Abstract
The paper analyzes the geological and mineralogical features of a pyritic polymetallic deposit. The use of Kohonen neural networks in solving the problem of technological typification of this type of ore is justified, since the flotation process is essentially a multifactorial and nonlinear object. The associative method of analyzing phenomena is more direct and visual than the “implicit” setting of connections or regularities in the form of a formalized mathematical model of a narrow range of phenomena. In the case of Kohonen neural network modeling, the image of a multidimensional space on a single plane in the form of a two-dimensional grid, on which the trend of changes in the processed ore mixture can be applied, is more adequately perceived by the operator. To achieve higher reliability in the identification of topological Kohonen maps for diagnostic purposes a methodology is proposed, which includes the interpretation of calculated average values of studied parameters of all neurons, using the method of factor analysis, design of selected neurons on the plane of the main components Fi – Fj and applying on them the physical values of the vectors of the measured parameters and contour lines of output functions. The developed technology can be introduced at the plant online with the help of express data analysis control, which allows you to promptly change the reagent modes in order to achieve higher metal recovery and better quality of the resulting concentrates.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Nikolaeva, N., Aleksandrova, T., Romashev, A.: Effect of grinding on the fractional composition of polymineral laminated bituminous shales. Miner. Process. Extr. Metall. Rev. 39(4), 231–234 (2018). https://doi.org/10.1080/08827508.2017.1415207
Kuznetcov, V.V., Aleksandrova, T.N.: Methods for efficiency evaluation of flotation recovery of precious metals from sulphide raw materials. In: Topical Issues of Rational use of Natural Resources - Proceedings of the International Forum-Contest of Young Researchers 2018, pp. 211–216 (2019)
Nikolaeva, N., Romashev, A., Aleksandrova, T.: Degree evaluation of grinding on fractional composition at destruction of polymineral raw materials. In: IMPC 2018 – 29th International Mineral Processing Congress, pp. 474–480 (2019)
Alexandrova, T.N.: Key directions in processing carbonaceous rocks. Zapiski Gornogo instituta 220, 568–572 (2016). https://doi.org/10.18454/pmi.2016.4.568
Aleksandrova, T.N., Arustamyan, K.M., Romanenko, S.A.: The mathematical analysis methods application in estimation of the international practice of copper-zinc and pyritic-polymetallic ores selective flotation. Obogashchenie Rud 5(371), 21–27 (2017)
Zimin, A.V., Arustamyan, M.A., Solovyova, L.M.: Classification of technological schemes of flotation of pyritic copper and copper-zinc ores. Gorny J. 11, 28–33 (2012)
Abdullin, A.A., Bespaev, H.A., Votsalevsky, E.S.: Deposits of Lead and Zinc in Kazakhstan. Almaty (1997)
Sveshnikov, G.B.: ElectroChemical Processes in Sulfide Deposits. Leningrad University Press, Leningrad (1967)
Titov, D.V.: The use of geophysical methods for evaluating the technological properties of ores of Pyrrhic-polymetallic deposits. Proc. Tomsk Polytechn. Univ. 4(309), 40–47 (2006)
Romanenko, S.A., Ushakov, E.K.: Development of technological typification of copper-zinc pyrrhotite-containing ores on the example of the Prior Deposit. In: Materials of the XXIV International Scientific and Technical Conference Scientific Bases and Practice of Processing of Ores and Technogenic Raw Materials, pp. 66–71. Yekaterinburg (2019)
Romanenko, S.A.: Effectiveness of multi-sensor ionometry systems and neural network modeling methods application in flotation processes laboratory studies. Obogashchenie Rud 1, 18–22 (2013)
Heikkinen, S., Mashevsky, G.N.: Algorithmic base for controlling the flotation process. Ore Dressing 6, 32–37 (2005)
Kohonen, T.: Samoorganizuyushchiyesya Karty: Adaptivnyye i Intellektualnyye Sistemy (Self-organizing Maps: Adaptive and Intelligent Systems). BINOM. Laboratoriya znaniy, Moscow (2010)
Mashevskiy, G.N., Romanenko, S.A.: Copper-pyrite ores flotation cleaning cycle mathematical model. Obogashchenie Rud 4, 27–33 (2014)
Mashevskiy, G.N., Petrov, A.V., Romanenko, S.A., Sufyanov, F.S.: Development of ore types processing classification principles on the basis of flotation process parameters control and neural network modeling. Obogashchenie Rud 4, 36–42 (2012)
Acknowledgement
The research was carried out under the grant received from Russian Foundation of Fundamental Research № 20-55-12002.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ushakov, E., Aleksandrova, T., Romashev, A. (2021). Neural Network Modeling Methods in the Analysis of the Processing Plant’s Indicators. In: Murgul, V., Pukhkal, V. (eds) International Scientific Conference Energy Management of Municipal Facilities and Sustainable Energy Technologies EMMFT 2019. EMMFT 2019. Advances in Intelligent Systems and Computing, vol 1259. Springer, Cham. https://doi.org/10.1007/978-3-030-57453-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-57453-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57452-9
Online ISBN: 978-3-030-57453-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)