Software-based segmentation of metallic inclusions in additive manufactured alloys for microstructure-property linkage

In this application note, ZEISS explores the application of machine learning (ML) and image analysis techniques in segmenting metallic inclusions in additive manufactured high-temperature aluminum alloys. The study demonstrates the use of correlative microscopy, combining light and electron microscopy, to train a robust ML system for inclusion characterization. By leveraging ML-based segmentation, inclusions generated during the additive manufacturing process can be accurately identified and quantified. The note highlights the importance of understanding the microstructure-property relationship and the potential of ML in advancing microstructural analysis in material science.