Intelligent system for extraction of product data from CADD models

This paper reports a system for automatic extraction of geometric and non-g eometric part information from 'engineering drawings' created using compute r-aided design and drafting (CADD) tools. A heuristic search is employed to interpret the characteristic attributes of dimension sets that denote line ar, diametrical, radial and angular dimensions. Textual callouts are proces sed using natural language processing (NLP) techniques to interpret informa tion related to part/feature function and related processes. The part infor mation so recognized is represented using object oriented paradigm (OOP) su itable for linking to the downline CAD/CAM activities of the product cycle. The system, thus provides an effective alternative for design automation u sing CADD models. (C) 2001 Elsevier Science B.V. All rights reserved.