Machine learning for additive manufacturing: Predicting materials characteristics and their uncertainty. (March 2023)

• Record Type: Journal Article
• Authors: Chernyavsky, Dmitry; Kononenko, Denys Y.; Han, Jun Hee; Kim, Hwi Jun; van den Brink, Jeroen; Kosiba, Konrad
• Is Part Of: Materials & design. Volume 227(2023)
• Publication Date: 2023-03
• Subjects: Additive manufacturing -- Laser powder bed fusion -- Machine learning -- Gaussian processes -- Metallic glass -- Uncertainty quantification; Materials -- Periodicals; Engineering design -- Periodicals; Matériaux -- Périodiques; Conception technique -- Périodiques; Electronic journals; 620.11
• DOI: 10.1016/j.matdes.2023.111699
• Languages: English
• ISSNs: 0264-1275

Abstract

Graphical abstract: Highlights: Additive manufacturing requires process control for the parts fabrication. A machine learning approach is proposed for processing parameters optimization. The approach provides tools for in-depth uncertainty quantification.. The method is demonstrated by modeling the amorphicity of a glass-forming alloy. 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 Zr52.5 Cu17.9 Ni14.6 Al10 Ti5 (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.