Applying Improved Optical Recognition with Machine Learning on Sorting Cu Impurities in Steel Scrap

Abstract: Cu impurities in scrap, originating from motors and wires, limit the efficiency of recycling steel scrap, especially for shredded automobile scrap, due to the occurrence of surface hot shortness during hot working resulting from high Cu content. Considering the distinct difference of color between metal Cu and Fe and the potential differences between shapes of shreds depending on Cu content, optical recognition was explored as a method for detecting and separating Cu-rich shreds. In order to optimize detection and minimize effects of surface inhomogeneity, etc., convolutional neural networks (CNNs) were adopted to improve the optical recognition of shredded scrap obtained from industrial sources. The results show that the proposed neural network achieves significantly better recognition on Cu impurities and results in a reduction of Cu content. An optimized accuracy of 90.6% could be obtained for recognizing Cu impurities through applied CNNs architecture with dataset of cropped photographs. This results in an overall reduction of Cu impurities from 0.272 to 0.087 wt% in steel scrap, if the identified Cu-rich parts were removed. Graphical Abstract: [Figure not available: see fulltext.]