Digitalisation – Machine Learning for Segmentation and Classification of Complex Steel Microstructures – Part 1

Microstructure refers to the internal structure of a material that both reflects its processing history and determines its physical and chemical properties [1]. Accurate analysis of the microstructure, including its phases, distribution, shapes, and sizes, is essential for understanding the links between processing, microstructure, and properties [2]. As the materials science community shifts from empirical process-property correlations to microstructure-driven material development, optimizing materials for quality assurance, research, and sustainability has become increasingly critical, especially in the context of resource preservation and climate change. Today, microstructure analysis is still frequently performed manually and often provides qualitative statements only, making them a bottleneck in microstructure-based materials development and process control. A microstructure analysis pipeline generally consists of a metallographic preparation step, followed by contrasting, a segmentation of the microstructural components and their quantification and classification. Especially for these latter analysis steps, machine learning (ML) approaches promise substantial benefits [2]. In fact, ML has already replaced conventional solutions in computer vision and is employed, for example, for obstacle recognition in autonomous driving [3]. As many human vision tasks cannot be adequately solved using a simple deterministic, rule-based solution, the significance of ML lies in the fact that it makes problems accessible to automatic processing by computers for which full mathematical modeling is hopeless.