Long-short term memory networks for modeling track geometry in laser metal deposition
Modeling metal additive manufacturing processes is of great importance because it allows for the production of objects that are closer to the desired geometry and mechanical properties. Over-deposition often takes place during laser metal deposition, especially when the deposition head changes its d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2023.1156630/full |
| _version_ | 1797798475789762560 |
|---|---|
| author | Martina Perani Ralf Jandl Stefano Baraldo Anna Valente Beatrice Paoli |
| author_facet | Martina Perani Ralf Jandl Stefano Baraldo Anna Valente Beatrice Paoli |
| author_sort | Martina Perani |
| collection | DOAJ |
| description | Modeling metal additive manufacturing processes is of great importance because it allows for the production of objects that are closer to the desired geometry and mechanical properties. Over-deposition often takes place during laser metal deposition, especially when the deposition head changes its direction and results in more material being melted onto the substrate. Modeling over-deposition is one of the necessary steps toward online process control, as a good model can be used in a closed-loop system to adjust the deposition parameters in real-time to reduce this phenomenon. In this study, we present a long-short memory neural network to model over-deposition. The model has been trained on simple geometries such as straight tracks, spiral and V-tracks made of Inconel 718. The model shows good generalization capabilities and can predict the height of more complex and previously unseen random tracks with limited performance loss. After the addition to the training dataset of a small amount of data coming from the random tracks, the performance of the model for such additional shapes improves significantly, making this approach feasible for more general applications as well. |
| first_indexed | 2024-03-13T04:05:19Z |
| format | Article |
| id | doaj.art-7696d87bbb384da19d23081aa56d02af |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-03-13T04:05:19Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-7696d87bbb384da19d23081aa56d02af2023-06-21T08:17:10ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122023-06-01610.3389/frai.2023.11566301156630Long-short term memory networks for modeling track geometry in laser metal depositionMartina Perani0Ralf Jandl1Stefano Baraldo2Anna Valente3Beatrice Paoli4Laboratory for Web Science, Department for Research and Services, Fernfachhochschule Schweiz (FFHS), Brig, SwitzerlandLaboratory for Web Science, Department for Research and Services, Fernfachhochschule Schweiz (FFHS), Brig, SwitzerlandAutomation Robotics and Machines Laboratory, Department of Innovative Technologies, University of Applied Science and Arts of Southern Switzerland (SUPSI), Lugano, SwitzerlandAutomation Robotics and Machines Laboratory, Department of Innovative Technologies, University of Applied Science and Arts of Southern Switzerland (SUPSI), Lugano, SwitzerlandLaboratory for Web Science, Department for Research and Services, Fernfachhochschule Schweiz (FFHS), Brig, SwitzerlandModeling metal additive manufacturing processes is of great importance because it allows for the production of objects that are closer to the desired geometry and mechanical properties. Over-deposition often takes place during laser metal deposition, especially when the deposition head changes its direction and results in more material being melted onto the substrate. Modeling over-deposition is one of the necessary steps toward online process control, as a good model can be used in a closed-loop system to adjust the deposition parameters in real-time to reduce this phenomenon. In this study, we present a long-short memory neural network to model over-deposition. The model has been trained on simple geometries such as straight tracks, spiral and V-tracks made of Inconel 718. The model shows good generalization capabilities and can predict the height of more complex and previously unseen random tracks with limited performance loss. After the addition to the training dataset of a small amount of data coming from the random tracks, the performance of the model for such additional shapes improves significantly, making this approach feasible for more general applications as well.https://www.frontiersin.org/articles/10.3389/frai.2023.1156630/fulllaser metal depositionartificial intelligencelong-short-term-memory networktrack height predictionover-depositiongeneralizable model |
| spellingShingle | Martina Perani Ralf Jandl Stefano Baraldo Anna Valente Beatrice Paoli Long-short term memory networks for modeling track geometry in laser metal deposition Frontiers in Artificial Intelligence laser metal deposition artificial intelligence long-short-term-memory network track height prediction over-deposition generalizable model |
| title | Long-short term memory networks for modeling track geometry in laser metal deposition |
| title_full | Long-short term memory networks for modeling track geometry in laser metal deposition |
| title_fullStr | Long-short term memory networks for modeling track geometry in laser metal deposition |
| title_full_unstemmed | Long-short term memory networks for modeling track geometry in laser metal deposition |
| title_short | Long-short term memory networks for modeling track geometry in laser metal deposition |
| title_sort | long short term memory networks for modeling track geometry in laser metal deposition |
| topic | laser metal deposition artificial intelligence long-short-term-memory network track height prediction over-deposition generalizable model |
| url | https://www.frontiersin.org/articles/10.3389/frai.2023.1156630/full |
| work_keys_str_mv | AT martinaperani longshorttermmemorynetworksformodelingtrackgeometryinlasermetaldeposition AT ralfjandl longshorttermmemorynetworksformodelingtrackgeometryinlasermetaldeposition AT stefanobaraldo longshorttermmemorynetworksformodelingtrackgeometryinlasermetaldeposition AT annavalente longshorttermmemorynetworksformodelingtrackgeometryinlasermetaldeposition AT beatricepaoli longshorttermmemorynetworksformodelingtrackgeometryinlasermetaldeposition |