Journal of Mining Science

, Volume 47, Issue 4, pp 493–505 | Cite as

Application of a hybrid method of machine learning for description and on-line estimation of methane hazard in mine workings

  • M. Sikora
  • Z. Krzystanek
  • B. Bojko
  • K. Śpiechowicz
Mine Aerogasdynamics

Abstract

The paper presents application of a hybrid method of methane hazard prediction in exploited mine workings in coal mines. For prediction, the authors used so-called local linear models, the number of which is defined in an adaptive way, and the model of time series prediction ARIMA. The prediction task consists in generating the maximum predicted methane concentration value in a certain time horizon. This forecast is then used to define a methane hazard level by means of a fuzzy system of the Mamdami type. Another important issue covered by the paper is processing of row measurement data to an acceptable form using analytical method and adaptation of the model to changing environmental conditions. The experimental part of the paper presents results of data analysis completed for two longwalls.

Keywords

Longwall methane prediction models hybrid method rules-based classification systems tree of local linear models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bojko, B., The Analysis of Acquired Measurements of Methane Concentration in Mine Galeries-Selected Examples, Proc. of the 3rd School of Mine Ventilation, Zakopane, 2004 (in Polish).Google Scholar
  2. 2.
    Bojko, B., Dynamics of Methane Content in Mine Workings, Extended Abstract of PhD Dissertation, Polish Academy of Sciences, Strata Mechanics Institute, Cracow, 2004 (in Polish).Google Scholar
  3. 3.
    Nakayama, S., Uchino, K., and Inoue, M., Simulation of Methane Gas Distribution at a Heading Face, Journal of the Mining and Materials Processing Institute of Japan, 1998, vol. 114, no. 4.Google Scholar
  4. 4.
    Ushakov, K.Z., Gas Dynamics of Shafts, Moscow: Nauka, 1984.Google Scholar
  5. 5.
    Krause, E. and Łukowicz, K., Dynamic Prediction of Absolute Methane Emissions to Extraction Panels, Proc. of the 29th Int. Conf. of Safety in Mines Research Institutes, 2001, Szczyrk, Poland, vol. 1 (in Polish).Google Scholar
  6. 6.
    Kurnosow, W.G. and Krasik, J.L., Methane Hazard and Its Monitoring, Proc. of the 7th Int. Mine Ventilation Congress, 2001, Cracow, Poland.Google Scholar
  7. 7.
    Dixon, W.D., A Statistical Analysis of Monitored Data for Methane Prediction, Extended Abstract of PhD Dissertation, University of Nottingham, Dept. of Mining Engineering, 1992.Google Scholar
  8. 8.
    Firganek, B., Stochastic Model of Methane Emission in Longwall Faces, Proc. of the 29th Int. Conf. of Safety in Mines Research Institutes, 2001, Szczyrk, Poland, vol. 1 (in Polish).Google Scholar
  9. 9.
    Wasilewski, S., Analysis of the Measurement Signals of Ventilation Processes, Mining Automation Bulletin, 1986, no. 31 (in Polish).Google Scholar
  10. 10.
    Sikora, M. and Sikora, B., Application of Machine Learning for Prediction of Methane Concentration in a Coal-Mine, Archives of Mining Sciences, 2006, vol. 51,issue 4.Google Scholar
  11. 11.
    Sikora, M., Krzystanek, Z., Bojko, B., and Spiechowicz, K., Hybrid Adaptative System of Gas Concentration Prediction in Hard-Coal Mines, Proc. of the 19th Int. Conf. on Systems Engineering, IEEE Computer Society (CPS), 2008, Las Vegas, Nevada, USA.Google Scholar
  12. 12.
    Krzystanek, Z., Dylong, A., and Wojtas, P., Monitoring of Environmental Parameters in Coal Mine-The SMP-NT System, Mechanizacja i Automatyzacja Górnictwa, 2004, no. 9.Google Scholar
  13. 13.
    Gralewski, K. and Krzystanek, Z., New Features of the SMP/NT System for Environmental Hazard Monitoring in Coal Mines, Mechanizacja i Automatyzacja Górnictwa, 2004, no. 9.Google Scholar
  14. 14.
    Box, G. E. P. and Jenkins, G.M., Time Series Analysis: Forecasting and Control, New Jersey: Prentice Hall, 3th edition, 2004.Google Scholar
  15. 15.
    Czogała, E. and Łęski, J. Fuzzy and Neuro-Fuzzy Intelligent Systems, Studies in Fuzziness and Soft Computing, 2000, vol. 47, Springer-Verlag Company.Google Scholar
  16. 16.
    Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J., Classification and Regression Trees, Wadsworth, Belmont CA, 1994.Google Scholar
  17. 17.
    Quinlan, J.R., Learning with Continuous Classes, Proc. Int. Conf. on Artificial Intelligence (AI`92), Singapore, World Scientific, 1992.Google Scholar
  18. 18.
    Quinlan, J.R., Combining Instance-Based Learning and Model-Based Learning, Proc of the 10th Int. Conf. on Machine Learning (ML-93), 1993.Google Scholar
  19. 19.
    Knuth, D.E., The Art of Computer Programming, vol. 3, Sorting and Searching, Addison-Wesley, 1998.Google Scholar
  20. 20.
    Quinlan, J.R., C4.5 Programs for Machine Learning, Morgan Kaufman Publishers, San Mateo, California, 1992.Google Scholar
  21. 21.
    Witten, I.H and Frank, E., Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufman, 2005.Google Scholar
  22. 22.
    Grychowski, T., Hazard Assessment Based on Fuzzy Logic, Archives of Mining Sciences, 2008, vol. 53, no. 4Google Scholar
  23. 23.
    Yager, R.R. and Filev, D.P., Essential of Fuzzy Modelling and Control, John Wiley & Sons, Inc, 2004.Google Scholar
  24. 24.
    Statistica 8.0 (www.statsoft.com).
  25. 25.
    Matlab 2009 (www.mathworks.com).
  26. 26.
    Oh, S.K., Pedrycz, W., and Park, H.S., Rules Based Multi-FNN Identification with the Aid of Evolutionary Fuzzy Granulation, Knowledge-Based Systems, vol. 17, 2004.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2011

Authors and Affiliations

  • M. Sikora
    • 1
  • Z. Krzystanek
    • 1
  • B. Bojko
    • 1
  • K. Śpiechowicz
    • 1
  1. 1.Silesian University of TechnologyGliwicePoland

Personalised recommendations