Microstructure Generation via Generative Adversarial Network for Heterogeneous, Topologically Complex 3D Materials

Abstract

Using a large-scale, experimentally captured 3D microstructure data set, we implement the generative adversarial network (GAN) framework to learn and generate 3D microstructures of solid oxide fuel cell electrodes. The generated microstructures are visually, statistically, and topologically realistic, with distributions of microstructural parameters, including volume fraction, particle size, surface area, tortuosity, and triple-phase boundary density, being highly similar to those of the original microstructure. These results are compared and contrasted with those from an established, grain-based generation algorithm (DREAM.3D). Importantly, simulations of electrochemical performance, using a locally resolved finite element model, demonstrate that the GAN-generated microstructures closely match the performance distribution of the original, while DREAM.3D leads to significant differences. The ability of the generative machine learning model to recreate microstructures with high fidelity suggests that the essence of complex microstructures may be captured and represented in a compact and manipulatable form.

Modeling the Solid Electrolyte Interphase: Machine Learning as a Game Changer?

“…[331][332][333] At the microstructure scale, generative models for solid materials have been very successful even for complex heterogeneous systems and limited datasets. [325,[328][329][330][334][335][336][337] Generative models can be used for inverting the design process of better battery interphases by going from properties to structure-and composition-conditional generative models that learn correlations in structural space conditioned to the properties. [15] Thus, favorable SEI forming electrolyte compositions can be probabilistically generated.…”

Pitting Corrosion in 316L Stainless Steel Fabricated by Laser Powder Bed Fusion Additive Manufacturing: A Review and Perspective

“…[133][134][135] These simulation tools could potentially be combined with emerging data-driven tools, including machine learning and generative models, which have been applied to complex microstructure generation in other contexts. 136 In principle, these digital microstructures can serve as starting microstructures for subsequent corrosion response simulations. However, to date, relatively few simulation studies have probed the specific connection between process/microstructure models and microstructure-dependent corrosion behavior.…”

Rechargeable Batteries of the Future—The State of the Art from a BATTERY 2030+ Perspective

“…Full diversity of representations are usable for atomic scale structures, but at the continuum scale, image-based representations are most useful. [109,115] Beyond constraints learnt from data, additional known physical laws and constraints can be imposed on the generation. [116,117] Generation of new structures at the atomic scale can also be defined as a Markov decision process and deep reinforcement learning [118,119] working with a physics simulation environment can be used to train a structure generator.…”