| About this Abstract |
| Meeting |
TMS Specialty Congress 2025
|
| Symposium
|
8th World Congress on Integrated Computational Materials Engineering (ICME 2025)
|
| Presentation Title |
Effect of Random Porosities and Surface Roughness on Fatigue Life of Additively Manufactured Maraging Steel |
| Author(s) |
Aditya Pandey, Vidit Gaur |
| On-Site Speaker (Planned) |
Vidit Gaur |
| Abstract Scope |
A combined approach of machine learning, computational fluid dynamics and analytical model was established to explore the interaction between porosity distribution and surface roughness on the fatigue life of additively manufactured components. A new fatigue life estimation model was proposed by introducing parameter gamma (γ) by modifying the Murakami’s model based on defect size and effective stress. A total of 100 fatigue test were conducted at different stress ratios followed by the post fracture defect analysis and surface roughness measurements. Different machine learning algorithms such as artificial neural network (ANN) and random forest (RF) etc. were employed to estimate the fatigue life. The results revealed that the randomly distributed subsurface porosities and surface defects increases the scatter in fatigue lives thereby leading to uncertainty in fatigue life prediction. Furthermore, the machine learning algorithms exhibit promising prediction performance, especially when considering the parameter gamma and combining surface roughness with porosity. |
| Proceedings Inclusion? |
Undecided |