Physical and Chemical Geotechnologies

Purpose

Analysis of the influence of geological and mining technical factors on the drift stability to determine the reliable and effective support of workings during the service period.

Methodology

Investigation of the features of the excavation work during the coal seam mining. Conducting computational experiments to determine the stress- strain state of a rock mass and the construction of a support system.

Findings

Analysis of the impact of mining and geological and mining factors on the stability of underground workings throughout the life of the mine. The stress-strain state, pressure influence and conditions of workings support depending on mining and technological parameters are investigated. The artificial neural network was constructed and trained for regression analysis. Regression analysis using the construction and training of an artificial neural network on the basis of the data obtained to determine the degree of influence of each specific parameter on the stability of working. Experiment results are established the zones of high pressure in the sides of the workings (especially the left side) had the greatest influence on the workings stability. The influence of the reference pressure zone on the left side of the working is up to 82% of the total. The trained neural network can be successfully used in the future when designing excavations in this area. They contain the researches, which were conducted within the project GP – 497, financed by Ministry of Education and Science of Ukraine.

Keywords: artificial neural networks, underground mining, workings support

References

1. Sidorenko A. and Ivanov V. 2016. Underground mining of multiple seam of coal. ARPN Journal of Engineering and Applied Sciences. Vol. 11, No 7, pp. 4448 – 4454.
2. Fomychov V. & Sotskov V. (2018). Determination of parameters of non- uniform fractured rock massif in computing experiment. Dniprop. Univer. bulletin, Geology, geography., 26(1), 26-32
3. Małkowski, P., Niedbalski, Z., Majcherczyk, T., 2016. Roadway design efficiency indices for hard coal mines. Acta Geodynamica et Geomaterialia. No13(2), pp. 201 – 211
4. Lefik M. 2013. Some aspects of application of artificial neural network for numerical modeling in civil engineering. Bulletin of the polish academy of sciences. Vol. 61, No. 1, 39 – 50.
5. Hejmanowski R., Witkowski W. 2015. Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage. Journal of sustainable mining, 14, pp. 101 – 107
6. Malashkevych, D., Sotskov V., Medyanyk V. & Prykhodchenko D. (2018). Integrated Evaluation of the Worked-Out Area Partial Backfill Effect of Stress-Strain State of Coal-Bearing Rock Mass. Solid State Phenomena, (277), 213-220.
7. Li Xuwei, Nemcik, J., Aziz, N., Mirza, A. and Rasekh H., 2015. Modelling of Rebar and Cable Bolt Behaviour in Tension/Shear. 15th Coal Operators' Conference, pp. 175 – 181.
8. Mahdevari, S., Shahriar, K., Sharifzadeh, M., & Tannant, D. D. 2017. Stability prediction of gate roadways in longwall mining using artificial neural networks. Neural Computing and Applications, 28(11), 3537-3555.
9. Petlovanyi, M. V., Lozynskyi, V. H., Saik, P. B., & Sai, K. S. (2018). Modern experience of low-coal seams underground mining in Ukraine. International Journal of Mining Science and Technology. doi:10.1016/j.ijmst.2018.05.014
10. Sotskov V., Podvyhina O., Dereviahina N. & Malashkevych D. (2018). Substantiating the criteria for applying selective excavation of coal deposits in the Western Donbass. Dniprop. Univer. bulletin, Geology, geography., 26(1), 158-164.