Learning group-technology part families from solid models by parallel distributed processing

This paper presents a new approach to part classification in group technology. It advocates the introduction of a feature-based solid-modelling scheme for part representation which, in turn, helps in identifying features of interest. The extracted features of the part are then used to determine the part family to which the part belongs. A parallel distributed processing (PDP) model has been utilised in developing a learning module for the part-classification problem. The proposed model has been implemented in the Unix environment of a Sun work-station. The usefulness of the proposed model has been validated with an example of 16 parts in three part families.