Hyperspectral Imaging Applications for Steel Production

Date

2024-1-11

Author

Korkmaz, Özgür

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

262
views

0
downloads

Cite This

Steel production is the backbone of numerous infrastructure projects and industrial applications around the world. To maintain and improve its productivity, quality, and environmental sustainability, the steel industry is constantly looking for innovative technologies and methods. Hyperspectral imaging is a promising technology in this context. In this thesis, a novel, non-destructive approach is presented to quantify the free lime content in Basic Oxygen Furnace (BOF) slag by utilizing an integrated algorithm applied to hyperspectral images. This method includes spectral unmixing for mixture component quantification and endmember extraction of the mixture. The methodology involved various experiments with both fresh and six month aged BOF slag, demonstrating its accuracy compared to the Rietveld Analysis of X-ray Diffraction patterns, with a Root Mean Square Error of 5.57% for aged BOF slag and 6.51% for fresh BOF slag. Furthermore, the thesis explores the application of hyperspectral imaging in the identification of impurities in iron ore and the detection of copper deposits in continuous pickling lines through the use of hyperspectral analysis methods. As a result of the experiments, the impurities in the raw iron ore were identified and copper deposits were detected at various sensitivities on the steel sheet produced in the continuous pickling line process. An in-depth analysis of the challenges and limitations associated with the use of hyperspectral imaging in steel production is provided, including the effect of illumination conditions and validation methods.

Subject Keywords

Hyperspectral image processing, Unmixing models, Intimate mixture unmixing, Free lime measurement of BOF slag, BOF slag volume stability

URI

https://hdl.handle.net/11511/108310

Collections

Graduate School of Informatics, Thesis