Abstract
The analysis of non-metallic inclusions is crucial for the assessment of steel properties. Scanning electron microscopy (SEM) coupled with energy dispersive spectroscopy (EDS) is one of the most prominent methods for inclusion analysis. This study utilizes the output generated from SEM/EDS analysis to predict inclusion types from BSE images. Prediction models were generated using two different algorithms, Random Forest (RF) and convolutional neural networks (CNN), for comparison. For each method, three separate models were developed. Starting with a simple binary model to differentiate between inclusions and non-inclusions, then developing to more complex four and five class models. For the 4-class model, inclusions were split into oxides, sulfides, and oxy-sulfides, in addition to the non-inclusion class. The 5-class model included specific types of inclusions only, namely alumina, calcium aluminates, calcium sulfides, complex calcium-manganese sulfides, and oxy-sulfide inclusions. CNN achieved better accuracy for the binary (92%) and 4-class (78%) models, compared to RF (binary 87%, 4-class 75%). For the 5-class model, the results were similar, 60% accuracy for RF and 59% for CNN.
Highlights
Steel production methods have consistently evolved toward producing material with lower impurity levels and better properties
We investigate the use of machine learning and computer vision methods to extract information on inclusion chemical composition from backscattered electron (BSE) Scanning electron microscopy (SEM) images
It was assumed that all Mn would be in the form of MnS, the remaining S would be in calcium sulfides (CaS), and all other inclusions would be in the form of oxides
Summary
Steel production methods have consistently evolved toward producing material with lower impurity levels and better properties. Efforts in this area are generally referred to as “clean steel” production, with the level of cleanliness required depending on the product requirements. It is generally accepted that clean steels have a low frequency of product defects due to the presence of non-metallic inclusions (Cramb and Briant, 1999). Non-metallic inclusions are oxide, sulfide, or nitride particles that are present in the liquid metal. They form due to chemical reactions occurring during steelmaking and by entrainment of oxide slag and refractory materials. The analysis of non-metallic inclusions is crucial for the assessment of steel properties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
