Knowledge-based incremental sheet metal free-forming using probabilistic density functions and voronoi partitioning

A knowledge-based automation approach for a special incremental sheet metal free-forming process is introduced. A database consisting of tool path information for characteristic component shapes is the basis of the approach. Each manufacturing process of a specific component is fully described through the tool path coordinates and order of forming steps. For the knowledge-based automation approach, tool paths are represented as probabilistic stroke density functions. New part shapes can be deduced by homogeneous transformation and interpolation of the stroke density functions in the database. The order of the incremental forming steps gets lost, because density functions are based on a first derivative of the underlying stroke distribution. In this work, a method is presented to derive a suitable stroke order from the database, which enables full automation of the complex cataloging and subsequent derivation of transformed tool paths for arbitrary component manufacturing. Therefore, Voronoi partitioning is used to subdivide tool paths. The obtained subdomains can be adapted according to the stroke density function and allow for an accurate determination of the stroke order for arbitrary tool paths. Finally, the effectiveness of the proposed method is validated and verified on the basis of real experiments. (C) 2019 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/) Selection and peer-review under responsibility of the organizing committee of SHEMET 2019.