Microstructure optimization with constrained design objectives using machine learning-based feedback-aware data-generation AITranslate

Basic Information:

DOI：https://doi.org/10.1016/j.commatsci.2019.01.015

Chinese Library Classification Number:

Citation Information:

Microstructure sensitive design has a critical impact on the performance of engineering materials. The safety and performance requirements of critical components, as well as the cost of material and machining of Titanium components, make dovetailing of the microstructure imperative. This paper addresses the optimization of several microstructure design problems for Titanium components under specific design constraints using a feedback-aware data-driven solution methodology. In this study, the microstructure is modeled with an orientation distribution function (ODF) that measures the volumes of different crystallographic orientations. Two algorithms are used to sample the entire microstructure space followed by machine learning-aided identification of a minimal subset of ODF dimensions which is subsequently explored by targeted sampling. Conventional optimization methods lead to a unique microstructure rather than yielding a comprehensive space of optimal or near-optimal microstructures. Multiple solutions are crucial for the deployment of materials design for manufacturing as traditional manufacturing processes can only generate a limited set of microstructures. Our data sampling-based methodology not only outperforms or is on par with other optimization techniques in terms of the optimal property value, but also provides numerous near-optimal solutions, 3–4 orders of magnitude more than previous methods. Consequently, the proposed framework delivers a spectrum of optimal solutions in the microstructure space which can accelerate materials development and reduce manufacturing costs. Graphical abstract Flow diagram of the proposed methodology. There are two phases in the sampling process. In the first phase, two data generation algorithms are explored for dataset creation, namely partition and allocation. In the first step, we execute our data-generation algorithms (depicted by orange arrows) to generate many valid solutions for each set of constraint. In the second phase, a machine learning-guided feedback-aware sampling approach (depicted by green allows) extracts a combination of non- zero ODF dimensions. ODFs generated with these subset of combinations lead to optimal or near-optimal solutions. Download : Download high-res image (93KB) Download : Download full-size image