Hyperspectral scrap characterisation for scrap composition optimisation in steel recycling
Heimo Gursch, Andreas Ofner, Robert Harb, Malte Jaschik, Harald Ganster, Johannes Rieger · 2026
Read Hyperspectral scrap characterisation for scrap composition optimisation in steel recycling by Heimo Gursch, Andreas Ofner, Robert Harb, Malte Jaschik, Harald Ganster, Johannes Rieger (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13612865.txt.
Description
Heimo Gursch and colleagues describe in 2026 a three-part system for sorting steel scrap by what it actually contains, so steel mills can recycle it into high-grade steel. Scrap is a valuable raw material, since reusing steel saves much energy compared with making it from ore. Stones, plastic, and non-iron metals mixed into scrap can spoil the melt, so mills need to know the mix before they start.
First, a special camera records 437 bands of short-wave infrared light from the scrap. Next, the team tested three kinds of deep learning to name 14 material classes in the images, and a three-dimensional network did best. Last, a math routine picks the scrap blend that best fits the steel grades to be made, turning inspection data into a practical recipe for the furnace.
Catalog record
| CREATOR | Heimo Gursch, Andreas Ofner, Robert Harb, Malte Jaschik, Harald Ganster, Johannes Rieger |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31139 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |