Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates
Refill friction stir spot welding (RFSSW) technology is a solid-state joint that can replace conventional welding or riveting processes in aerospace applications. The quality of the new welding process is directly influenced by the welding parameters selected. A finite element analysis was performed...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/16/13/4519 |
| _version_ | 1797591387348140032 |
|---|---|
| author | Dan Cătălin Bîrsan Viorel Păunoiu Virgil Gabriel Teodor |
| author_facet | Dan Cătălin Bîrsan Viorel Păunoiu Virgil Gabriel Teodor |
| author_sort | Dan Cătălin Bîrsan |
| collection | DOAJ |
| description | Refill friction stir spot welding (RFSSW) technology is a solid-state joint that can replace conventional welding or riveting processes in aerospace applications. The quality of the new welding process is directly influenced by the welding parameters selected. A finite element analysis was performed to understand the complexity of the thermomechanical phenomena during this welding process, validated by controlled experiments. An optimization model using neural networks was developed based on 98 parameter sets resulting from changing 3 welding parameters, namely pin penetration depth, pin rotation speed, and retention time. Ten parameter sets were used to verify the learning results of the optimization model. The 10 results were drawn to correspond to a uniform distribution over the training domain, with the aim of avoiding areas that might have contained distortions. The maximum temperature and normal stress reached at the end of the welding process were considered output data. |
| first_indexed | 2024-03-11T01:36:40Z |
| format | Article |
| id | doaj.art-f5b334f30ea44bf7870d10384b178b39 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-11T01:36:40Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-f5b334f30ea44bf7870d10384b178b392023-11-18T16:55:56ZengMDPI AGMaterials1996-19442023-06-011613451910.3390/ma16134519Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy PlatesDan Cătălin Bîrsan0Viorel Păunoiu1Virgil Gabriel Teodor2Faculty of Engineering, Department of Manufacturing Engineering, “Dunărea de Jos” University of Galati, Domnească Street, 47, RO-800008 Galati, RomaniaFaculty of Engineering, Department of Manufacturing Engineering, “Dunărea de Jos” University of Galati, Domnească Street, 47, RO-800008 Galati, RomaniaFaculty of Engineering, Department of Manufacturing Engineering, “Dunărea de Jos” University of Galati, Domnească Street, 47, RO-800008 Galati, RomaniaRefill friction stir spot welding (RFSSW) technology is a solid-state joint that can replace conventional welding or riveting processes in aerospace applications. The quality of the new welding process is directly influenced by the welding parameters selected. A finite element analysis was performed to understand the complexity of the thermomechanical phenomena during this welding process, validated by controlled experiments. An optimization model using neural networks was developed based on 98 parameter sets resulting from changing 3 welding parameters, namely pin penetration depth, pin rotation speed, and retention time. Ten parameter sets were used to verify the learning results of the optimization model. The 10 results were drawn to correspond to a uniform distribution over the training domain, with the aim of avoiding areas that might have contained distortions. The maximum temperature and normal stress reached at the end of the welding process were considered output data.https://www.mdpi.com/1996-1944/16/13/4519stir spot weldingnumerical simulationaluminum alloy |
| spellingShingle | Dan Cătălin Bîrsan Viorel Păunoiu Virgil Gabriel Teodor Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates Materials stir spot welding numerical simulation aluminum alloy |
| title | Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates |
| title_full | Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates |
| title_fullStr | Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates |
| title_full_unstemmed | Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates |
| title_short | Neural Networks Applied for Predictive Parameters Analysis of the Refill Friction Stir Spot Welding Process of 6061-T6 Aluminum Alloy Plates |
| title_sort | neural networks applied for predictive parameters analysis of the refill friction stir spot welding process of 6061 t6 aluminum alloy plates |
| topic | stir spot welding numerical simulation aluminum alloy |
| url | https://www.mdpi.com/1996-1944/16/13/4519 |
| work_keys_str_mv | AT dancatalinbirsan neuralnetworksappliedforpredictiveparametersanalysisoftherefillfrictionstirspotweldingprocessof6061t6aluminumalloyplates AT viorelpaunoiu neuralnetworksappliedforpredictiveparametersanalysisoftherefillfrictionstirspotweldingprocessof6061t6aluminumalloyplates AT virgilgabrielteodor neuralnetworksappliedforpredictiveparametersanalysisoftherefillfrictionstirspotweldingprocessof6061t6aluminumalloyplates |