Estimation of Impurities Present in an Iron Ore Using CNN

Iron ore is a crucial raw material for the production of steel, but its quality is dependent on the presence of impurities. In this study, we aimed to estimate the impurities present in an iron ore sample and assess their potential hazards. Using state-of-the-art analytical techniques, we found that the sample contained various impurities, including toxic compounds and radioactive materials. Our findings suggest that these impurities may have adverse effects on the quality of the iron ore and pose risks to the health and safety of workers and the environment. Mining companies should, therefore, take necessary measures to reduce the levels of impurities in their iron ore and ensure that they are producing high-quality and safe products. The proposed work attempts at the employment of Decision Tree algorithm for the retrieval of significant features from the dataset. Then these features would be inputted to Random Forest and Convolutional neural network for better prediction of presence of impurities and finally eliminating them. This study provides valuable insights into the composition and quality of iron ore and underscores the importance of responsible mining practices.