteristics with a satisfactory accuracy.