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.
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.
Distributing the red-sludge flow between paralleled thickeners is a relevant problem for controlling the process of thickening and washing the alumina sludge. Sludge sticks to thickener walls and rakes in operation, which reduces the effective volume of the machine and puts a greater strain on the rakes; raising the rakes is necessary to avoid breaking the stirrer, but this reduces the compacting rate of the thickened product. Redistributing the feed pulp between thickeners over the course of their gradual uneven contamination might solve the problem of the thickened product being under-compacted in the thickening-washing line. There are patents that address this issue; however, they only describe semiautomatic approaches. The problem has been covered to a great extent by Russian scientists and engineers such as M V Levin, T B Potapova, V V Aleksandrov, T G Milberger, P F Minin, I M Fain, R M Khamidov, as well as by the following institutions: All-Union Research and Development Institute of Aluminum, Magnesium, and Electrode Industries, Pikalevo Alumina Plant, Pavlodar Aluminum Plant. The paper describes the algorithm of an artificial immune system for redistributing the red-sludge flow in alumina production between paralleled thickeners.
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.
Abstract. 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. IntroductionThe mathematical models are becoming more significant in researching metallurgical processes and solving optimization tasks. They make visible the correlation between input variables and output variables. There are no unified methods for developing these models. This is due to a large variety of control object's types [1-9]: static and dynamic, continuous and discrete, deterministic and stochastic, etc. Each method starts with data wrangling. There are several methods of technological data wrangling for modeling [7][8][9], but they are not determinated for metallurgical processes.The goal of this research is to determine the most suitable methods for wrangling technological data for developing and using a mathematical model of the technological process of melting coppernickel sulfide raw materials in the Vanyukov furnace. The control process data of the Vanyukov process during 5 months were examined. The analysis of the operational control data of the Vanyukov process showed (Figure 1) that the copper content in matte varies between 46 and 68%. The variation range is more than 20% while the average copper content in matte is 58%. This indicates to the heterogeneity of data (a large variety in data relative to a mean value), low predictability of copper content in matte and low stability of the process. The low stability of the process makes the predictability difficult. So the data of these processes have to be prepared before modelling.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.