Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods
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 <inline-formula><math xmlns="...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/12/9/1281 |
| _version_ | 1797489651872694272 |
|---|---|
| author | Jens Decke Anna Engelhardt Lukas Rauch Sebastian Degener Seyed Vahid Sajadifar Emad Scharifi Kurt Steinhoff Thomas Niendorf Bernhard Sick |
| author_facet | Jens Decke Anna Engelhardt Lukas Rauch Sebastian Degener Seyed Vahid Sajadifar Emad Scharifi Kurt Steinhoff Thomas Niendorf Bernhard Sick |
| author_sort | Jens Decke |
| collection | DOAJ |
| description | 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>24</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>350</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>200</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>400</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C and at strain rates ranging from 0.001 s<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula> to 0.1 s<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula> 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. |
| first_indexed | 2024-03-10T00:19:39Z |
| format | Article |
| id | doaj.art-36a7d44d8f854df386e460ea7d5c6ee4 |
| institution | Directory Open Access Journal |
| issn | 2073-4352 |
| language | English |
| last_indexed | 2024-03-10T00:19:39Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj.art-36a7d44d8f854df386e460ea7d5c6ee42023-11-23T15:44:28ZengMDPI AGCrystals2073-43522022-09-01129128110.3390/cryst12091281Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning MethodsJens Decke0Anna Engelhardt1Lukas Rauch2Sebastian Degener3Seyed Vahid Sajadifar4Emad Scharifi5Kurt Steinhoff6Thomas Niendorf7Bernhard Sick8Intelligent Embedded Systems, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetallic Materials, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyIntelligent Embedded Systems, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetallic Materials, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetallic Materials, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetal Forming Technology, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetal Forming Technology, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyMetallic Materials, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyIntelligent Embedded Systems, Universität Kassel, Mönchebergstraße 3, 34125 Kassel, GermanyThe 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>24</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>350</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to set different cooling rates after solution heat-treatment. Isothermal uniaxial tensile tests in the temperature range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>200</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>400</mn><msup><mspace width="3.33333pt"></mspace><mo>∘</mo></msup></mrow></semantics></math></inline-formula>C and at strain rates ranging from 0.001 s<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula> to 0.1 s<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></semantics></math></inline-formula> 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.https://www.mdpi.com/2073-4352/12/9/1281machine learningeXtreme Gradient BoostingZerilli–Armstrongflow stressAA7075 |
| spellingShingle | Jens Decke Anna Engelhardt Lukas Rauch Sebastian Degener Seyed Vahid Sajadifar Emad Scharifi Kurt Steinhoff Thomas Niendorf Bernhard Sick Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods Crystals machine learning eXtreme Gradient Boosting Zerilli–Armstrong flow stress AA7075 |
| title | Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods |
| title_full | Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods |
| title_fullStr | Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods |
| title_full_unstemmed | Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods |
| title_short | Predicting Flow Stress Behavior of an AA7075 Alloy Using Machine Learning Methods |
| title_sort | predicting flow stress behavior of an aa7075 alloy using machine learning methods |
| topic | machine learning eXtreme Gradient Boosting Zerilli–Armstrong flow stress AA7075 |
| url | https://www.mdpi.com/2073-4352/12/9/1281 |
| work_keys_str_mv | AT jensdecke predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT annaengelhardt predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT lukasrauch predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT sebastiandegener predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT seyedvahidsajadifar predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT emadscharifi predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT kurtsteinhoff predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT thomasniendorf predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods AT bernhardsick predictingflowstressbehaviorofanaa7075alloyusingmachinelearningmethods |