Reconstructing Microstructures From Statistical Descriptors Using Neural Cellular Automata

Abstract

The problem of generating microstructures of complex materials in silico has been approached from various directions including simulation, Markov, deep learning and descriptor-based approaches. This work presents a hybrid method that is inspired by all four categories and has interesting scalability properties. A neural cellular automaton is trained to evolve microstructures based on local information. Unlike most machine learning-based approaches, it does not directly require a data set of reference micrographs, but is trained from statistical microstructure descriptors that can stem from a single reference. This means that the training cost scales only with the complexity of the structure and associated descriptors. Since the size of the reconstructed structures can be set during inference, even extremely large structures can be efficiently generated. Similarly, the method is very efficient if many structures are to be reconstructed from the same descriptor for statistical evaluations. The method is formulated and discussed in detail by means of various numerical experiments, demonstrating its utility and scalability.

Review Study on Mechanical Properties of Cellular Materials

“…Microstructure Formation Method Reference architected cellular materials additive manufacturing [85] hard sphere packings with lognormal or gamma distributions investigating geometric characteristics [45] cellular ceramic composites 3d microarchitecture [3] cellular automata modeling for deformation processes [86] metals and alloys in laser additive manufacturing laser additive manufacturing [87] porous metals solid freeform fabrication techniques [88] neural cellular automata [89] hexagonal honeycomb cellular material polynomial interpolation method [35] metal foams 3D Voronoi structure [41] Poly-methacrylimide (PMI) foam in situ x-ray micro-computed tomography (CT) [39] The second and most popular approach uses computational techniques to virtually create cellular materials, such as topology optimization and finite element analysis. Using these techniques, materials' behavior under various conditions was simulated, and their microstructure was optimized to produce desirable characteristics like stiffness, strength, or thermal conductivity [46,[90][91][92].…”