Image-Based Machine Learning of In Situ Captured Images of Die-Workpiece Interface in Forging

Abstract:

The lubricant thickness in cold forging was estimated by machine learning of the in situ captured images of the die–workpiece contact interface. The images were in situ captured by a high-speed camera from the backside of the transparent glass die during forging of commercially pure aluminum workpiece. On the other hand, the images of the lubricated workpiece were individually captured as training images for random forest with classification. The classification accuracy of the lubricant thickness was confirmed to be approximately 75% (classification ability: 5–10 μm in lubricant thickness) in the training images with 22,500 px (50 px/mm). The in situ captured images of the die–workpiece contact interface during forging were classified by random forest using the training images. The estimated lubricant thickness of the in situ captured image almost agreed with the lubricant thickness estimated from the mean brightness value of the in situ captured image.

• Periodical: Defect and Diffusion Forum (Volume 441)
• Pages: 39-43
• DOI: https://doi.org/10.4028/p-Ex7OhS
• Online since: March 2025
• Authors: Ryo Matsumoto*, Shusuke Kunisawa, Yusaku Nakamura, Hiroshi Utsunomiya
• Keywords: Extrusion, Forging, Image Analysis, Lubrication, Machine Learning

References

[1] A. Azushima, Direct observation of contact behavior to interpret the pressure dependence of the coefficient of friction in sheet metal forming, CIRP Ann. Manuf. Technol., 44-1 (1995) 209–212.

DOI: 10.1016/s0007-8506(07)62309-9

[2] T. Shimizu, H. Kobayashi, J. Vorholt, M. Yang, Lubrication analysis of micro-dimple textured die surface by direct observation of contact interface in sheet metal forming, Metals, 9-9 (2019) 917.

DOI: 10.3390/met9090917

[3] Y. Abe, K. Ichimura, K. Mori, In-situ observation of behavior of containing ceramic particles in lubricant in ironing using glass die, Proc. 71st Jpn. Jt. Conf. Technol. Plast., (2020), 201–212.

[4] K. Hirade, T. Morishima, A. Yanagida, Direct measurement of lubricant film thickness during flat drawing process by fluorescence method, Proc. 74th Jpn. Jt. Conf. Technol. Plast., (2023), 59–60.

[5] H. Utsunomiya, Y. Terada, K. Ono, R. Matsumoto, In situ observation of the interface between a roll and a sheet in flat rolling process, CIRP Ann. Manuf. Technol., 71-1 (2022) 245–248.

DOI: 10.1016/j.cirp.2022.04.012

[6] R. Matsumoto, Y. Nakamura, H. Utsunomiya, In situ observation of re-lubrication of die–workpiece interface during forging with ram pulsation, J. Manuf. Process., 101 (2023) 675–686.

DOI: 10.1016/j.jmapro.2023.06.017

[7] Z. Hao, Z. Li, F. Ren, S. Lv, H. Ni, Strip steel surface defects classification based on generative adversarial network and attention mechanism, Metals, 12-2 (2022) 311.

DOI: 10.3390/met12020311

[8] J.W. Verhoeven, Glossary of terms used in photochemistry (IUPAC Recommendations 1996), Pure and Applied Chemistry, 68-12 (1996) 2230.

DOI: 10.1351/pac199668122223