Selim Koroglu

An approach to the calculation of multilayer magnetic shielding using artificial neural network

Abstract The electromagnetic interference has many undesired effects to the office equipments and the performance of technological devices. Therefore, electrical devices should have field protection mechanism against magnetic fields. The shielding mechanism prevents external magnetic field emitted from the device to the vicinity area. This work attempts to apply artificial neural network in order to estimate shielded magnetic field for multilayer shielding application. The multilayer magnetic shielding performances of cylindrical shaped ferromagnetic shields under extremely low frequency are investigated. For this purpose, three different ferromagnetic materials in cylindrical shape are chosen for magnetic shielding. The shielding performances of these materials are measured and a selected set of data is used to train and test an artificial neural network. The proposed neural network model achieves an intelligent decision for the shielded magnetic field level based on distance, unshielded magnetic field value, number of shield layer and skin-depth of the shield.

Comparison of analytical, finite element and neural network methods to study magnetic shielding

Abstract Three types of methods are studied to calculate the shielding efficiency of a cylindrical ferromagnetic shield in Fe–Si steel, i.e. an analytical method, a finite element method and a neural network method. The methods take into account nonlinear hysteretic behaviour in the shield. All of the methods are compared with each other and with measurements: the shielding factor is computed and measured for several shield radii, thicknesses, field amplitudes and frequencies. The mean absolute error rates are calculated for AM, FEM and NN to be 9.16%, 6.45% and 5.54%, respectively. The analytical model is very fast and accurate for materials with mild nonlinearity. In case of highly nonlinear material and a strongly non-uniform field distribution in the shield, the modeling of the nonlinear behavior in the analytical model is not accurate. The FEM is very accurate for all considered shielding configurations if the mesh density is well chosen, but its evaluation time is high. The neural network has the disadvantage that it should be trained. It is, however, a fast method with the additional advantage that it can be used without any knowledge of the shield geometry and material properties if the training is based on measurements.

ELECTROMAGNETIC LOSSES IN MAGNETIC SHIELDS FOR BURIED HIGH VOLTAGE CABLES

The electromagnetic losses and shielding e-ciency of shields for a buried three phase high voltage cable are studied for several shielding conflgurations. The shields are U-shaped gutters covered with plates, and the power cables are positioned either in trefoil or in ∞at conflguration. The shielding e-ciency and the losses are compared for shields with the same geometry but several shielding materials: aluminium, and two ferromagnetic steel grades. The numerical models are validated with experimental results. From the experiments, it is observed that the average reducing factor of the ∞ux density is about 7 with the ∞at cable conflguration while the average reducing factor of the ∞ux density is about 5 with the trefoil cable conflguration. But the power losses in the DX52 shield for trefoil conflguration is about 40% lower compared to the ∞at conflguration. In case of trefoil conflguration, the losses are 12.14W/m per meter length in the shield for a current of 750A. Next to the shield material and the cable conflguration, the paper investigates the in∞uence of several parameters on both the shielding e-ciency and the losses: the size of the shield, the current amplitude in the cable and the thickness of the shield.

A neural network based estimation method for magnetic shielding at extremely low frequencies

The attenuation of extremely low-frequency magnetic fields is important in reducing electromagnetic interference on electric and electronic equipment. In this paper, an innovative method is presented for shielded magnetic field level estimation at power frequencies by a neural network (NN) technique which uses experimental data. The utilized NN is applied to cylindrical shields (transformer-grade iron, copper, and aluminum) in various shield arrangements. Using the developed NN model, the mitigated magnetic field of multilayered shields is measured and evaluated to predict the magnetic field at any distance apart from the magnetic source. The NN, which is based on a feed-forward neural network (FNN), is trained with scaled conjugate gradient, gradient descent with momentum and adaptive learning back propagation, and Levenberg-Marquardt algorithms to compute the shielded magnetic field. Results have shown that the developed FNN trained with the Levenberg-Marquardt algorithm is better than the other training algorithms in predicting the shielded magnetic field value accurately even in the presence of various shield arrangements.

Integrated Model of Power Electronics, Electric Motor, and Gearbox for a Light EV

This study presents a model of a drivetrain for an integrated design of a light electric vehicle (EV). For the drivetrain of each front wheel of the single-person, battery-powered EV tricycle consists of a battery, an inverter, and an outer rotor permanent magnet synchronous motor (PMSM), which is connected to an in-wheel gearbox. The efficiency of the inverter, motor, and gearbox is analyzed over the New European Driving Cycle. To calculate the losses and efficiency of the PMSM, the power electronics in the inverter and gearbox are used. The analytical models provide a fast, but less accurate result, useful for optimization purposes. To accurately predict the efficiency of the PMSM, a finite element model is used. The models are validated by test setups. Correspondingly, a good agreement between the measurements and the calculated results is achieved. A parameter study is performed to investigate the influence of the detailed component parameters (i.e., outer rotor radius, gear ratio, and number of pole pairs and stator slots) on the average efficiency of the drivetrain.

Experimental performance investigation of double-layer shields at power frequency magnetic shielding

Double-layer shields have received attention in magnetic shielding at extremely low frequency. Also, cylindrical shape is one of shielding structures widely used in industry. In this study, cylindrical shaped shields with commonly available and inexpensive materials used for power frequency magnetic field shielding. The magnetic shielding performances are investigated experimentally for single and double-layer shields at power frequencies. The aim of this work is to extend the discussion in the area of shielding performance of the double-layer shields.

Optimal design and implementation of a drivetrain for an ultra-light electric vehicle

This paper presents an integrated design of a drivetrain for a single-person ultra-light electric vehicle (ULEV). To calculate losses and efficiency of the inverter, the permanent magnet synchronous machines (PMSMs) and the gearbox, parameterised analytical models are used. For the gearbox - which has a single gear ratio - the studied parameters are the gear ratio, the number of stages, the number of teeth and the module of each spur gear combination. The novelty of the paper is that it learns how the total average efficiency and the total mass of the drivetrain depend on the gear ratio, on the number of stages in the gearbox, on the motor parameters and on the chosen several driving cycles including the new European driving cycle (NEDC). On the basis of the presented results, it is possible to choose the right configuration of power electronics, PMSM and gearbox in order to have a good trade-off between high efficiency and low mass.

Influence of contact resistance on shielding efficiency of shielding gutters for HV cables

Shielding of buried three phase high voltage cables can be done by placing the cables in conducting ferromagnetic U-shaped gutters covered by plates. In case of a perfect electrical contact between adjacent gutters and between adjacent cover plates, the induced currents in the shield efficiently reduce the field generated in the vicinity of the cables. However, as a perfect contact cannot be guaranteed, it is useful to quantify the effect of a bad electrical contact on the shielding performance. From 2D FEM, 3D FEM and experiments, it is observed that a bad contact does not influence significantly the shielding if the axial length of the plates is relatively long compared to their other dimensions.