The relevance of the research is due to the acquisition of new knowledge about the features of the applicability of the support vector machine, related to machine learning tools, for solving problems of mathematical modeling of mining and processing equipment. The purpose of the research is a statistical analysis of the results of semi-industrial tests of the Knelson CVD technology on tin raw materials using the support vector machine method and the development of mathematical models suitable for further optimization of the technological parameters of the equipment. The objects of research were the products obtained as a result of the operation of hydro-cyclones, as well as the technological parameters of the operation of centrifugal concentrators. The work uses classical methods of mathematical statistics, the least squares method for constructing a linear regression model, the support vector machine implemented on the basis of the Scikit-learn library, as well as the method of verifying the resulting models based on the ShuffleSplit library. A general description of the process of testing the Knelson concentrator with continuous controlled unloading in relation to the enrichment of tin ores is presented. The results obtained were processed using the support vector machine. Regression models are obtained in the form of polynomials of the second degree and in the form of radial basis functions. A significant non-linearity is shown in the dependence between the content of the valuable component in the tailings and the values of the technological parameters of the apparatus.
The paper is devoted to developing a model of baddeleyite recovery from dump products of an apatite-baddeleyite processing plant using centrifugal concentrators. The relevance of the work arises from the acquisition of new knowledge on the optimization of technological parameters of centrifugal concentrators using Knelson CVD (continuous variable discharge) technology – in particular, setting the frequency of valve opening and the duration of valves remaining open. The purpose of the research was to assess the applicability of CVD technology in the treatment of various dump products of the processing plant and to build a model of dependencies between the concentrate and tailings yields and the adjustable parameters, which will allow to perform preliminary calculations of the efficiency of implementing this technology at processing plants. The research objects are middling and main separation tailings of the coarse-grained stream and combined product of main and recleaner separation tailings of the fine-grained stream. The study uses general methods of mathematical statistics: methods of regression analysis, aimed at building statistically significant models, describing dependence of a particular variable on a set of regressors; group method of data handling, the main idea of which is to build a set of models of a given class and choose the optimal one among them. Authors proposed an algorithm for processing experiment results based on classical regression analysis and formulated an original criterion for model selection. Models of dependencies between the concentrate and tailings yields and the adjustable parameters were built, which allowed to establish a relationship between the concentrate yield and the valve opening time, as well as a relationship between the tailings yield and the G-force of the installation.
The paper presents the analysis of studies of the enrichment of sulfide and oxidized ores in Yakutia deposits. The ore of the deposit is a mixture of primary, mixed and oxidized ores. The main useful component of the studied ore samples is gold with a content of 1.5 to 2.8 g/t, the silver content is low – 5-17 g/t. Ore minerals are represented by sulfides, among which pyrite predominates. The total sulfide content does not exceed 3-5 %. The presence in the ore of free and associated gold with a grain size from fractions of a micron to 1.5 mm. Gold is represented by nuggets in intergrowth with sulfides and also forms independent inclusions. Ores are classified as easily cyanidable. It was found that the content of amalgamable gold is 10-49, the share of cyanidable gold ranges from 66.67-91, the share of refractory gold is 9.0-33.33 %, which in absolute amount equals to 0.24-0.8 g/t. The extraction of gold in gravitation concentrate varies depending on the gold content in the ore and the yield of concentrate and for ores with a gold content of 1.5-2.8 g/t from 40 to 60 %. The direct cyanidation of all studied ore samples established the possibility of extracting gold into solution up to 86.7-92.9 %, the gold content in cyanidation cakes is 0.2-0.3 g/t. Investigations of the gravitation concentrate by the method of intensive cyanidation showed that with an initial gold content of ~ 500 g/t, up to 98.9 % is extracted into the solution. The gold content in intensive cyanide cakes will be 6-15 g/t. A set of studies carried out by the authors of the article at various institutes showed that it is advisable to process ore from the deposit using cyanidation technology with preliminary gravitational extraction of gold.