Vision-based surface roughness inspection of machined aluminium parts
by Rene Kamguem; Victor Songmene; Jean-Pierre Kenne; Souheil Antoine Tahan
International Journal of Machining and Machinability of Materials (IJMMM), Vol. 12, No. 3, 2012

Abstract: This article presents an experimental research project which aims to control the roughness of aluminium parts produced by high-speed milling using vision data. A CCD camera is used to acquire images and a suitable processing system which uses machining data helps deriving information needed to estimate the surface roughness. A preliminary study on effect of machining parameters on part surface quality shows that roughness is influenced primarily by the feed per tooth, followed by the coating type used, and lastly, by workpiece material. In view of this information, we implemented a data processing tool allowing real-time roughness estimation based on the image captured by a camera and the feed per tooth. This tool takes into account the type of workpiece material and the cutting tool used (coatings and geometry). The results are in good agreement with data obtained using a traditional contact measurement system. The overall results of this study would encourage developments in the field of robust 3D vision system for online measurement of roughness for industrial use.

Online publication date: Sat, 23-Aug-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Machining and Machinability of Materials (IJMMM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com