Robust YOLO-Based Ejection of Copper-Containing Particles in Heavily Corroded Scrap Towards Green-Steel Production

The current transition from conventional blast furnaces to electronic arc furnaces is a viable path to reducing CO2 emissions during steel production. However, this transition of technologies changes the requirements for possible scrap that may be used as a secondary raw material during EAF steel production. Copper is especially challenging, as it remains in the melt, reducing the mechanical properties of the produced crude steel while being lost to any secondary use. Currently, the two main routes to reduce the copper content are X-Ray Fluorescence sorting and manual sorting. We propose a third approach by using computer vision and machine learning methods to detect copper-containing particles in a post-shredder scrap fraction on low-cost and low-powered hardware. Furthermore, this proposed method is robust to environmental factors, such as heavily corroded particles caused by prolonged storage without proper weather protection. This method can effectively reduce the need for expensive XRF equipment or manual sorting. The developed sorting pipeline was examined in an industrial setting through sorting trials and achieved 99.9 wt.% purity in the produced iron fraction at throughputs of over 3 t/h.