Big data analysis is becoming a daily task for companies all over the world as well as for Russian companies. With advances in technology and reduced storage costs, companies today can collect and store large amounts of heterogeneous data. The important step of extracting knowledge and value from such data is a challenge that will ultimately be faced by all companies seeking to maintain their competitiveness and place in the market. An approach to the study of metallurgical processes using the analysis of a large array of operational control data is considered. Using the example of steel rolling production, the development of a predictive model based on processing a large array of operational control data is considered. The aim of the work is to develop a predictive model of rolling mill roll wear based on a large array of operational control data containing information about the time of filling and unloading of rolls, rolled assortment, roll material, and time during which the roll is in operation. Preliminary preparation of data for modeling was carried out, which includes the removal of outliers, uncharacteristic and random measurement results (misses), as well as data gaps. Correlation analysis of the data showed that the dimensions and grades of rolled steel sheets, as well as the material from which the rolls are made, have the greatest influence on the wear of rolling mill rolls. Based on the processing of a large array of operational control data, various predictive models of the technological process were designed. The adequacy of the models was assessed by the value of the mean square error (MSE), the coefficient of determination (R²), and the value of the Pearson correlation coefficient (R) between the calculated and experimental values of the mill roll wear. In addition, the adequacy of the models was assessed by the symmetry of the values predicted by the model relative to the straight line Ypredicted = Yactual. Linear models constructed using the least squares method and cross-validation turned out to be inadequate (the coefficient of determination R² does not exceed 0.3) to the research object. The following regressions were built on the basis of the same operational control database: Linear Regression multivariate, Lasso multivariate, Ridge multivariate, and ElasticNet multivariate. However, these models also turned out to be inadequate to the object of the research. Testing these models for symmetry showed that, in all cases, there is an underestimation of the predicted values. Models using algorithm composition have also been built. The methods of random forest and gradient boosting are considered. Both methods were found to be adequate for the object of the research (for the random forest model, the coefficient of determination is R² = 0.798; for the gradient boosting model, the coefficient of determination is R² = 0.847). However, the gradient boosting algorithm is recognized as preferable thanks to its high accuracy compared with the random forest algorithm. Control data for symmetry in reference to the straight line Ypredicted = Yactual showed that, in the case of developing the random forest model, there is a tendency to underestimate the predicted values (the calculated values are located below the straight line). In the case of developing a gradient boosting model, the predicted values are located symmetrically regarding the straight line Ypredicted = Yactual. Therefore, the gradient boosting model is preferred. The predictive model of mill roll wear will allow rational use of rolls in terms of minimizing overall roll wear. Thus, the proposed model will make it possible to redistribute the existing work rolls between the stands in order to reduce the total wear of the rolls.

The paper evaluates the behavior of a red-mud solid fraction in a thickener feeder cup, aiming to identify the main characteristics of particle distribution in the flocculation zone and to determine the dependencies affecting the further process taking place in the particle-free sedimentation zone in the thickener-thickening unit. This work used mathematical and numerical modeling to study the influence of such parameters as the flow rate of the feed pulp in the thickener, the flow rate of the flocculant, the density of pulp at the inlet to the unit, and the viscosity and temperature of the pulp on the particle-size distribution from under the feeder cup. The results and dependencies obtained are intended to be used as nominal values in the red-mud thickening process performed on a lab-scale unit.

The relevance of the research is due to the need to stabilize the composition of the melting products of copper-nickel sulfide raw materials in the Vanyukov furnace. The goal of this research is to identify the most suitable methods for the aggregation of the real time data for the development of a mathematical model for control of the technological process of melting copper-nickel sulfide raw materials in the Vanyukov furnace. Statistical methods of analyzing the historical data of the real technological object and the correlation analysis of process parameters are described. Factors that exert the greatest influence on the main output parameter (copper content in matte) and ensure the physical-chemical transformations are revealed. An approach to the processing of the real time data for the development of a mathematical model for control of the melting process is proposed. The stages of processing the real time information are considered. The adopted methodology for the aggregation of data suitable for the development of a control model for the technological process of melting copper-nickel sulfide raw materials in the Vanyukov furnace allows us to interpret the obtained results for their further practical application.

The approach to the study of metallurgical processes with the help of analysis of the trends of dependencies of the main parameters on the technological process is considered. The adopted technique for experimental data processing makes it possible to interpret the results obtained for their further practical application. The way of definition of probabilistic dependences between variables of the research object, checking the efficiency of ACS control using the basic material flows, and quality of a target product is presented. The influence of individual factors on the composition of the desired product is analyzed.

This paper substantiates why it is necessary to reduce the concentration of sodium hydroxide in red mud before it can be transported to the mud disposal area and why the liquid-to-solid ratio should be maintained after each unit of the thickening and washing line. The main unit is a single-tier radial thickener comprised of flocculation, free settling, hindered settling and rake zones. The paper gives a brief overview of the basic mathematical formulas describing the hindered and free settling zones of the thickener, as well as the basic material balance equations for describing the countercurrent washers. At the studied site, no reagent is added at the washing stage and there is no flocculation zone in the washers. The first part of experimental study focused on red mud thickening with addition of dissolved flocculant that is normally used at the studied site, considering how it is prepared and injected. Sedimentation curves for red mud samples with different concentrations of solids in the feed stream were obtained. The authors substantiate the application of modified Kynch method for calculating empirical parameters based on sedimentation curves. The following parameters were calculated: settling rate, average Stokes diameter of a flocculated particle, critical concentration (gel point), hindered settling index. The Kynch flux density functions were calculated for different concentrations of solids in the initial slurry. The second part of experimental study focused on countercurrent washing of the earlier flocculated slurry. Following a series of periodic experiments on sedimentation of flocculated slurry involving 3, 4, 5 and 6 cycles of countercurrent washing, conclusions were drawn on the concentration of sodium hydroxide at each washing stage, and the washing efficiency was estimated. The described results will be used for building a mathematical model of a radial thickener at the thickening and washing stage.

All production processes are controlled by control systems, in which several information flows are generated. However, operators only use a small percent of this information as the processing capacity of a human mind is limited. The paper demonstrates that production process control is to a great extent influenced by human factor. The paper describes a production data processing technique that enables the personnel to make a better use of their resources for operations control. An approach is considered to studying metallurgical processes through analysis of indirect indicators – i.e. the spectral density and autocorrelation function of the key process indicator signals. A method is described to check the efficiency of material flow control systems. The above techniques were applied to a big array of monitoring data collected during a 24-hour smelting operation for copper-nickel sulphide material. Data from three different shifts were used for this analysis. Different operators have different control patterns. The proposed technique, which enables to analyze big arrays of monitoring data, helps minimize the human factor. The adopted experimental data processing technique helps interpret the obtained results for further practical use, development of new control algorithms and optimization of the current control system.