Abstract The detection and characterization of non-metallic inclusions are essential for clean steel production. Recently, imaging analysis combined with high-dimensional data processing of metallic materials using artificial intelligence (AI)-based machine learning (ML) has developed rapidly. This technique has achieved impressive results in the field of inclusion classification in process metallurgy. The present study surveys the ML modeling of inclusion prediction in advanced steels, including the detection, classification, and feature prediction of inclusions in different steel grades. Studies on clean steel with different features based on data and image analysis via ML are summarized. Regarding the data analysis, the inclusion prediction methodology based on ML establishes a connection between the experimental parameters and inclusion characteristics and analyzes the importance of the experimental parameters. Regarding the image analysis, the focus is placed on the classification of different types of inclusions via deep learning, in comparison with data analysis. Finally, further development of inclusion analyses using ML-based methods is recommended. This work paves the way for the application of AI-based methodologies for ultraclean-steel studies from a sustainable metallurgy perspective.
Lian et al. (Sun,) studied this question.