Towards an instant structure-property prediction quality control tool for additive manufactured steel using a crystal plasticity trained deep learning surrogate. (January 2022)

• Record Type: Journal Article
• Authors: Tu, Yuhui; Liu, Zhongzhou; Carneiro, Luiz; Ryan, Caitriona M.; Parnell, Andrew C.; Leen, Seán B; Harrison, Noel M
• Is Part Of: Materials & design. Volume 213(2022)
• Publication Date: 2022-01
• Subjects: Crystal plasticity -- Deep neural network -- 17-4PH stainless steel -- Additive manufacturing -- Micromechanics; PBF powder bed fusion -- CPFE crystal plasticity finite element -- EBSD electron backscatter diffraction -- RVE representative volume element -- VT Voronoi tessellation -- AM additive manufacturing -- DL deep learning -- CNN convolutional neural network -- DNN deep neural network -- PBC periodic boundary condition -- Vf, m Martensite volume fraction -- FIPs fatigue indicator parameters -- MAE mean absolute error -- MSE mean squared error -- BP back propagation -- YS yield stress; Materials -- Periodicals; Engineering design -- Periodicals; Matériaux -- Périodiques; Conception technique -- Périodiques; Electronic journals; 620.11
• DOI: 10.1016/j.matdes.2021.110345
• Languages: English
• ISSNs: 0264-1275

Abstract

Graphical abstract: Abstract: The ability to conduct in-situ real-time process-structure-property checks has the potential to overcome process and material uncertainties, which are key obstacles to improved uptake of metal powder bed fusion in industry. Efforts are underway for live process monitoring such as thermal and image-based data gathering for every layer printed. Current crystal plasticity finite element (CPFE) modelling is capable of predicting the associated strength based on a microstructural image and material data but is computationally expensive. This work utilizes a large database of input–output samples from CPFE modelling to develop a trained deep neural network (DNN) model which instantly estimates the output (strength prediction) associated with a given input (microstructure) of multi-phase additive manufactured stainless steels. The DNN model successfully recognizes phase regions and the associated unique crystallographic orientation variations. It also captures differences in macroscopic stress response due to the varying microstructure. However, it is less reliable in terms of fatigue life predictions. The DNN model exhibits high accuracy for the structure–property relationship as a surrogate prediction tool compared to CPFE while significantly reducing the computational cost to just a few seconds.