Geodesic measurements of mining area deformations indicate that their description fails to be regular,
as opposed to what the predictions based on the relationships of the geometric-integral theory suggest.
The Knothe theory, most commonly applied in that case, considers such parameters as the exploitation
coefficient a and the angle of the main influences range tgβ, describing the geomechanical properties of the
medium, as well as the mining conditions. The study shows that the values of the parameters a = 0.8 and
tgβ = 2.0, most commonly adopted for the prediction of surface deformation, are not entirely adequate in
describing each and every mining situation in the analysed rock mass. Therefore, the paper aims to propose
methodology for determining the value of exploitation coefficient a, which allows to predict the values
of surface subsidence caused by underground coal mining with roof caving, depending on geological and
mining conditions. The characteristics of the analysed areas show that the following factors affect surface
subsidence: thickness of overburden, type of overburden strata, type of Carboniferous strata, rock mass
disturbance and depth of exploitation. These factors may allow to determine the exploitation coefficient a,
used in the Knothe theory for surface deformation prediction.
The article attempts to transfer information from the Point Nuisance Method (PNM) used in Poland in the issue of protection of buildings in mining areas, to the system of inference based on Bayesian formalism. For this purpose, all possible combinations occurring in PNM were selected. The number of numerically generated patterns was 6,718,464 cases. Then, based on Python package Scikit-Learn, a classification model was created in the form of the Naïve Bayes Classifier (NBC). The effectiveness of three methods used to build this type of decision-support system was analysed, from which the Categorical Multinomial Naive Bayes (CMNB) approach was finally selected. With the created classifier, its properties were verified in terms of quality of classify and generalization. For this purpose a general approach was used, analysing the level of accuracy of the model in relation to training and teaching data, and detailed, based on the analysis of the confusion matrix. Additionally, the operation of the created classifier was simulated to determine the optimal Laplace smoothing parameter α. The article ends with conclusions from the carried out calculations, in which an attempt was made to answer the question concerning potential reasons for incorrect classification of the created CMNB model. The discussion ends with a reference to the planned research, in which, among other things, the use of more complex Bayesian belief networks (BBN) is planned.
The paper presents a new geotechnical solution indicating a possibility of effective building structures protection. The presented solutions enable minimization of negative effects of underground mining operations. Results of numerical modelling have been presented for an example of design of preventive ditches reducing the influence of mining operations on the ground surface. To minimize the mining damage or to reduce its reach it is reasonable to look for technical solutions, which would enable effective protection of building structures. So far authors concentrated primarily on the development of building structure protection methods to minimize the damage caused by the underground mining. The application of geotechnical methods, which could protect building structures against the mining damage, was not considered so far in scientific papers. It should be noticed that relatively few publications are directly related to those issues and there are no practical examples of effective geotechnical protection. This paper presents a geotechnical solution indicating a possibility of effective protection of building structures. The presented solutions enable minimization of negative effects of underground mining operations. Results of numerical modelling have been presented for an example of design of preventive ditches reducing the influence of mining operations on the ground surface. The calculations were carried out in the Abaqus software, based on the finite element method.