Paper Titles
Numerical Investigation and Optimization of Blank-Holder and Magnetorheological Actuators Configurations for Deep Drawing Objectives
p.83
Feature Based Investigation of the Forming Behavior of Titanium Grade 1 for Bipolar Plate Manufacturing
p.95
Pressure Wave Analysis in Electrohydraulic Forming - A Multiple Sensor Approach
p.107
Numerical Modeling of Controlled Multi-Step Expansion in Plasma Arc Welded AISI 316 Stainless-Steel Tubes
p.115
Multivariate Analysis of Scrap Web Sheared Surface Roughness for Punch Wear Indicators in Sheet-Metal Forming
p.125
Extending the Process Window of Sheet Injection in AW6082-T6 Aluminium via Localised Laser Heat Treatment
p.135
Gas Based Hot Forming of Micro-Channels for High Strength Aluminum Alloy Sheets
p.143
Mechanical Characterization by Profilometry-Based Indentation Plastometry of Locally Heat-Treated Blanks for Sheet Injection Applications
p.151
Influence of Process Parameter Variations on Stamping-Bending Component Quality
p.159

Multivariate Analysis of Scrap Web Sheared Surface Roughness for Punch Wear Indicators in Sheet-Metal Forming

Article Preview
View Pdf By email

Abstract:

In precise sheet-metal forming operations such as fine blanking, the closed tool design precludes direct observation during production, which makes indirect monitoring of punch wear necessary. Previous work has shown that the sheared surfaces of the scrap web can be used to infer the punch wear through spatial correlation analysis of areal roughness parameters. However, these correlations have so far each explained only a limited portion of the variance and have only been investigated for a single punch geometry, leaving their robustness and generalizability open to question. In this work, multivariate regression approaches and feature importance analysis are used to combine complementary areal roughness parameters and generate robust indicators of punch wear. The plausibility of these indicators is validated by linking the correlated scrap web sheared surface features to physically interpretable wear mechanisms, such as worn surface area or punch breakage. Furthermore, the approach is extended to multiple punch geometries to examine the extent to which the identified correlation patterns can be transferred to different tool designs and process conditions. The results demonstrate the generalizability of spatial correlation-based indicators across different geometries and process conditions.

You have full access to the following eBook
Incremental and Sheet Metal Forming Read eBook

Info:

Periodical:

Solid State Phenomena (Volume 389)

Pages:

125-133

DOI:

https://doi.org/10.4028/p-8Tbjxt

Citation:

Cite this paper

Online since:

April 2026

Authors:

Jiyoung Moon*, Alexander Frigge, Philipp Niemietz, Tim Herrig, Thomas Bergs

Keywords:

Multivariate Analysis, Punch Wear Assessment, Sheet-Metal Forming

Funder:

The publication of this article was funded by the RWTH Aachen University 10.13039/501100007210

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Share:

Citation:

* - Corresponding Author

References

[1] Siemens AG, The True Cost of Downtime 2024 (2024).

Google Scholar

[2] C. Kubik, M. Becker, D.-A. Molitor, P. Groche, Towards a systematical approach for wear detection in sheet metal forming using machine learning, Prod. Eng. Res. Devel. 17 (2023) 21–36.

DOI: 10.1007/s11740-022-01150-x

Google Scholar

[3] M. Becker, P. Niemietz, T. Bergs, Study on the explainability of deep learning models for time series analysis in sheet metal forming, Procedia CIRP 126 (2024) 727–732.

DOI: 10.1016/j.procir.2024.08.298

Google Scholar

[4] P. Niemietz, M. Fencl, T. Bergs, Study on learning efficient stroke representations in clocked sheet metal processing: theoretical and practical evaluation, Prod. Eng. Res. Devel. 17 (2023) 279–289.

DOI: 10.1007/s11740-023-01182-x

Google Scholar

[5] M. Unterberg, Data-driven indirect tool condition monitoring in sheet-metal stamping. Dissertation, 1st ed.

Google Scholar

[6] A. Frigge, M. Unterberg, T. Kaufmann, P. Niemietz, T. Bergs, Enhancing Crack Prediction in Fine Blanking Through Multi-sensor Data Fusion, in: W.-G. Drossel, S. Ihlenfeldt, M. Dix (Eds.), Production at the leading edge of technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024, Springer, Cham, 2025, p.153–161.

DOI: 10.1007/978-3-031-86893-1_17

Google Scholar

[7] L. Ortjohann, M. Becker, P. Niemietz, T. Bergs, Material-data-driven prediction of sheared surface tears of fine blanked parts, in: Material Forming: ESAFORM 2024, Materials Research Forum LLC, 2024, p.1416–1425.

DOI: 10.21741/9781644903131-157

Google Scholar

[8] J. Moon, M. Unterberg, P. Niemietz, T. Bergs, Spatial Correlation Analysis between Punch and Scrap Web Sheared Surface Roughness for Indirect Punch Wear Assessment in Sheet-metal Forming, in: Congress of the German Academic Association for Production Technology WGP 2025 (accepted).

Google Scholar

[9] L. Prokhorenkova, G. Gusev, A. Vorobev, A.V. Dorogush, A. Gulin, CatBoost: unbiased boosting with categorical features (2017).

Google Scholar