An example of artificial neural network model for predicting air pollution has been presented. The research was conducted in Serbia, the Moravica District, on the territory of two municipalities (Lučani and Ivanjica) and the town Čačak. The level of air pollution was classified by a neural network model according to the input data: municipality, site, year, levels of soot, sulfur dioxide (SO2), nitrogen dioxide (NO2) and particulate matter. The model was evaluated using a lift chart and a root mean square error (RMSE) has been determined, whose value was 0.0635. A multilayer perceptron has also been created and trained with a back propagation algorithm. The neural network was tested with the data mining extensions (DMX) queries. The results have been obtained for air pollution based on new input data that can be used to predict the level of pollution in future if new measurements are carried out. A web-based application was designed for displaying the results.

This paper presents a new way of implementing a computer as a teaching tool in the teaching module “Rotating Magnetic Field in AC machines.” Software for simulation, measurement, and visualization of the rotating magnetic field using three‐axis hall sensor was created in the form of remote experiment. After students’ evaluation, it was found that remote experiments ensure better achievement of students regarding this particular topic, while also contributing to better quality of teaching rotating magnetic fields in the subject of electrical machines.

No abstract

The aim of this paper is to describe a procedure and experimental setup for calibration of AC induction magnetometer. The paper presents an overview of the previous research and results of measurement of magnetic flux density inside largediameter multilayer solenoid. This solenoid is magnetising coil of the magnetometer. The paper also describes a system of five smaller coils of the magnetometer which are placed inside the large solenoid. Three small coils are pickup coils, accompanied with two compensation coils, of which one is an empty coil for magnetic field measurement. The experimental results of calibration of this coil system have been presented. A proper discussion of all the results presented has been also given in the paper.

The heating of an ethylene-propylene rubber (EPR) insulated cable installed in a vertical polyvinyl chloride (PVC) pipe is analysed in this paper. In particular, this paper considers the heating of an EPR cable used to energize a submersible water pump and analyses the upper part of the well where the space between the EPR cable and the inner surface of the PVC pipe is filled with air. The temperatures of the cable’s surface are determined analytically, and then such temperature values are validated numerically by using the finite element method (FEM) in COMSOL. In addition to these calculations, experiments are performed on a physical model representing the part of the well between the static water level and the solid concrete cover of the well. The percentage deviation of the calculated values for the cable’s surface temperature from the measured ones at different load currents ranges from 1.47% to 4.63%. After the experimental validation of the calculated values for the cable’s surface temperature, an analytic expression (i.e. correlation) that defines the dependence of that temperature on the load current and the pipe’s inner surface temperature is derived. Finally, an analytic expression for the cable load current as a function of the cable’s surface temperature and the pipe’s inner surface temperature is also derived, which can be further used to determine the ampacity of any power cable for known service conditions.