| About this Abstract |
| Meeting |
2020 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing Fatigue and Fracture IV: Toward Confident Use in Critical Applications
|
| Presentation Title |
Prediction of Fatigue Life of Flight-critical Metallic Components Fabricated by Additive Manufacturing |
| Author(s) |
Xuesong Fan, Baldur Steingrimsson, Duckbong Kim, Peter K. Liaw |
| On-Site Speaker (Planned) |
Baldur Steingrimsson |
| Abstract Scope |
This abstract describes a comprehensive toolset for predicting the fatigue life of flight-critical metallic components fabricated by additive manufacturing (AM). Existing toolsets cannot predict how AM affects material properties of additively manufactured parts. Hence, we propose a machine learning (ML) framework for predicting fatigue properties of additively manufactured metallic components. The framework is a generalization of Statistical Fatigue Life model by one of the authors, and employs sophisticated, physics-based metallurgical prediction models. ML can help avoid inaccuracies in fitting traditional models to real-world fatigue data. ML can also account for all the sources that can impact fatigue life of AM components. In this work, we identify defects, inhomogeneity and unwanted features (DIUF) at macro, micro, and nano-levels in AM process and comparing different DIUFs between AM and casting. We then show how stress life (S/N curves) for Ti-6Al-4V can be accurately predicted, based on data already available from the literature. |
| Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |