ARTIFICIAL INTELLIGENCE IN MODELLING OF SURFACE SUBSIDENCE DUE TO WATER WITHDRAWAL IN UNDERGROUND MINING

References: 15th International Multidisciplinary Scientific GeoConference SGEM 2015, www.sgem.org, SGEM2015 Conference Proceedings, ISBN 978-619-7105-34-6 / ISSN 1314-2704, June 18-24, 2015, Book2 Vol. 1, 503-510 pp

ABSTRACT
In the article discusses the issues that accompany changes in drainage work in underground mining. The deformation associated with the void created in the subsurface are well described by the different calculation methods. Whereas the changes due to drainage process depend on many factors and mathematical description is difficult in those cases. In previous studies, the author proposed to use a new approach to the problem of predicting changes in drainage which are tools of artificial intelligence. One of them is a multi-layer perceptron network (MLP), which was used in the calculation. In the present article compares the results from analytical models, which are used in open pit mining to modelling surface subsidence, with responses from a trained neural network. The whole research was performed on the example of one of the Polish underground coal mine. Analytical models have been adapted to local mining and geological conditions. The article shows the advantages and disadvantages of each method and indicated directions for further work on the use of artificial intelligence in modeling drainage changes in underground mining.

Keywords: subsidence, drainage, neural network, MLP, modeling