Stochastic characterization and reconstruction of material microstructures for establishment of process-structure-property linkage using the deep generative model

End-to-end three-dimensional designing of complex disordered materials from limited data using machine learning

Precise 3D representation of complex materials, here the lithium-ion batteries, is a critical step toward designing optimized energy storage systems. One requires obtaining several such samples for a more accurate evaluation of uncertainty and variability, which in turn can be costly and time demanding. Using 3D models is crucial when it comes to evaluating the transport and heat capacity of batteries. Further, such models represent the microstructures more precisely where connectivity and heterogeneity can be detected. However, 3D images are hard to access, and the available images are often collected in two dimensions (2D). Such 2D images, on the other hand, are more accessible and often have higher resolution. In this paper, a deep learning method has been applied to take advantage of 2D images and build 3D models of heterogeneous materials through which more accurate characterization and physical evaluations can be achieved. While being trained using only 2D images, the proposed framework can be utilized to generate 3D images. The proposed method is applied to a few realistic 3D images of lithium-ion battery electrodes. The results indicate that the implemented method can reproduce important structural properties while the flow and heat properties are within an acceptable range.

Identification of microstructures critically affecting material properties using machine learning framework based on metallurgists’ thinking process

In materials science, machine learning has been intensively researched and used in various applications. However, it is still far from achieving intelligence comparable to that of human experts in terms of creativity and explainability. In this paper, we investigate whether machine learning can acquire explainable knowledge without directly introducing problem-specific information such as explicit physical mechanisms. In particular, a potential of machine learning to obtain the capability to identify a part of material structures that critically affects a physical property without human prior knowledge is mainly discussed. The guide for constructing the machine learning framework adopted in this paper is to imitate human researchers’ process of thinking in the interpretation and development of materials. Our framework was applied to the optimization of structures of artificial dual-phase steels in terms of a fracture property. A comparison of results of the framework with those of numerical simulation based on governing physical laws demonstrated the potential of our framework for the identification of a part of microstructures critically affecting the target property. Consequently, this implies that our framework can implicitly acquire an intuition in a similar way that human researchers empirically attain the general strategy for material design consistent with the physical background.