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.
