Methodological aspects of applying artificial neural networks for geodynamic zoning of territories when selecting locations for environmentally hazardous facilities (as exemplified by nuclear fuel cycle facilities) are considered. To overcome the uncertainty caused by complexity of the analysis of information about the properties, processes, and structure of the geological environment, a system approach to analyzing the information is used. Geological environment is presented as a system of interacting anthropogenic facility and natural environment, between which connections are organized. When assessing safety of such system operation, it is important to monitor environmental condition indicators. According to modern regulatory requirements of both international and domestic organizations, one of the main, and at the same time difficult to determine indicators of the condition of the nuclear fuel cycle facilities sites, are modern movements of the earth's crust. In the paper, we presented a method for predicting modern movements of the earth's crust based on artificial neural networks. Based on the predicted kinematic characteristics of the earth's crust, it is possible to identify zones that are dangerous in the manifestation of geodynamic processes: tension, compression, elastic energy accumulation zones, and so on. Preliminary results obtained on the presented neural network architecture showed positive prospects of applying this methodology for solving geodynamic zoning problems.

Methods of assessing quality of perimeter blasting when driving mine workings are considered. One of the main criteria is achieving “smooth” working contour. It is shown that a working contour line is a fractal object, geometry of which is adequately estimated by the fractional fractal dimensionality. Determining fractal dimensionality is based on Richardson’s law, connecting the length of an infinitely broken line with a measurement step. An algorithm for calculating the fractal dimensionality in computer software program is presented. Analysis of actual contours of underground workings produced using drilling and blasting operations allowed identifying statistically valid relationship between working surface roughness factor and the value of its fractal dimensionality. A criterion for assessing quality of perimeter blasting is proposed — fractal factor of a working shape. Its value is the ratio of the area of the working equivalent section to its squared perimeter, determined by fractal dimensionality of the contour line. The obtained relationships allow reliable assessing quality of perimeter blasting when driving mine workings.

For optimizing control of ore preparation processes, a complex criterion “yield of productive class −2... +10 mm” adapted to the conditions of closed cycle crushing – screening was proposed, which reflects the efficiency of all the processes as a whole. The established dependences of yields of individual ore grain-size fractions and the proposed optimization criterion on the parameters of the crushing process show their relationship with energy intensity of the process. It was shown that increasing load on the screen causes decreasing screening efficiency and increasing mass fraction of +2 mm grain-size fraction in the circulating ore. Excessive increasing width of the crusher relieve slot causes increasing output of the circulating product and increasing energy consumption. Decreasing relieve slot below 7.5 mm leads to increasing yield of −2 mm fraction. Improved system and algorithm for visiometric analysis of ore grain-size were proposed and tested. Ore grain-size control sensors are located above the conveyors for transportation of the screening oversize and undersize. The visiometric analysis mode provides for consecutive switching on/off the feeding conveyors and crushers, which ensures the flow of crushed product from one crusher into the measurement zone. Total duration of the grain-size analysis for ores from 6 crushers amounts to 12 minutes that does not affect the final productivity. The developed algorithm application enables significant increasing accuracy of the crushed ore grain-size analysis and reducing energy consumption at the ore preparation stage.

To create more effective dialkyldithiophosphate collector for use in combination with potassium butyl xanthate in silver ore flotation (for Ducat deposit ores), the effect of a number of dialkyldithiophosphate collectors was studied depending on their surface-active properties and water-repelling ability. It was shown that their collecting ability, at rather similar water-repelling ability increases with strengthening their surface-active properties and reaches maximum at surface tension of 42–45.3 mN/m, and then begins to decrease. The water repellent ability decrease, even at their high surface-active properties, for example, for hydrolyzed samples, significantly reduces silver recovery. Taking into account the studied effect of surface activity and water repellent ability of the reagents, a more efficient dialkyldithiophosphate collector has been developed, which increases silver recovery compared to the standard reagent by 1.8–3.4% depending on ore dressability. Optimal ratio of the proposed dialkyldithiophosphate collector and xanthate dosing also contributes to increasing silver recovery with no reducing the process selectivity.