Classification of steel scrap in the EAF process using image analysis methods

Industrial practice and market situation shows that there is still a big degree of uncertainty when it comes to scrap material properties in EAF process. Fast development of machine vision technology and software allow to challenge with this problem. The main goal of this work is to extract the most information for the process of loading scrap into the charging baskets. Data concerning transferred scrap are acquired from digital industrial camera and processed by the mean of image analysis methods. There are certain image features, which allow to describe the scrap for the classification. The extracted features will be used to build the machine vision system for steel scrap classification. Research on the intelligent control of the electric-arc steelmaking process is done by the authors within the research project.