A non-contact approach for surface roughness prediction in CNC turning using a linear regression model

• Published in: Materials today : proceedings Vol. 26; pp. 350 - 355
• Main Authors: Patel, Dhiren R., Kiran, M.B.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01-01-2020
• Subjects: Linear regression; Machine vision system; Roughness parameters; Surface profilometer; Texture features; Machine vision system; Linear regression; Texture features; Surface profilometer; Roughness parameters
• ISSN: 2214-7853; 2214-7853
• DOI: 10.1016/j.matpr.2019.12.029

At present, the combination of non-contact type optical techniques and machine vision systems has a huge significance in the assessment of surface roughness. The non-contact measurement methods seem to have greater advantages over the conventional stylus method. Traditionally used contact-type surface roughness measurement technique assesses the roughness of machined component in a single line which is overcome by optical-based techniques and machine vision techniques with the capability to assess the whole machined surface. This paper deals with selected contact type stylus method and non-contact type machine vision methods for components prepared by turning of AISI 1040 steel at a variety of feed rates. The correlations have been developed between two dimensional (2D) surface roughness parameter and texture features for the components. The 2D surface roughness parameters have been recorded using a contact-type surface profilometer. On the other hand, the texture features have been extracted using a Gray level co-occurrence matrix algorithm (GLCM) and machine vision system. The correlation has been developed between extracted texture features of machined surfaces and measured 2D surface roughness parameters. The linear regression analysis has been performed in order to predict the surface roughness of machined components. The comparative results reveal a maximum measurement difference of 15% between contact types and presented a non-contact type assessment.