The present work addresses a machine learning approach to study the linkage between deformation processing and microstructural texture evolution. The texture evolution is represented with a one-point probability descriptor, orientation distribution function (ODF) by employing a rate-independent single-crystal plasticity model. The ODF relates to the volume densities of different orientations in a microstructure, and thus it quantifies the texture during processing. First, a database of microstructural textures and deformation processes is built to generate the training dataset. The Latin hypercube sampling method is implemented to create uniformly distributed ODF values that represent the initial texture. Next, the crystal plasticity simulations using the initial ODF samples are performed for different deformation processes such as tension, plane strain compression, shear, shear, and shear; and the final texture information is stored in the database. Transductive learning is employed by using the training data to predict the label (optimum process) that can produce a given unlabeled texture. Two example process design applications are discussed for a galfenol alloy. In the first problem, the transductive learning approach is verified by using the previously optimized ODF solutions for a vibration tuning problem. In the second example, the process design is performed for a multiphysics optimization problem.
Machine Learning Approach for Identification of Microstructure–Process Linkages
AIAA Journal ; 57 , 8 ; 3608-3614
2019-05-31
7 pages
Article (Journal)
Electronic Resource
English
Synthesizing Single DOF Linkages Via Transition Linkage Identification
Online Contents | 2008
|Springer Verlag | 2022
|Automotive engineering | 1985
|SAE Technical Papers | 1985
|