A priori knowledge-based recognition and inspection in carbide insert production

Abstract

In processes of the production chain of carbide inserts, such as unloading or packaging, the conformity test of the insert type is performed manually, which causes a statistic increase of errors due to monotony and fatigue of workers and the wide variety of insert types. A machine vision system is introduced that automatically measures and inspects the chip-former geometry of inserts, the most significant insert quality feature, in the production line. The proposed recognition approach is developed with utilisation of a priori knowledge of carbide inserts and of production environments. This new method has been tested on several inserts of different types. Test results show that prevalent insert types can be inspected and robustly classified in a real production environment and therefore the manufacturing automation can be improved.