利用超分辨率生成对抗网络提高电池电极材料的EBSD分析通量
Enhancing EBSD throughput of battery electrode materials using super-resolution generative adversarial networks
浏览论文内容
中文总结 AI 辅助
本研究提出SRGAN超分辨率框架，将EBSD分析通量提升25倍，优于经典插值方法，可高效获取高精度电池电极微观结构数据，助力材料研发与工业应用。
中文摘要 AI 辅助
利用电子背散射衍射（EBSD）对锂离子电池电极材料进行定量微观结构表征，已被证明是优化电池性能的关键方法。然而，EBSD固有的缓慢特性会阻碍材料微观结构统计表征所需的分析通量。本研究展示了一种使用生成对抗网络的机器学习超分辨率框架（SRGAN），可显著提高EBSD分析通量。SRGAN模型在LiNixMnyCozO2（NMC）正极颗粒的EBSD数据上进行训练，以通过计算增强低分辨率数据集，并在各种放大倍数（2倍至12倍）下与经典插值方法的性能进行比较。定性图像指标和定量微观结构分析均证实，SRGAN系统地优于经典方法，尤其在保留小晶粒和维持真实晶界方面表现突出。研究表明，5倍放大倍数（对应采集时间提速25倍或视场扩大25倍）在保持晶粒尺寸、形状等关键指标可接受精度的同时具有实用性。例如，在5倍放大时，晶粒面积等效直径、晶粒最大内切球直径、晶界长度的相对误差分别为+5.7%、+8.2%和-14.6%。本研究开发的SRGAN方法显著提高了EBSD采集效率，可获得统计上更稳健的微观结构数据集，使EBSD成为材料研究和工业工艺开发的高通量表征工具。
英文摘要
Quantitative microstructural characterization of Li-ion battery electrode materials using electron backscatter diffraction (EBSD) has been proven as a critical method for optimizing cell performance. However, the inherently slow nature of EBSD can hinder the throughput of analyses needed for statistical representation of a material microstructure being developed. This work demonstrates a machine learning super-resolution framework using a generative adversarial network (SRGAN) to significantly increase EBSD throughput. The SRGAN model was trained on EBSD data of LiNixMnyCozO2 (NMC) cathode particles to computationally enhance low-resolution datasets and its performance is compared against classical interpolation methods across various upscaling factors (2x to 12x). Both qualitative image metrics and quantitative microstructural analysis verified that the SRGAN systematically outperformed classical methods, particularly in preserving small grains and maintaining realistic grain boundaries. We demonstrate that a 5x upscaling factor, corresponding to a 25x speed-up in acquisition time or a 25x larger field of view, is practical while maintaining acceptable accuracy in key metrics like grain size and shape. For instance, at 5x upscaling, relative errors were +5.7%, +8.2%, and -14.6% on grain area-equivalent diameter, grain maximum sphere-inscribed diameter, and grain boundary length, respectively. The SRGAN methodology developed in this work significantly enhances the efficiency of EBSD acquisition for more statistically robust microstructural dataset, enabling EBSD as a high-throughput characterization tool for materials research and industrial process development.
