| About this Abstract |
| Meeting |
2025 TMS Annual Meeting & Exhibition
|
| Symposium
|
REWAS 2025: Automation and Digitalization in Recycling Processes
|
| Presentation Title |
Optimizing Secondary Steel Production by Copper Contaminant Removal Using Artificial Intelligence |
| Author(s) |
Nalin Kumar, Isha Maun, Kanishka Tyagi |
| On-Site Speaker (Planned) |
Isha Maun |
| Abstract Scope |
The efficient removal of copper (Cu) contaminants from steel scrap is crucial for enhancing the quality and sustainability of secondary steel production. UHV Technologies Inc explores the application of artificial intelligence (A.I.) techniques to optimize this decontamination process. A.I. algorithms, including machine learning models, are employed to analyze and classify Cu contaminants of varying types, shapes, and sizes within the steel scrap. By leveraging advanced data analytics and pattern recognition, these A.I.-driven approaches aim to improve the efficiency and effectiveness of separation methods. Currently, the secondary steel production industry uses fresh steel material to reduce the contamination to the levels acceptable for material production. The presentation discusses how A.I. enables real-time efficient classification, enhances sorting accuracy, and contributes to overall productivity and decarbonization in secondary steel production. Experimental results and analysis on steel scrap decontamination are highlighted, illustrating the transformative potential of A.I. in metallurgical recycling processes. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Iron and Steel, Machine Learning, Recycling and Secondary Recovery |