Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process
This study focuses on ductile fracture behavior prediction for Ti6Al4V alloys fabricated via Selective Laser Melting (SLM). A modified Gurson-Tvergaard-Needleman (GTN) model characterizes void growth and shear mechanisms under uniaxial stress. The research explores the impact of Artificial Neural N...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Gruppo Italiano Frattura
2024-03-01
|
| Series: | Fracture and Structural Integrity |
| Subjects: | |
| Online Access: | https://fracturae.com/index.php/fis/article/view/4783 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832568779688640512 |
|---|---|
| author | Mohsen Sarparast Majid Shafaie Mohammad Davoodi Ahmad Memaran Babakan Hongyan Zhang |
| author_facet | Mohsen Sarparast Majid Shafaie Mohammad Davoodi Ahmad Memaran Babakan Hongyan Zhang |
| author_sort | Mohsen Sarparast |
| collection | DOAJ |
| description |
This study focuses on ductile fracture behavior prediction for Ti6Al4V alloys fabricated via Selective Laser Melting (SLM). A modified Gurson-Tvergaard-Needleman (GTN) model characterizes void growth and shear mechanisms under uniaxial stress. The research explores the impact of Artificial Neural Network (ANN) architecture, specifically hidden layers and neurons, on predicting fracture parameters. Results reveal that increasing hidden layers substantially enhances accuracy, particularly for fracture displacement. Notably, predicting maximum force requires fewer layers than fracture displacement. Using selected layers and neurons, the system consistently achieved R2-values exceeding 0.99 for both maximum force and fracture displacement. The study identifies the initial void volume fraction (f0) parameter as having the most significant influence on both properties.
|
| format | Article |
| id | doaj-art-6cb19cccc1d04c1785ebf68f0d580bf3 |
| institution | Kabale University |
| issn | 1971-8993 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Gruppo Italiano Frattura |
| record_format | Article |
| series | Fracture and Structural Integrity |
| spelling | doaj-art-6cb19cccc1d04c1785ebf68f0d580bf32025-02-03T00:35:50ZengGruppo Italiano FratturaFracture and Structural Integrity1971-89932024-03-011868Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM ProcessMohsen Sarparast0https://orcid.org/0000-0002-9159-8460Majid Shafaie1https://orcid.org/0000-0002-3140-5495Mohammad Davoodi2Ahmad Memaran Babakan3Hongyan Zhang4Department of Mechanical, Industrial & Manufacturing Engineering, The University of Toledo, Toledo, OH, USADepartment of Mechanical Engineering, Amirkabir University of Technology, Tehran, Iran.Department of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranDepartment of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranDepartment of Mechanical, Industrial & Manufacturing Engineering, The University of Toledo, Toledo, OH, USA This study focuses on ductile fracture behavior prediction for Ti6Al4V alloys fabricated via Selective Laser Melting (SLM). A modified Gurson-Tvergaard-Needleman (GTN) model characterizes void growth and shear mechanisms under uniaxial stress. The research explores the impact of Artificial Neural Network (ANN) architecture, specifically hidden layers and neurons, on predicting fracture parameters. Results reveal that increasing hidden layers substantially enhances accuracy, particularly for fracture displacement. Notably, predicting maximum force requires fewer layers than fracture displacement. Using selected layers and neurons, the system consistently achieved R2-values exceeding 0.99 for both maximum force and fracture displacement. The study identifies the initial void volume fraction (f0) parameter as having the most significant influence on both properties. https://fracturae.com/index.php/fis/article/view/4783FractureGTN modelAMANNHidden layers |
| spellingShingle | Mohsen Sarparast Majid Shafaie Mohammad Davoodi Ahmad Memaran Babakan Hongyan Zhang Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process Fracture and Structural Integrity Fracture GTN model AM ANN Hidden layers |
| title | Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process |
| title_full | Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process |
| title_fullStr | Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process |
| title_full_unstemmed | Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process |
| title_short | Predictive Modeling of Fracture Behavior in Ti6Al4V Alloys Manufactured by SLM Process |
| title_sort | predictive modeling of fracture behavior in ti6al4v alloys manufactured by slm process |
| topic | Fracture GTN model AM ANN Hidden layers |
| url | https://fracturae.com/index.php/fis/article/view/4783 |
| work_keys_str_mv | AT mohsensarparast predictivemodelingoffracturebehaviorinti6al4valloysmanufacturedbyslmprocess AT majidshafaie predictivemodelingoffracturebehaviorinti6al4valloysmanufacturedbyslmprocess AT mohammaddavoodi predictivemodelingoffracturebehaviorinti6al4valloysmanufacturedbyslmprocess AT ahmadmemaranbabakan predictivemodelingoffracturebehaviorinti6al4valloysmanufacturedbyslmprocess AT hongyanzhang predictivemodelingoffracturebehaviorinti6al4valloysmanufacturedbyslmprocess |