Applying Improved Optical Recognition with Machine Learning on Sorting Cu Impurities in Steel Scrap
- PDF / 2,260,741 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 87 Downloads / 154 Views
RESEARCH ARTICLE
Applying Improved Optical Recognition with Machine Learning on Sorting Cu Impurities in Steel Scrap Zhijiang Gao1 · S. Sridhar1 · D. Erik Spiller1 · Patrick R. Taylor1 Received: 26 May 2020 / Accepted: 29 September 2020 © The Minerals, Metals & Materials Society 2020
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
Keywords Steel scrap · Cu impurities · Optical recognition · Convolutional neural networks The contributing editor for this article was Sharif Jahanshahi. * Zhijiang Gao [email protected] 1
Kroll Institute for Extractive Metallurgy, Mining Engineering Department, Colorado School of Mines, 1500 Illinois St., Golden, CO, USA
13
Vol.:(0123456789)
Journal of Sustainable Metallurgy
Introduction Steel Scrap Recycling Over 70% of steel is recycled today by re-melting scrap in electric-arc furnaces (EAF) [1] and the percentage of steel scrap present in the charge for EAF has been varied depending on the manufacture of final steel products. Obsolete scrap, which has been dominated by shredded automobile scrap, is the major source of steel scrap for steelmaking and could be treated as low grade considering the Cu content, as shown in Table 1 for the composition of different types of scrap and allowable limits of scrap residuals in industrial steel products [2]. Only reinforcing bar, which has a higher tolerance for Cu content, could be produced with sufficient grade through charging 100% obsolete scrap. But for producing high-value steel product, such as Interstitial Free (IF) steel, which is mainly utilized for automotive production, 100% charging of obsolete scrap is unacceptable. As a result, EAF operating plants have to adopt pig iron or other ironcontaining materials to blend with scrap [3]. This is because impurities such as Cu and Sn, accumulated in the obsolete scrap through wires and motors in cars and tin-plate, cause surface cracking when the produced st
Data Loading...
