A METHOD OF DATA INTERPRETATION IN SEISMICITY AND DEFORMATION MONITORING IN UNDERGROUND MINING IN TERMS OF THE KUKISVUMCHORR DEPOSIT OF APATIT COMPANY

The objective of this study is to develop an assessment method for geomechanical monitoring in rocks in terms of the Kirov Mine, Apatit company. Prediction of basic parameters of rock mass stress state, as any other problem arising in data bulk handling, depends both on selection of the number and type of approximating functions. Despite a collection of formal quality metrics and estimation techniques, the approximating models and criteria should be selected individually for each specific array of data. Underground mining alters natural stress state in rocks. This article sets forth algorithms of machine learning in applied problems of geomechanics and geo-information science. Correlation of mine operating schedules and seismic activity data with deformation time-series obtained from deformation monitoring can produce a functional relationship for prediction of strain distribution in rock mass. The article describes the results of the computational experiment which illustrates feasibility and advisability of using machine learning algorithms in solving of geomechanical problems.


For citation:  Gospodarikov A. P., Morozov K. V., Revin I. E. О методе обработки данных сейсмического и деформационного мониторинга при ведении подземных горных работ на примере Кикусвумчоррского месторождения АО «Апатит». MIAB. Mining Inf. Anal. Bull. 2019;(8):157168. [In Russ]. DOI: 10.25018/0236-1493-2019-08-0-157-168.

Keywords

Algorithm, gradient boosting, monitoring, Khibiny apatite–nepheline deposits, geoinformation science.

Issue number: 8
Year: 2019
ISBN: 0236-1493
UDK: 622.83.551.252
DOI: 10.25018/0236-1493-2019-08-0-157-168
Authors: Gospodarikov A. P., Morozov K. V., Revin I. E.

About authors: A.P. Gospodarikov, Dr. Sci. (Eng.), Professor, K.V. Morozov, Cand. Sci. (Eng.), I.E. Revin1, Graduate Student, e-mail: revine@4inbox.ru, Saint-Petersburg Mining University, 199106, Saint-Petersburg, Russia. Corresponding author: I.E. Revin, e-mail: revine@inbox.ru.

REFERENCES:

1. Protosenya A. G., Verbilo P. E. Study of compressive strength of fractured rock mass. Zapiski Gornogo instituta. 2017. Vol. 223, pp. 51—57. [In Russ].

2. Ridgeway G. The state of boosting. Computing Science and Statistics. 1999, Vol. 31. Pp. 172—181.

3. Mishulina O. A. Statisticheskiy analiz i obrabotka vremennykh ryadov [Statistical analysis and processing of time series], Moscow, MIFI, 2004, 180 p.

4. Holt Charles C. Forecasting trends and seasonal by exponentially weighted averages. International Journal of Forecasting. January—March 2004. 20 (1): 5—10.

5. Friedman J. H. Greedy Function Approximation: a Gradient Boosting Machine. Technical Report. Dept. of Statistics, Stanford University, 1999.

6. Mason L., Baxter J., Bartlett P. L., Frean Marcus. Boosting Algorithms as Gradient Descent (PDF). In S. A. Solla and T.K. Leen and K. Müller. Advances in Neural Information Processing Systems 12. MIT Press. 1999. pp. 512—518.

7. Brown R. G., Meyer R. F. The fundamental theorum of exponential smoothing. Oper. Res, 1961. Vol. 9. no 5.

8. Muller A., Guido S. Introduction to Machine Learning with Python: A Guide for Data Scientist. Moscow: O'Reilly Media, 2017. p. 392.

9. Silen D., Meysman A., Ali M. Osnovy Data Science i Big Data. Python i nauka o dannykh [Data Science and Big Data basics. Python and data science], Saint-Petersburg, Piter, 2017, 336 p.

10. Brown Robert Goodell Smoothing Forecasting and Prediction of Discrete Time Series. Englewood Cliffs, NJ: Prentice-Hall. 1963.

11. Lukashin Yu. P. Adaptivnye metody kratkosrochnogo prognozirovaniya vremennykh ryadov [Adaptive methods of short-term time series forecasting], Moscow, Finansy i statistika, 2003, 416 p.

12. Podkorytova O. A., Sokolov M. V. Analiz vremennykh ryadov: uchebnoe posobie dlya bakalavriata i magistratury. 2-e izd. [Time-series analysis: textbook for undergraduate and graduate programs. 2nd edition], Moscow, Izd-vo Yurayt, 2018, 267 p.

13. Box G., Jenkins G., Reinsel G., Ljung G. Time series analysis: forecasting and control. John Wiley & Sons, 2015.

14. Aravkin A., Burke J. V. , Ljung L., Lozano A., Pillonetto G. Generalized kalman smoothing: Modeling and algorithms. Survey to appear in Automatica, 2017.

15. Aravkin A., Abrami A., Kim Y. Time series using exponential smoothing cells. Stat ML, 2017.

Our partners

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.