• search hit 1 of 1
Back to Result List

Neural networks for inline segmentation of image data in punching processes

  • Punching is a process that is sensitive to a multitude of parameters. The estimation of part and punch quality is often based on expert knowledge and trial-and-error methods, mostly carried out as a separate offline process analysis. In a previous study, we developed an optical inline monitoring system with subsequent image processing which showed promising results in terms of capturing every manufactured part, but was limited by slow image processing. Here, we present a more efficient image processing technique based on neural networks. For our approach, we manually identify the burnish parts in images based on criteria established via an expert survey in order to generate a training dataset. We then employ a combination of region-based and boundary-based losses to optimize the neural network towards a segmentation of the burnish surface which allows for an accurate measurement of the burnish height. The hyperparameter optimization is based on custom evaluation metrics that reflect the requirements of the burnish surfacePunching is a process that is sensitive to a multitude of parameters. The estimation of part and punch quality is often based on expert knowledge and trial-and-error methods, mostly carried out as a separate offline process analysis. In a previous study, we developed an optical inline monitoring system with subsequent image processing which showed promising results in terms of capturing every manufactured part, but was limited by slow image processing. Here, we present a more efficient image processing technique based on neural networks. For our approach, we manually identify the burnish parts in images based on criteria established via an expert survey in order to generate a training dataset. We then employ a combination of region-based and boundary-based losses to optimize the neural network towards a segmentation of the burnish surface which allows for an accurate measurement of the burnish height. The hyperparameter optimization is based on custom evaluation metrics that reflect the requirements of the burnish surface identification problem as well. After comparing different neural network architectures, we focus on optimizing the backbone of the UNet++ structure for our task. The promising results demonstrate that neural networks are indeed capable of an inline segmentation that can be used for measuring the burnish surface of punching parts.show moreshow less

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Maximilian LorenzORCiDGND, Robert MartinORCiD, Thomas Brücklmayr, Christian DonhauserGND, Bernd R. PinzerORCiD
DOI:https://doi.org/10.1007/s00170-023-11784-5
Identifier:1433-3015 OPAC HS OPAC extern
Identifier:0268-3768 OPAC HS OPAC extern
Parent Title (English):The International Journal of Advanced Manufacturing Technology
Publisher:Springer
Place of publication:London
Document Type:Article
Language:English
Date of Publication (online):2023/07/12
Year of first Publication:2023
Number of pages:14 Seiten
Institutes:EPT – Institut für Effiziente Produktionstechnik
IMS - Institut für Maschinelles Sehen
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 62 Ingenieurwissenschaften
Open Access:open_access
Research focus:FSP2: Mobilität
FSP3: Produktion
Publication Lists:Donhauser, Christian
Lorenz, Maximilian
Pinzer, Bernd
Publication reviewed:begutachtet
Licence (German):Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International
Release Date:2023/07/12
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.