Issue |
EPJ Web Conf.
Volume 321, 2025
VII International Conference on Applied Physics, Information Technologies and Engineering (APITECH-VII-2025)
|
|
---|---|---|
Article Number | 01003 | |
Number of page(s) | 5 | |
Section | Applied and Industrial Physics: Fluid Dynamics, Thermodynamics, and Mechanical Systems | |
DOI | https://doi.org/10.1051/epjconf/202532101003 | |
Published online | 10 March 2025 |
https://doi.org/10.1051/epjconf/202532101003
Toolset profiling for rotary draw bending of waveguides
Siberian Federal University, 79 Svobodny Pr., Krasnoyarsk, 660041, Russia
* Corresponding author: ikudryavcev@sfu-kras.ru
Published online: 10 March 2025
The paper discusses the problem of bending quality of thin-walled structures of waveguides of rectangular cross section. Modern methods of solving the bending problems have been studied, from empirical relations to the use of artificial intelligence methods to achieve a minimum bending radius without product defects. It has been shown that the quality of the bend depends on a combination of many input parameters that are not always controllable. Even with the current level of computer performance, taking into account all these external factors, leads to the need to solve the probabilistic problem of a large number of variables, the unambiguous answer of which can currently only be given by approaches based on artificial intelligence. Despite the development and popularity of artificial intelligence methods, this way is still very expensive and long, so we propose a solution based on creating bending conditions that limit unwanted deformation and actually lead to die forming of the product. As a result, the resulting product and its quality parameters should be practically independent of various external factors and only the correctness of calculations and the accuracy of manufacturing the toolset of the pipe bending machine should be determined.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.