Datum
2022-09-09Autor
Decke, JensEngelhardt, AnnaRauch, LukasDegener, SebastianSajadifar, Seyed VahidScharifi, EmadSteinhoff, KurtNiendorf, ThomasSick, BernhardMetadata
Zur Langanzeige
Aufsatz
Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods
Zusammenfassung
The present work focuses on the prediction of the hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. The data considered focus on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of 200°C to 400°C and at strain rates ranging from 0.001 s-¹ to 0.1 s-¹ were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the Zerilli–Armstrong model (Z–A) as reference. Related work focuses on predicting single data points of the curves that the model was trained on. Due to the way data were split with respect to training and testing data, it is possible to predict entire stress–strain curves. The model allows to decrease the number of required laboratory experiments, eventually saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z–A model, the extreme Gradient Boosting model (XGB) showed superior results, i.e., the highest error reduction of 91% with respect to the Mean Squared Error.
Zitierform
In: Crystals Volume 12 / Issue 9 (2022-09-09) eissn:2073-4352Zitieren
@article{doi:10.17170/kobra-202304217875,
author={Decke, Jens and Engelhardt, Anna and Rauch, Lukas and Degener, Sebastian and Sajadifar, Seyed Vahid and Scharifi, Emad and Steinhoff, Kurt and Niendorf, Thomas and Sick, Bernhard},
title={Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods},
journal={Crystals},
year={2022}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2022$n2022 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/14621 3000 Decke, Jens 3010 Engelhardt, Anna 3010 Rauch, Lukas 3010 Degener, Sebastian 3010 Sajadifar, Seyed Vahid 3010 Scharifi, Emad 3010 Steinhoff, Kurt 3010 Niendorf, Thomas 3010 Sick, Bernhard 4000 Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods / Decke, Jens 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/14621=x R 4204 \$dAufsatz 4170 5550 {{Aluminiumlegierung}} 5550 {{Maschinelles Lernen}} 5550 {{Fließgrenze}} 7136 ##0##http://hdl.handle.net/123456789/14621
2023-04-24T08:35:47Z 2023-04-24T08:35:47Z 2022-09-09 doi:10.17170/kobra-202304217875 http://hdl.handle.net/123456789/14621 eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ machine learning eXtreme Gradient Boosting Zerilli-Armstrong flow stress AA7075 600 670 Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods Aufsatz The present work focuses on the prediction of the hot deformation behavior of thermo-mechanically processed precipitation hardenable aluminum alloy AA7075. The data considered focus on a novel hot forming process at different tool temperatures ranging from 24°C to 350°C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of 200°C to 400°C and at strain rates ranging from 0.001 s-¹ to 0.1 s-¹ were carried out on four different material conditions. The present paper mainly focuses on a comparative study of modeling techniques based on Machine Learning (ML) and the Zerilli–Armstrong model (Z–A) as reference. Related work focuses on predicting single data points of the curves that the model was trained on. Due to the way data were split with respect to training and testing data, it is possible to predict entire stress–strain curves. The model allows to decrease the number of required laboratory experiments, eventually saving costs and time in future experiments. While all investigated ML methods showed a higher performance than the Z–A model, the extreme Gradient Boosting model (XGB) showed superior results, i.e., the highest error reduction of 91% with respect to the Mean Squared Error. open access Decke, Jens Engelhardt, Anna Rauch, Lukas Degener, Sebastian Sajadifar, Seyed Vahid Scharifi, Emad Steinhoff, Kurt Niendorf, Thomas Sick, Bernhard 19 Seiten doi:10.3390/cryst12091281 Aluminiumlegierung Maschinelles Lernen Fließgrenze publishedVersion eissn:2073-4352 Issue 9 Crystals Volume 12 false 1281
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: