Extraction of dimension requirements from engineering drawings for supporting quality control in production processes

Abstract

Engineering drawings accompany a workpiece throughout its production process and include information about the dimensions and tolerances as well as the associated regulatory standards. Even though the construction and manufacturing process of a workpiece can be almost entirely performed automatically, the design and use of engineering drawings is still not fully integrated in the automated production process. This work provides DigiEDraw, a conceptual approach as well as a prototype to extract dimensioning information from engineering drawings and to integrate this information into the production process to facilitate and optimize quality control. The extraction process is based on 2D clustering. The challenge is to determine the parameters to distinguish clusters representing different dimensioning information. The approach uses DBSCAN, achieving a recall value of over 88%. The applicability of DigiEDraw is demonstrated based on a real-world manufacturing process.