Machine Learning Methods for the Prediction of the Inclusion Content of Clean Steel Fabricated by Electric Arc Furnace and Rolling

Machine Learning classification models have been trained and validated from a dataset including experimental information of a clean cold forming steel fabricated by electric arc furnace and hot rolling. The dataset comprises 73 features and 13,616 instances. A classification model was developed to identify inclusion contents above the median. The following algorithms were implemented: Logistic Regression, K-Nearest Neighbors, Decision Tree, among others, to accurately predict the inclusion content. The results reveal that machine learning techniques can effectively be employed to enhance the understanding and reliability of clean steel production processes, ultimately leading to improved quality control. Furthermore, the study demonstrates that the chosen models can significantly assist in predicting critical parameters, thereby facilitating better-informed decision-making in industrial applications. The findings emphasize the potential benefits of integrating advanced machine learning methods into the steel manufacturing industry, providing a solid foundation for further research in this area.