Image analysis of material microstructures through microscopy is an integral capability in the field of materials science. The topological and chemical information obtained through microscopy allow us to draw vital co...
详细信息
Image analysis of material microstructures through microscopy is an integral capability in the field of materials science. The topological and chemical information obtained through microscopy allow us to draw vital connections between material microstructures, properties, and processing. While scanning electron microscopy (SEM) image is able to yield a considerable wealth of information interpretable by the intuition of experts, there has been significant amount of interests in using machine learning, convolutional neural networks (CNNs) in particular, for such image analysis task. Training CNNs for an image analysis task requires a large annotated dataset. However, in many materials science applications, obtaining a large annotated dataset is cost and labor intensive. In this work, we study the use of synthetic data to enlarge the available annotated experimental data of uranium oxide. We utilize a modified Potts model to simulate uranium oxide particles with morphologies similar to those observed experimentally. We then leverage an image-to-image translation model to synthesize the simulated particles as if they are acquired with SEM. Through this process, we obtain pairs of particle images and their corresponding SEM representations, which corresponds to pairs of annotations and images. Unlike previous works, we leverage synthetic data for pretraining a CNN model prior, and finetune that model further with experimental data. We experimentally demonstrate that using synthetic data as an incremental learning process benefits the overall performance compared to training a model on combined synthetic and experimental data.
Ultra-precision diamond cutting is a promising machining technique for realizing ultra-smooth surface of different kinds of *** fundamental understanding of the impact of workpiece material properties on cutting mecha...
详细信息
Ultra-precision diamond cutting is a promising machining technique for realizing ultra-smooth surface of different kinds of *** fundamental understanding of the impact of workpiece material properties on cutting mechanisms is crucial for promoting the capability of the machining technique,numerical simulation methods at different length and time scales act as important supplements to experimental *** this work,we present a compact review on recent advancements in the numerical simulations of material-oriented diamond cutting,in which representative machining phenomena are systematically summarized and discussed by multiscale simulations such as molecular dynamics simulation and finite element simulation:the anisotropy cutting behavior of polycrystalline material,the thermo-mechanical coupling tool-chip friction states,the synergetic cutting responses of individual phase in composite materials,and the impact of various external energetic fields on cutting *** particular,the novel physics-based numerical models,which involve the high precision constitutive law associated with heterogeneous deformation behavior,the thermo-mechanical coupling algorithm associated with tool-chip friction,the configurations of individual phases in line with real microstructural characteristics of composite materials,and the integration of external energetic fields into cutting models,are ***,insights into the future development of advanced numerical simulation techniques for diamond cutting of advanced structured materials are also *** aspects reported in this review present guidelines for the numerical simulations of ultra-precision mechanical machining responses for a variety of materials.
暂无评论