No abstract

Based on the results of tests on feed coal from the Lublin Coal and Upper Silesian Coal Basin and its fly ash and slag carried out using X-ray diffraction and X-ray fluorescence analysis, atomic emission spectroscopy, and scanning electron microscopy, it was found that in feeds, coal Th is associated with phosphates and U with mineral matter. The highest Th content was found in anhedral grains of monazite and in Al-Si porous particles of fly ash of <0.05 mm size; whereas in the slag, Th is concentrated in the massive Al-Si grains and in ferrospheres. U is mainly concentrated in the Al-Si surface of porous grains, which form a part of fly ash of <0.05 mm size. In the slag, U is to be found in the Al-Si massive grains or in a dispersed form in non-magnetic and magnetic grains. Groups of mineral phase particles have been identified that have the greatest impact on the content of Th and U in whole fly ash and slag. The research results contained in this article may be important for predicting the efficiency of Th and U leaching from furnace waste storage sites and from falling dusts to soils and waters.

The study included 24 samples of coal with 7 cores, boreholes (7 coal seams), made by the Polish Geological Institute in Warsaw at the site of a Chelm field and 6 coal samples taken from 2 decks in the Lublin Coal mine „Bogdanka“ S.A. in LCB. Based on performed tests found generally low levels of Sb and Bi in coal. In the vertical profile of the LCB contents of Bi and Sb in coal generally increases from coal seams younger to older age. Content of Bi in coal from roof part coal seams is usually higher, and ash content in the coal content of Sb are generally lower than in the carbon of the middle part decks. The content of Bi in the lateral coal deposits is unlikely to vary, and the gap in the coal content of Bi between the sampling regions coal do not exceed 1.7 g / Mg. In contrast gap Sb content in coal on the extent LCB is from 1.7 g / Mg of 5.8 g / Mg. The biggest influence on the content of Bi and Sb in coal from the LCB is probably organic matter in which these elements are scattered and do not form their own minerals.

The study of the petrographic structure of medium- and high-rank coals is important from both a cognitive and a utilitarian point of view. The petrographic constituents and their individual characteristics and features are responsible for the properties of coal and the way it behaves in various technological processes. This paper considers the application of convolutional neural networks for coal petrographic images segmentation. The U-Net-based model for segmentation was proposed. The network was trained to segment inertinite, liptinite, and vitrinite. The segmentations prepared manually by a domain expert were used as the ground truth. The results show that inertinite and vitrinite can be successfully segmented with minimal difference from the ground truth. The liptinite turned out to be much more difficult to segment. After usage of transfer learning, moderate results were obtained. Nevertheless, the application of the U-Net-based network for petrographic image segmentation was successful. The results are good enough to consider the method as a supporting tool for domain experts in everyday work.

No abstract