[Analysis Case] Extraction of Active Material from Battery Cathode Material and Data Analysis
We determined the particle size of active substances from SEM images using deep learning and data analysis.
Deep learning enables the extraction of target objects from images. Additionally, by analyzing the regions corresponding to the obtained targets, information can be obtained in numerical form. In this instance, we used deep learning to extract active material particles and detect cracks in cross-sectional SEM images of battery cathode materials. Extraction is also possible for 3D data, such as Slice&View data. We extracted particles with and without cracks from the 3D data and calculated their respective particle sizes. Measurement methods: SEM, Slice&View, computational science, AI, data analysis Product fields: Solar cells, secondary batteries, fuel cells Analysis purposes: Structural evaluation, shape evaluation, failure analysis, defect analysis For more details, please download the materials or contact us.
- Company:一般財団法人材料科学技術振興財団 MST
- Price:Other