Abstract
The PoDFA inclusion measurement is achieved by identifying the inclusions and their concentration in the melt for each type with a trained operator. The standard technique is realized by using a square grid with an optical microscope to count the total area with each detected square. This manual and non-efficient method requires a lot of time and effort and can generate important variations in PoDFA results for reproducibility and repeatability. In the past, there were many unsuccessful attempts to automatically detect, count, and classify all inclusion types due to the complexity of the application. Disc sampling, image artifacts, polishing defects, and metallurgical constituents are some examples that can interfere with the inclusion detection and the measurement methodology. Commercial image analysis systems with threshold options and Boolean logical operations are not sufficient to automate the solution. The implementation of artificial intelligence technologies such as supervised machine learning algorithms are necessary to automate this complex method. The benchmarking study was achieved between the standard PoDFA methodology compared to the artificial intelligent way. Results show that the new technique exhibits a good correlation and a high potential for industrial use.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wannasin, J., Schwam D. and Wallace J.F. Evaluation of Methods for Metal Cleanliness Assessment in Die Casting, Elsevier, Journal of Material Processing Technology. Volume 191. Issues 1-3, August 2007, Pages 242-246.
L. Liu and F.H. Samuel. Assessment of melt cleanliness in A356.2 aluminium casting alloy using the porous disc filtration apparatus technique: Part I Inclusion measurements, Journal of Material Science, Volume 32, 1997, Pages 5901-5925.
Kitaoka, S., Evaluation of the Melt Cleanliness by K-mold Test, COM 2001, Conference paper, Pages 13-24.
Bernd Prillhofer et al., Nonmetallic inclusions in the secondary aluminum industry for the production of aerospace alloys, TMS Light Metals 2008, Conference paper, Pages 603-608.
Gökelma M. et al., Assessment of Settling Behavior of Particles with Different Shape Factors by LiMCA Data Analysis. Light Metals. 2016. Pages 843–848.
D. Doutre, B. Gariépy, J. P. Martin & G. Dubé., Aluminium Cleanliness Monitoring: Methods and Applications in Process Development and Quality Control, Light Metals 2016, Volume 3, Cast Shop for Aluminum Production. Pages 296–304.
P. V. Evans, P. G. Enright and R. A. Ricks. Molten metal cleanliness: recent developments to improve measurement reliability. TMS Light Metals 2018, Pages 839-846.
Stanica, Carmen & Moldovan, Petru., Aluminum melt cleanliness performance evaluation using PoDFA (porous disk filtration apparatus) technology, UPB Scientific Bulletin, Series B: Chemistry and Materials Science, January 2009, Vol. 71, Iss. 4, Pages 107–114
ABB. Bomem, Metallographic Evaluation of PoDFA Inclusions Residue, Alcan, ARDC, Method Grid, 2012-96., URL: https://library.e.abb.com/public/d1511d760475946f85256dff0059f3a5/PoDFA%20report%20example%202006.pdf.
Kazakov A. A., Kiselev D. V., Kur A., PoDFA-based computer-aided analysis of non-metallic inclusions in aluminium alloys using image analysis, Journal of Material Science, Tsvetnye Metally, 2019, #3.
Kazakov A. A., Kiselev D. V., Kur A., Automated evaluation of nonmetallic inclusions in aluminum alloys by PoDFA method using image analysis., Tsvetnye Metally, April 2019.
Choudhary, Kamal et al., Recent advances and applications of deep learning methods in material science, Computational Material, Volume 8, 2022. 26 pages.
Sosa, John, Sul, Pavel and Small, Laurence. Automated micrograph analysis enables pionnering R&D, ASM International, Advanced Material & Processes, January 2019. Pages 16-21.
Hannes Zedel, Robert Fritzsch, Shahid Akhtar and Ragnhild E. Aune. Automated Metal Cleanliness Analyzer (AMCA—An Alternative Assessment of Metal Cleanliness in Aluminum Melts, Light Metals 2021, February 2021, Pages 778-784.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Minerals, Metals & Materials Society
About this paper
Cite this paper
Gauthier, P., Bilodeau, V., Sosa, J. (2024). A PoDFA Benchmarking Study Between Manual and AI-supervised Machine Learning Methods to Evaluate Inclusions in Wrought and Foundry Aluminum Alloys. In: Wagstaff, S. (eds) Light Metals 2024. TMS 2024. The Minerals, Metals & Materials Series. Springer, Cham. https://doi.org/10.1007/978-3-031-50308-5_121
Download citation
DOI: https://doi.org/10.1007/978-3-031-50308-5_121
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50307-8
Online ISBN: 978-3-031-50308-5
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)