Recognition of features in sheet metal parts manufactured using progressive dies

Feature recognition is an important stage in digital manufacturing as it supports activities such as automated process planning and part re-design. This paper describes a two-stage algorithm for recognising features in sheet metal parts which are manufactured using progressive dies. Representation of the part in neutral format (STEP AP203) facilitates the first stage of this algorithm in which the thickness faces are extracted in the form of chains. In the second stage, an extracted chain of faces is classified by, first, determining its topological and geometric characteristics and then comparing its characteristics with pre-set attributes for each feature. The system was developed in C++ and has been successfully tested on representative parts containing features ranging from simple bends to composite features, such as a cut-out with lance.