Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: mineral identification

Sortuj według:

Ogranicz wyniki do:

Determination of the liberation size of Mekaneselam iron ore in the southern wollo zone, northern Ethiopia: implications for benefificiation

Meseret Getahun, Kebede Bisrat, Digafe Belayneh

Journal of Sustainable Mining

2025

Vol. 24, iss. 1

53--64

Previous investigations in the target area primarily focused on ore genesis or the geological formations of the ore deposit, neglecting the specific beneficiation aspects associated with the ore. Due to gaps with respect to beneficiation aspects,the research aimed to determine the liberation size of the target ironbearing ore mineral through mineralogical identification, chemical composition analysis, and examination of the particle size distribution. In this study, various methods were employed, including atomic absorption spectrometry (AAS), X-ray fluorescence (X-RF), X-ray diffraction (XRD) analysis, and sieve analysis. The chemical composition analysis of Mekaneselam iron ore revealed significant amount of 16.55–77.59 % Fe2O3, 7.31–59.02% SiO2, 1.44–17.38% Al2O3, and minor compositions of P2O5 resulting from X-RF and AAS compositional analysis. P80 of the ground ore sample occurred at a size of 1100μm. The size-wise chemical compositional analysis using AAS indicated a higher weight percentage of the target ore mineral within the sieve size range of (-250μm +180μm). This indicates ,the appropriate liberation size of the target iron-bearing ore mineral falls within the sieve size range of (-250μm and +180μm).This finding is most important as it provides crucial information for the beneficiation process, allowing for the optimization of grinding and subsequent extraction operations.

Optimized 3D-2D CNN for automatic mineral classification in hyperspectral images

Attallah Youcef, Zigh Ehlem, Adda Ali Pacha

Reports on Geodesy and Geoinformatics

2024

Vol. 118

82--91

Mineral classification using hyperspectral imaging represents an essential field of research improving the understanding of geological compositions. This study presents an advanced methodology that uses an optimized 3D-2D CNN model for automatic mineral identification and classification. Our approach includes such crucial steps as using the Diagnostic Absorption Band (DAB) selection technique to selectively extract bands that contain the absorption features of minerals for classification in the Cuprite zone. Focusing on the Cuprite dataset, our study successfully identified the following minerals: alunite, calcite, chalcedony, halloysite, kaolinite, montmorillonite, muscovite, and nontronite. The Cuprite dataset results with an overall accuracy rate of 95.73 % underscore the effectiveness of our approach and a significant improvement over the benchmarks established by related studies. Specifically, ASMLP achieved a 94.67 % accuracy rate, followed by 3D CNN at 93.86 %, SAI-MLP at 91.03 %, RNN at 89.09 %, SPE-MLP at 85.53 %, and SAM at 83.31 %. Beyond the precise identification of specific minerals, our methodology proves its versatility for broader applications in hyperspectral image analysis. The optimized 3D-2D CNN model excels in terms of mineral identification and sets a new standard for robust feature extraction and classification.