This paper presents mathematical models enabling the calculation of the distribution and patterns of methane inflow to the air stream in a longwall seam being exploited and spoil on a longwall conveyor, taking into account the variability of shearer and conveyor operation and simulation results of the mining team using the Ventgraph-Plus software. In the research, an experiment was employed to observe changes in air parameters, in particular air velocity and methane concentration in the Cw-4 longwall area in seam 364/2 at KWK Budryk, during different phases of shearer operation in the area of the mining wall in methane hazard conditions. Presented is the method of data recording during the experiment which included records from the mine’s system for automatic gasometry, records from a wireless system of eight methane sensors installed in the end part of the longwall and additionally from nine methane anemometers located across the longwall on a grid. Synchronous data records obtained from these three independent sources were compared against the recording the operating condition of the shearer and haulage machines at the longwall in various phases of their operation (cleaning, cutting). The results of the multipoint system measurements made it possible to determine the volume of air and methane flow across the longwall working, and, consequently, to calculate the correction coefficients for determining the volume of air and methane from measurements of local air velocity and methane concentration. An attempt was made to determine the methane inflow from a unit of the longwall body area and the unit of spoil length on conveyors depending on the mining rate. The Cw-4 longwall ventilation was simulated using the data measured and calculated from measurements and the simulation results were discussed.
The aim of the study was to evaluate the possibility of applying different methods of data mining to model the inflow of sewage into the municipal sewage treatment plant. Prediction models were elaborated using methods of support vector machines (SVM), random forests (RF), k-nearest neighbour (k-NN) and of Kernel regression (K). Data consisted of the time series of daily rainfalls, water level measurements in the clarified sewage recipient and the wastewater inflow into the Rzeszow city plant. Results indicate that the best models with one input delayed by 1 day were obtained using the k-NN method while the worst with the K method. For the models with two input variables and one explanatory one the smallest errors were obtained if model inputs were sewage inflow and rainfall data delayed by 1 day and the best fit is provided using RF method while the worst with the K method. In the case of models with three inputs and two explanatory variables, the best results were reported for the SVM and the worst for the K method. In the most of the modelling runs the smallest prediction errors are obtained using the SVM method and the biggest ones with the K method. In the case of the simplest model with one input delayed by 1 day the best results are provided using k-NN method and by the models with two inputs in two modelling runs the RF method appeared as the best.