Method of complex copper–zinc ore typification using neural network models

The article discusses variability of feed stock of a processing plant. Currently it is essential to classify ore meant for treatment. Heterogeneity of the processing feed stock affects the process of beneficiation. It is found that classical regression models fail to provide the wanted reliability of cross impact in pairs of factors due to the multi-factor and nonlinear nature of the flotation object. The geological and mineralogical features of test ore are analyzed using neural network modeling. The test subject was copper–zinc ore. The multi-factor nature of the test ore was analyzed on a model developed using a Kohonen neural network. The neural network model revealed six basic clusters. Each class features similar values of yield. Using the obtained data, the Kohonen self-organizing maps were constructed for the visual interpretation of the results. The technological performance dependence on the type of feed batch is demonstrated. It is required to develop a high-automated flotation technology to ensure enhanced recovery of metals.

Keywords: neural networks, metal recovery, flotation, modeling, raw material typification.
For citation:

Aleksandrova T. N., Ushakov E. K., Orlova A. V. Method of complex copper–zinc ore typification using neural network models. MIAB. Mining Inf. Anal. Bull. 2020;(5):140-147. [In Russ]. DOI: 10.25018/0236-1493-2020-5-0-140-147.


This work was supported by the Russian Science Foundation (project no. 19-17-00096).

Issue number: 5
Year: 2020
Page number: 140-147
ISBN: 0236-1493
UDK: 622.765-52
DOI: 10.25018/0236-1493-2020-5-0-140-147
Article receipt date: 02.02.2020
Date of review receipt: 28.02.2020
Date of the editorial board′s decision on the article′s publishing: 20.04.2020
About authors:

T.N. Aleksandrova1, Dr. Sci. (Eng.), Professor, Head of Chair,
E.K. Ushakov1, Graduate Student,
A.V. Orlova1, Graduate Student,
1 Saint-Petersburg Mining University, 199106, Saint-Petersburg, Russia.

For contacts:

E.K. Ushakov, e-mail:


1. Lomonosov G. G., Turygina N. A. Influence of the material composition of ores on processing indicators. Gornyy informatsionno-analiticheskiy byulleten’. 2010, no 2, pp. 314— 320.

2. Bicak O. A technique to determine ore variability in a sulphide ore. Minerals Engineering. 2019. Vol. 142, Article 105927. DOI: 10.1016/j.mineng.2019.105927.

3. Lvov V., Sishchuk J., Chitalov L. Intensification of Bond ball mill work index test through various methods. 17th International Multidisciplinary Scientific GeoConference & EXPO SGEM. 2017. Vol. 17, Issue 11, pp. 857—864. DOI: 10.5593/sgem2017/11/S04.109.

4. Sadeghi M., Hodouin D., Bazin C. Mineral processing plant data reconciliation including mineral mass balance constraints. Minerals Engineering. 2018. Vol. 123, Pp. 117—127. DOI: 10.1016/j.mineng.2018.04.023.

5. Beriashvili A. T., Pikulina V. M. A new approach to solving the problem of variable copper recovery on the example of the Zhezkazgan ore field. Obogashchenie rud. 2018, no 5, pp. 40—44.

6. Taguta J., McFadzean B., O`Connor C. The relationship between the flotation behaviour of a mineral and its surface energy properties using calorimetry. Minerals Engineering. 2019. Vol. 143, Article 105954. DOI: 10.1016/j.mineng.2019.105954.

7. Liu J., Long H., Corin K. C. A study of the effect of grinding environment on the flotation of two copper sulphide ores. Minerals Engineering. 2018. Vol. 122, Pp. 339—345. DOI: 10.1016/j.mineng.2018.03.031.

8. Romanenko S.A., Ushakov E. K. Development of classification ore for copper-zink pyrite-pirrotite priorskoe deposit. Materialy XXIV mezhdunarodnoy nauchno-tekhnicheskoy konferentsii «Nauchnye osnovy i praktika pererabotki rud i tekhnogennogo syr'ya», 9—12 aprelya 2019 g. [Proceedings of the XXIV international scientific and technical conference "Scientific bases and practice of processing ores and technogenic raw materials" April 9—12, 2019. Ekaterinburg, 2019, pp. 66—71.

9. 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. 2017, no 5 (371), pp. 21—27.

10. Kheikkinen S., Mashevskiy G. N. Algorithmic framework for the control of the flotation process. Obogashchenie rud. 2005, no 6, pp. 32—37.

11. Aleksandrova T., Romanenko S., Arastumian K. Electrochemistry research of preparation slurry before intermediate flotation for sulphide-polimetallic ores. 17th International Multidisciplinary Scientific GeoConference & EXPO SGEM. 2017. Vol. 17. No 11. Pp. 841—848.

12. Kokhonen T. Assotsiativnaya pamyat' [Associative memory], Moscow, Mir, 1980. 239 p.

13. Kokhonen T. Samoorganizuyushchiesya karty: Adaptivnye i intellektual'nye sistemy [Self-organizing maps: Adaptive and intelligent systems], Moscow, BINOM. Laboratoriya znaniy, 2010. 655 p.

14. Romanenko S.A. Effectiveness of multi-sensor ionometry systems and neural network modeling methods application in flotation processes laboratory studies. Obogashchenie rud. 2013, no 1, pp. 18—22.

15. Elektronnyy uchebnik po statistike [Electronic textbook on statistics] / StatSoft, available at: (accessed 20.07.2018). [In Russ].

Подписка на рассылку

Раз в месяц Вы будете получать информацию о новом номере журнала, новых книгах издательства, а также о конференциях, форумах и других профессиональных мероприятиях.