Machine learning for additive manufacturing: Predicting materials characteristics and their uncertainty

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

  • Dmitry Chernyavsky - , Leibniz Institute for Solid State and Materials Research Dresden (Author)
  • Denys Y. Kononenko - , Chair of Solid State Theory, Leibniz Institute for Solid State and Materials Research Dresden (Author)
  • Jun Hee Han - , Korea Institute of Industrial Technology (Author)
  • Hwi Jun Kim - , Korea Institute of Industrial Technology (Author)
  • Jeroen van den Brink - , Chair of Solid State Theory, Leibniz Institute for Solid State and Materials Research Dresden (Author)
  • Konrad Kosiba - , Leibniz Institute for Solid State and Materials Research Dresden (Author)

Abstract

Additive manufacturing (AM) is known for versatile fabrication of complex parts, while also allowing the synthesis of materials with desired microstructures and resulting properties. These benefits come at a cost: process control to manufacture parts within given specifications is very challenging due to the relevance of a large number of processing parameters. Efficient predictive machine learning (ML) models trained on small datasets, can minimize this cost. They also allow to assess the quality of the dataset inclusive of uncertainty. This is important in order for additively manufactured parts to meet property specifications not only on average, but also within a given variance or uncertainty. Here, we demonstrate this strategy by developing a heteroscedastic Gaussian process (HGP) model, from a dataset based on laser powder bed fusion of a glass-forming alloy at varying processing parameters. Using amorphicity as the microstructural descriptor, we train the model on our Zr52.5Cu17.9Ni14.6Al10Ti5 (at.%) alloy dataset. The HGP model not only accurately predicts the mean value of amorphicity, but also provides the respective uncertainty. The quantification of the aleatoric and epistemic uncertainty contributions allows to assess intrinsic inaccuracies of the dataset, as well as identify underlying physical phenomena. This HGP model approach enables to systematically improve ML-driven AM processes.

Details

Original languageEnglish
Article number111699
JournalMaterials and Design
Volume227
Publication statusPublished - Mar 2023
Peer-reviewedYes

Keywords

Keywords

  • Additive manufacturing, Gaussian processes, Laser powder bed fusion, Machine learning, Metallic glass, Uncertainty quantification