Khanh Hoa coal mine (Thai Nguyen province) is one of the largest coal mines in the north of Vietnam. For many years, this area suffered from underground fires at coal mine waste dumps, seriously affecting production activities and the environment. This paper presents the results of classification of underground fire areas at Khanh Hoa coal mine using Normalized Diference Coal Fire Index (NDCFI). 03 Landsat 8 OLI_TIRS images taken on December 2, 2013, December 10, 2016, and December 3, 2019 were used to calculate NDCFI index, and then classify the underground fire areas by thresholding method. In the study, the land surface temperature was also calculated from Landsat 8 thermal infrared bands data, and then compared with the results of underground coal fire classification at Khanh Hoa coal mine. The obtained results showed that the NDCFI index can be used effectively in detecting and monitoring underground fire areas at coal mines. The use of the NDCFI index also has many advantages due to its calculation simplicity and rapidness compared to other methods for classifying underground coal fire areas.

The paper is devoted to studying the possibility of using artificial neural networks (ANN) to estimate ground subsidence caused by underground mining. The experiments showed that the most suitable network structure is a network with three layers of perceptrons and four neurons in the hidden layer with the back propagation algorithm (BP) as a training algorithm. The subsidence observation data in the Mong Duong underground coal mine and other parameters, including: (1) the distance from the centre of the stope to the ground monitoring points; (2) the volume of mined-out space; (3) the positions of the ground points in the direction of the main cross-section of the trough; and (4) the time (presented by cycle number), were used as the input data for the ANN. The findings showed that the selected model was suitable for predicting subsidence along the main profile within the subsidence trough. The prediction accuracy depended on the number of cycles used for the network training as well as the time interval between the predicted cycle and the last cycle in the training dataset. When the number of monitoring cycles used for the network training was greater than eight, the largest values of RMS and MAE were less than 10 % compared to the actual maximum subsidence value for each cycle. If the network training was less than eight cycles, the results of prediction did not meet the accuracy requirements.

In the process of underground mining of deep levels rock pressure can appear in any form, creating a serious threat to the lives of miners, disrupting the normal course of mining works and reducing the efficiency of mining production. The solution of the problem of rock pressure control becomes very urgent for underground mines developing vein deposits at a depth of more than 250 m. The aim of the study is the development and justification of mining methods to provide safe and efficient mining of deposits in complicated mining and mechanical conditions. In this paper, the factors of redistribution and dangerous concentration of stresses in the mined ore mass were identified, the methods of rock mass management in complicated geotechnical conditions were studied, and their advantages and disadvantages were revealed. It was determined that the sublevel stoping with the combined use of existing methods of rock pressure control and applying selfpropelled mining machinery is currently one of the most promising method finding widening application scope. In the context of Zarmitan gold ore zone the options of technological schemes of the sublevel stoping method were considered, providing for a combination of different methods of rock pressure control, allowing to minimize the disadvantages of one method through using the advantages of other ones. We proposed sublevel stoping options with artificial polygonal pillars and with artificial columnar pillars, which allowed to reduce ore losses in inter-stope pillars, arch pillars, and secondary dilution. In addition, artificial pillars, taking compressive/tensile stresses, prevent their concentration and create safe conditions for extraction at adjacent and underlying levels.

Grain size distribution as a structural characteristic of waste rock and bulk masses in the course of mining and construction works acquires quantitative values in the process of rock blasting and hauling of rock mass. Such physical-mechanical and structural-textural parameters of a rock mass, as the ultimate strength of rocks and rock mass, fracturing, diameter of the natural rock jointing, have a significant impact on the blasted rock mass grain size distribution. On the other hand, such characteristics as stability, permeability of waste rock masses largely depend on the lithology and grain size distribution of the loosened rocks composing waste rock dumps and their height distribution within a dump. The paper describes the findings of the study of the grain size distribution of waste rock masses of Kuzbass coal strip mines and the features of its spatial variations within the masses. The textures of the bulk masses and physical and technical properties of the stacked rocks were studied both at the Kuzbass waste rock sites and in laboratory conditions. The grain size distribution of the fine lump part of the dumps with the lump size up to 50 mm was investigated by sieve method according to GOST 12536–2014, and the medium and large lump part was studied using oblique photoplanimetry. The field observations showed that the bottom part of the rock dumps, dumped by peripheral bulldozer or excavator methods was composed of coarse fraction with average lump size of: d_cr = 0.8–1 m, while the middle part, of rock lumps of d_cr = 0.4–0.6 m, and the upper part, mainly of fine fraction with lump size of less than 0.1 m. The ratio of length, width, and thickness of the blasted rock lumps was 1:0.85:0.8, which corresponds to elongated-flattened shape of the lumps. This requires significant number of coordinates for describing the lump positions in the rock mass, as well as taking into account the moments of inertia when modeling the motion of such lumps until they reach a stable position. Up-to-date non-commercial or commercial software and corresponding hardware can be used to take into account non-isometric shape of the lumps when modeling their motion.

At present, Kuzbass coal strip mines pay great attention to improving quality performance of mining equipment operation, including reliability and durability of components and units. One of the ways of the performance improvement is decreasing number of unforeseen failures. To achieve this purpose a mine dump truck part diagnostics should be introduced into a maintenance service procedure. At the same time the process of diagnostics should not increase the machinery downtime, but effectively reveal a condition of motor-wheel gearboxes in the course of dump truck operation. The aim of the research is to increase the reliability and service life of motor-wheel gearboxes of large BelAZ dump trucks. Failure of a motor-wheel gearbox is a rare phenomenon, but the cost of a new gearbox can vary from 3.5 to 10 million rubles. That is why it is important to implement such methods of diagnostics, which allow revealing the condition of gearboxes in the shortest possible time and without disassembling corresponding units. Determination of the actual technical condition of motor-wheel gearboxes is possible by different methods: vibroacoustic; acoustic; thermal; physical and chemical analysis of spent operating materials. The studies showed that none of these methods can be used as a universal one. When justifying and selecting the most suitable method, different factors should be considered, including technological, or a combination of methods should be applied, which will reduce risks, but at the same time increase costs. It is necessary to develop a better diagnostic method based on the use of several methods simultaneously.