Deep Learning strategies recently emerged as powerful tools for the characterization of heterogeneous materials. In this work, we discuss an approach for the multi-scale characterization of the mechanical response of polysilicon MEMS (micro electro-mechanical systems), based on data assimilation from two-dimensional stochastically representative images of the polycrystalline structure of films that typically represent the building block of the MEMS movable structures.
A dataset of microstructures is collected and a neural network is trained, to provide the appropriate scattering in the values of the overall stiffness (in terms e.g. of Young’s modulus) of the grain aggregate. Since results are framed within a stochastic procedure, the aim of the learning stage is not to accurately reproduce the microstructure-informed response of the polysilicon film, but instead to provide a fast method to be next used at the device level for statistical, Monte Carlo-like analyses of the relevant performance indices.
Accuracy of the proposed approach is assessed for different ratio between the dimension of the polycrystalline aggregate and the representative size of a single grain (i.e. for different number of grains gathered in the polycrystal), to check if size effects are correctly captured.