Academic Journal
Hyperspectral scrap characterisation for scrap composition optimisation in steel recycling.
| Τίτλος: | Hyperspectral scrap characterisation for scrap composition optimisation in steel recycling. |
|---|---|
| Συγγραφείς: | Gursch H; Methods and Algorithms for AI, Know Center Research GmbH, Graz, Austria., Ofner A; Methods and Algorithms for AI, Know Center Research GmbH, Graz, Austria., Harb R; Institute of Computer Graphics and Vision, Graz University of Technology, Austria., Jaschik M; DIGITAL, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Graz, Austria., Ganster H; DIGITAL, JOANNEUM RESEARCH Forschungsgesellschaft mbH, Graz, Austria., Rieger J; Area 1, K1-MET GmbH, Leoben, Austria. |
| Πηγή: | Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA [Waste Manag Res] 2026 Oct; Vol. 44 (10), pp. 1768-1776. Date of Electronic Publication: 2026 Jun 17. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Sage Publications Country of Publication: England NLM ID: 9881064 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1096-3669 (Electronic) NLM ISO Abbreviation: Waste Manag Res Subsets: MEDLINE |
| Imprint Name(s): | Publication: Original Publication: London ; New York : Academic Press, c1983- |
| Ιατρικοί όροι (MeSH): | Steel*/analysis , Recycling*/methods , Hyperspectral Imaging*, Convolutional Neural Networks ; Multilayer Perceptrons |
| Περίληψη: | Steel is an ideal recycling material as it can be recycled almost indefinitely, and steel recycling is a lot more energy-efficient than iron ore steel production. Steel making with usage of steel scrap in electric arc furnaces is heavily influenced by contaminants in the scrap, including non-ferrous metals, stones, or plastic. To produce high-quality steel, it is important to know what contaminants are part of the scrap to adapt the recycling process accordingly. This work presents a three-part processing pipeline to determine the scrap composition and optimise the recycling process parameters. The first part is hyperspectral imaging, recording images with 437 spectral bands in the short-wave infrared range. Next, deep learning-based image recognition, with multilayer perceptron, 2D and 3D convolutional neural networks (CNNs) have been compared. The 3D-CNN showed the best performance in detecting the 14 material classes in the scrap samples. Finally, a mixed integer optimisation is used to select the best scrap mix for the steel classes that are to be produced. The evaluation shows an accuracy of about 76% in detecting the 14 material classes correctly, with a higher accuracy for the steel class. The detected non-ferrous materials determine the scrap class which is input for the optimisation with its constraints that each scrap class has a minimum consumption to prevent storage overflows, and as little energy and additives as possible should be used. |
| Competing Interests: | Declaration of conflicting interestsThe authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. |
| Contributed Indexing: | Keywords: deep learning; hyper-spectral imaging; image recognition; machine learning; optimisation; steel scrap recycling |
| Substance Nomenclature: | 12597-69-2 (Steel) |
| Entry Date(s): | Date Created: 20260618 Date Completed: 20261001 Latest Revision: 20261001 |
| Update Code: | 20261001 |
| PubMed Central ID: | PMC13612865 |
| DOI: | 10.1177/0734242X261451604 |
| PMID: | 42311089 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1096-3669 |
|---|---|
| DOI: | 10.1177/0734242X261451604 |