| About this Abstract |
| Meeting |
2019 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing of Metals: Fatigue and Fracture III
|
| Presentation Title |
A Data-driven Approach to Investigate the Influence of Process Parameters on Fatigue Life of Additively Manufactured Metals |
| Author(s) |
Ashley D. Spear, Dillon Watring, Nadia Kouraytem |
| On-Site Speaker (Planned) |
Ashley D. Spear |
| Abstract Scope |
Understanding and predicting the relationships between process parameters and fatigue life will be essential to the qualification of metal structures produced by additive manufacturing (AM). One of the challenges in establishing process-structure-property relationships of AM-metal parts is that the design space for AM is very high-dimensional, and quantifying fatigue lifetimes for such a high-dimensional space can become intractable using conventional empirical approaches. This talk will focus on recent efforts to utilize data-driven approaches, including machine learning, to efficiently probe AM process space and establish links among AM process parameters and fatigue lifetimes. In general, the approaches described in this talk can be used to intelligently guide design-of-experiment (for example, in the case where optimal fatigue properties are sought), or to establish predictive fatigue-lifetime models with quantified uncertainty. The approaches have been applied to standard ASTM fatigue testing of AM IN718 and AM AlSi10Mg, both produced via laser powder bed fusion. |
| Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |