OPTICAL MEASUREMENT SYSTEM FOR INLINE INSPECTION IN CARBIDE INSERT PRODUCTION

Robert Schmitt, Tilo Pfeifer, Yu Cai, Huchen Zhang, Nils König

Abstract

In steps of the production chain of carbide inserts, such as unloading or packaging, the conformity test of the insert type is done manually, which causes a statistic increase of errors due to monotony and fatigue of the worker and the wide variety of the insert types. A machine vision system is introduced that measures and inspects the chip-former geometry of the inserts, the most significant insert quality feature in the production line automatically. The proposed two image processing approaches for insert geometry recognition, edge-based and feature-based method, are developed with utilisation of a priori knowledge of the carbide inserts and of the production environment. These new methods have been tested on several inserts of different types and the results have shown that the prevalent insert types can be inspected and robustly classified in real production environment and therefore improves the manufacturing automation.

Keywords

optical measurement, testing and inspection, industrial image processing, part recognition, automation

Download

IMEKO-TC2-2010-15.doc

DOI

-

IMEKO TC

TC2 - Photonics

Back to the proceedings