Jasna Radulović

Feedforward neural network and adaptive network-based fuzzy inference system in study of power lines

Over the past several decades, concerns have been raised over the possibility that the exposure to extremely low frequency electromagnetic fields from power lines may have harmful effects on human and living organisms. This paper presents novel approach based on the use of both feedforward neural network (FNN) and adaptive network-based fuzzy inference system (ANFIS) to estimate electric and magnetic fields around an overhead power transmission lines. An FNN and ANFIS used to simulate this problem were trained using the results derived from the previous research. It is shown that proposed approach ensures satisfactory accuracy and can be a very efficient tool and useful alternative for such investigations.

Maximizing performances of variable tilt flat-plate solar collectors for Belgrade (Serbia)

In Serbia, for heating of domestic hot water (DHW) it is customary to use electricity. As around 70% of electricity is produced by using low quality coal with high greenhouse emission, it is beneficial to environment to use solar energy by flat-plate solar collectors for heating of DHW in a solar DHW system (SDHWS). The SDHWS with variable tilt flat-plate solar collectors placed in north-south direction at roofs of houses are investigated for their optimal operation in Belgrade, Serbia. The investigated variable-tilt collectors annually take 2 tilts, 4 tilts, and 12 tilts. The used weather data are from the meteorological station. These investigations use three computer codes: EnergyPlus, GenOpt, and Hooke-Jeeves search algorithm. For different solar collectors, the investigations revile their optimum tilts that maximize the solar fraction by the SDHWS. Then, the solar fraction and avoided fossil energy by the SDHWS are maximized. In addition, the deficit in the solar fraction is estimated when the solar ...

Prediction of magnetic field near power lines by normalized radial basis function network

Over the past several decades, concerns have been raised over the possibility that the exposure to extremely low frequency electromagnetic fields from power lines may have harmful effects on human and living organisms. This work involved the computation of the magnetic field generated by 110kV overhead power lines using a normalized radial basis function (NRBF) network. Training of the evolving NRBF network is achieved by using the data generated from the numerical simulation based on Charge Simulation method (CSM). Then, NRBF has been used to determine the magnetic field distribution in a new geometry differing from the geometries used for training. These test results show that proposed NRBF network can be used as useful tool to calculate the magnetic fields from power lines, alternative to the conventional methods.

Application of RBF neural network and ANFIS for electromagnetic field prediction around the power lines

This paper presents novel approach based on the use of both radial basis function (RBF) network and adaptive network-based fuzzy inference system (ANFIS) to estimate electric and magnetic fields around an overhead power transmission lines. An RBF and ANFIS used to simulate this problem were trained using the results derived from the previous research. It is shown that proposed approach ensures satisfactory accuracy and can be a very efficient tool and useful alternative for such investigations.

Optimization of photovoltaics panels area at Serbian zero-net energy building

In this study, the possibilities to decrease energy consumption of a residential building in Serbian conditions are analyzed. The building uses electricity for space heating system, heating of domestic hot water, lighting, and for other electric equipment. The electrical energy is generated by photovoltaics (PV) system and it may be consumed by the building or may be fed-in to the electricity grid. The major aim of the optimization of PV area is to determine the avoided electricity from the grid (avoided exergy), and to minimize the consumption of primary energy. The residential buildings with variable thermal insulation thickness, hot water consumption, life time, and PVs embodied energy are investigated, in order to achieve zero-net energy building or positive-net energy building. The buildings are presented by a mathematical model, in EnergyPlus environment. Open Studio plug-in in Google SketchUp was used for building virtual design, Hooke-Jeeves algorithm for optimization, and GENOPT software for sof...

Modeling of radiation dose of human head during CT scanning using neural networks

In this study the authors present the method for determination of exposure dose on human head during computer tomography (CT) scanning procedure. The method is based on the use of the feed-forward neural network (FFNN) model to predict the exposure dose on human head. The neural network with Levenberg-Marquardt learning is constructed. The training data are obtained using the Monte Carlo method simulation. The simulation is performed by generating random numbers for determination of photon direction and for quantification of interaction between X-ray photon and head tissue. Spectra of photon energy is used for 3DCT scanner, X-ray tube Model XRS-125-7K-P. The FFNN predicted values are in accordance with the values obtained by the simulation with correlation coefficient around 0.99.