The application of artificial intelligence for the identification of the maceral groups and mineral components of coal
人工智能在煤显微组分组及矿物成分鉴定中的应用
Computers & Geosciences, Volume 103, June 2017, Pages 133-141
Mariusz Mlynarczuk, Marta Skiba
Abstract:The correct and consistent identification of the petrographic properties of coal is an important issue for researchers in the fields of mining and geology. As part of the study described in this paper, investigations concerning the application of artificial intelligence methods for the identification of the aforementioned characteristics were carried out. The methods in question were used to identify the maceral groups of coal, i.e. vitrinite, inertinite, and liptinite. Additionally, an attempt was made to identify some non-organic minerals. The analyses were performed using pattern recognition techniques (NN, kNN), as well as artificial neural network techniques (a multilayer perceptron – MLP). The classification process was carried out using microscopy images of polished sections of coals. A multidimensional feature space was defined, which made it possible to classify the discussed structures automatically, based on the methods of pattern recognition and algorithms of the artificial neural networks. Also, from the study we assessed the impact of the parameters for which the applied methods proved effective upon the final outcome of the classification procedure. The result of the analyses was a high percentage (over 97%) of correct classifications of maceral groups and mineral components. The paper discusses also an attempt to analyze particular macerals of the inertinite group. It was demonstrated that using artificial neural networks to this end makes it possible to classify the macerals properly in over 91% of cases. Thus, it was proved that artificial intelligence methods can be successfully applied for the identification of selected petrographic features of coal.
A more accurate method for estimating in situ coal density and mineral matter from ash and specific energy determinations
基于灰分与比能值的准确估算现场煤密度与矿物质的方法
International Journal of Coal Geology, Volume 168, Part 2, 15 November 2016, Pages 237-252
Eric Robeck, Dennis Huo
Abstract:The estimation of in situ coal density has been the subject of extensive research due to its importance for coal reserve estimation. However, despite decades of studies, a universal method for density estimation that can be applied to all coal deposits still does not exist. Traditional ash-based methods are inaccurate because ash is a combustion product that does not contain the volatile mineral components which are lost upon combustion.
Coal is composed of three primary constituents: organic macerals, inorganic mineral matter, and moisture. Understanding the properties of the mineral matter is particularly critical for accurate density estimation. The method described herein improves the accuracy of density estimates by first estimating the mineral matter percentage of each sample using only ash and specific energy analyses, both of which are performed on the large majority of exploration samples. A least-squares hyperbolic formula is derived from the dry coal and mineral properties in order to estimate the dry sample density. The formula accepts two in situ moisture percentages, for both coal and rock, in order to estimate in situ density for coal and other lithologies.
This method has several advantages over existing techniques. It is valid for all values of ash, with no loss in accuracy outside a limited range. The scatter caused by mineral volatiles is reduced, resulting in a much higher correlation coefficient. Coal and mineral densities derived from the formula may also provide insight into the coal maceral and mineral types present within a project, as well as changes in mineralogy with ash content.
Analysis, origin and significance of mineral matter in coal: An updated review
煤中矿物质分析、起源及意义：最新综述
International Journal of Coal Geology, Volume 165, 1 August 2016, Pages 1-27
Colin R. Ward
Abstract:The material classed as “mineral matter” in coal embraces crystalline mineral materials as well as a range of inorganic elements that occur in non-crystalline form. This review outlines the methods that may be used to evaluate the percentage of mineral matter for a coal sample, as opposed to the ash yield, and to identify the minerals, their individual percentages, and their modes of occurrence within the coal. The principal techniques include low-temperature oxygen-plasma ashing; quantitative evaluation of X-ray diffraction data; observation using optical microscopy; and a combination of observation, chemical analysis and, in some cases, mapping based on scanning electron microscopy and related methods. A range of other techniques may also be used to provide additional information on particular mineral matter components.
Processes responsible for mineral matter formation include detrital input, biogenic activity, and authigenic precipitation at different stages of the coal's depositional and post-depositional history. Differential migration of non-mineral inorganic elements may also occur in lower-rank coals, and expulsion of non-mineral inorganics may take place with rank advance. Knowledge of the mineral matter may be of assistance in understanding the modes of trace element occurrence, with implications for assessing possible environmental impacts and also the potential for recovery of economic products from coal. The behaviour of different mineral matter components at high temperatures is also discussed, as well as methods for mineralogical analysis of ashes and other coal utilization products. Information from mineral matter studies may provide an improved basis for understanding coal formation, and for evaluating the response of particular coals to different combustion, gasification and coking processes.
Mineral matter, major and trace element content of the Afşin–Elbistan coals, Kahramanmaraş, Turkey
土耳其Kahramanmaraş地区Afşin–Elbistan煤的矿物质及主要与微量元素含量
International Journal of Coal Geology, Volumes 144–145, 1 May 2015, Pages 111-129
Emine Cicioglu Sutcu, Ali Ihsan Karayigit
Abstract:The Afşin–Elbistan coal basin is one of the most important coal deposits of Turkey. The mineral matter, major and trace element concentrations of the Afşin–Elbistan coals and their modes of occurrence are discussed in this study. The coal seam is located within the Upper Miocene–Pliocene aged Ahmetcik Formation which is represented by fluvial–lacustrine facies. Thickness of the coal zone is 80 m, but it reaches 105 m in the Kışlaköy sector. A total of 86 samples were taken from the Kışlaköy open-pit mine and from the 14 boreholes drilled by the General Directorate of Mineral Research and Exploration (MTA) for coal exploration. The proximate, XRD, SEM-EDS, major and trace element analyses were conducted on the samples. The studied coals are characterized by relatively high moisture, ash, total sulfur, volatile matter contents and low gross calorific values. The mineral matters of the Afşin–Elbistan coal are represented by calcite, quartz, pyrite, feldspar, aragonite, opal-CT, gypsum, jarosite and clay minerals. Strontium, Rb, Sm, Zr, Hf, Nb, Mo, U, Zn, Pb, As, Mn, Co, Cr and Ni concentrations detected by EDP-XRF are higher than the world brown coal values. Many of the trace elements showing positive correlations with ash content imply inorganic affinity. The element concentrations of the coals are mainly related to the carbonate, silicate, sulfide, phosphate, ore minerals and fossil shells. However, some elements have also organic affinities.
