DB4ISF: An incremental sheet forming database

DB4ISF DB4ISF is an incremental sheet forming database consisting of 76 forming experiments executed by the Chair of Production Systems at Ruhr-Universität Bochum. The databse consists of the following data: • General process data (tool radii, sheet thickness, step depth, ...) • CAD files (stl, sldprt including CAMWorks toolpaths) • Toolpaths (surface points and normal vectors) • Robot programs used for forming (KRL) • Digitization (CDB) • Deviation of every toolpath point in normal direction • Precalculated surface representations for machine learning ML4ISF ML4ISF is a Matlab Framework with a GUI for the application of machine learning in incremental sheet forming and fully compatible with the database. The framework offers the following features: • Data management • Toolpath import with various presets • Calculation of surface representations utilized for machine learning • Generation of training data tables for machine learning in python • Prediction of the forming accuracy with several provided artificial networks • Toolpath adjustments based on the prediction and smoothing of the path • Generation of Kuka robot programs (other exporters could be implemented) • Various plotting functions Prerequisites: • Surface toolpath with the corresponding normal vectors • STL file of the part The framework was developed for the application of double sided incremental forming (DSIF) utilizing two industrial robots where the supporting robot applies a defined support force. Other methods such as SPIF with NC-machines can be implemented with slight modifications. ML4ISF can be downloaded here: https://doi.org/10.5281/zenodo.10036335. Contact If you have any questions about the database, please contact: Dennis Möllensiep [e-mail] License and Reference This databse is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. A publication which explains the approach in detail will be added once it is published.