Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Towards ML-assisted Advanced Manufacturing
This work addresses the resource-intensive development cycle in advanced manufacturing by integrating machine learning to visualize microstructures, though it is incremental as it builds on prior GAN applications.
The authors tackled the problem of expensive and small-scale experiments in advanced manufacturing by using conditional GANs to generate realistic SEM images conditioned on temper and parameters/properties for the ShAPE process, enabling immediate visualization of microstructures and forming a technical backbone for a new approach to understanding manufacturing without first-principle models.
The research and development cycle of advanced manufacturing processes traditionally requires a large investment of time and resources. Experiments can be expensive and are hence conducted on relatively small scales. This poses problems for typically data-hungry machine learning tools which could otherwise expedite the development cycle. We build upon prior work by applying conditional generative adversarial networks (GANs) to scanning electron microscope (SEM) imagery from an emerging manufacturing process, shear assisted processing and extrusion (ShAPE). We generate realistic images conditioned on temper and either experimental parameters or material properties. In doing so, we are able to integrate machine learning into the development cycle, by allowing a user to immediately visualize the microstructure that would arise from particular process parameters or properties. This work forms a technical backbone for a fundamentally new approach for understanding manufacturing processes in the absence of first-principle models. By characterizing microstructure from a topological perspective we are able to evaluate our models' ability to capture the breadth and diversity of experimental scanning electron microscope (SEM) samples. Our method is successful in capturing the visual and general microstructural features arising from the considered process, with analysis highlighting directions to further improve the topological realism of our synthetic imagery.