International Journal of Applied Electromagnetics and Mechanics

In computational electromagnetism there are manyfold advantages when using machine learning methods, because no mathematical formulation is required to solve the direct problem for given input geometry. Moreover, thanks to the inherent bidirectionality of a convolutional neural network, it can be trained to identify the geometry giving rise to the prescribed output field. All this puts the ground for the neural meta-modeling of fields, in spite of different levels of cost and accuracy. In the paper it is shown how CNNs can be trained to solve problems of optimal shape synthesis, with training data sets based on finite-element analyses of electric and magnetic fields. In particular, a concept of multi-fidelity model makes it possible to control both prediction accuracy and computational cost. The shape design of a MEMS design and the TEAM workshop problem 35 are considered as the case studies.

The simulation of electrical machines at the first design stage requires efficient methods to characterize among other properties its vibrational behavior. Particularly when considering both designed and parasitic geometrical modifications, magnetic circuit calculations of large-dimensioned machines by finite-element methods (FEM) are cumbersome. Semi-analytical approaches by means of conformal mapping are therefore useful to estimate the impact of several effects, such as asymmetric stator laminations, rotor pole shapes and air gap imperfections. No-load operation is studied and the presented approach is validated by FEM simulations. The aim of this work is to study force excitations by the magnetic air gap field in salient multi-pole synchronous generators deviating from ideal and symmetrical geometrical conditions by using conformal maps.

This paper presents a novel approach to the efficiency improvement of permanent magnet synchronous motor using gravitational search algorithm as an optimization tool. The gravitational search algorithm (GSA) is a recently developed meta-heuristic optimization algorithm, which so far has proven to be quite suitable for solving power engineering optimization problems. The aim of this research work is to implement this novel optimization algorithm for the efficiency improvement of permanent magnet synchronous motor, where the objective function in the optimization process is the efficiency of the investigated motor. Comparative analysis of the initial and a number of optimized solutions of the motor model is performed.

This paper refers to a new resilient cyber-physical machine learning-based system that enables the generation of high-resolution tomographic images. The research object was a model of a tank filled with tap water. Using electrical impedance tomography (EIT) with 16 electrodes, the possibility of identifying inclusions inside the reservoir was investigated. A two-stage hybrid approach was proposed. In the first stage, three independent models were trained for the Elastic Net, Artificial Neural Networks (ANN) and Support Vector Machine (SVM) methods. In the second stage, a k-Nearest Neighbors (kNN) classification model was trained, that optimizes tomographic reconstructions by selecting the best method for each pixel, taking into account the specificity of a given measurement vector. Research has shown that applying the new concept results in a higher reconstruction quality than other methods used singly. It should be emphasized that our research is not intended to develop a new homogenous machine learning method. Instead, the goal is to invent an innovative, original, and flexible way to simultaneously use multiple machine learning methods for image optimization in industrial electrical impedance tomography.

The paper presents 3D-FEA results of electromagnetic torque characteristics of a Field Control Axial Flux Permanent Magnet Machine (FCAFPMM) obtained for different pole shapes. The influence of the angular span of iron and permanent magnet poles on the cogging torque performance has been analysed at different excitations of an additional stator winding.

In the paper an original approach to efficiency map optimal synthesis is presented. A permanent magnet motor, working as controlled AC motor of synchronous type (PMSM), is selected as a case study. The first target of this research is to derive a lumped-parameter model of the motor (low-fidelity model), validated by magnetic field analysis (high-fidelity model). In turn, the end target is these two models application in a cost-effective optimisation procedures, where the goal is to identify the motor geometry maximizing the map area which is encompassed by a prescribed value for the motor efficiency.

Vector magnetic properties of various electrical steel sheets have been investigated by using a vector magnetic property measurement apparatus to select a magnetic material suitable as a motor core material. However, a magnetic material with a higher saturation magnetization than an electrical steel sheet is useful for increasing torque of a motor. Therefore, a permendur with higher saturation magnetization than an electrical steel sheet is selected as a measurement sample. It is known that a permendur does not have magnetic anisotropy. In this paper, vector magnetic properties of two kinds of permendurs made by VACUUMSCHMELZE (VAC) and Hitachi Metals are measured. Moreover, maximum magnetic field intensities and core losses of two kinds of permendurs to an inclination angle of magnetic flux density vector locus from rolling direction are evaluated for investigation of those magnetic anisotropies. As a result, differences of vector magnetic properties of two kinds of permendurs are revealed.

The research aimed to develop an optimal way of using known machine learning techniques in electrical impedance tomography (EIT) of flood embankments. The innovative approach is based on the smart use of many machine learning techniques to allow the optimal selection of one of these techniques for each pixel of the tomographic image. An additional advantage of the presented concept is that selecting the optimal method for each pixel depends on the measurement set of a given case. This fact makes the method flexible and enables the automation of dyke monitoring using cyber-physical systems. Several machine learning methods were used during the research, including Elastic Net, Support Vector Machine, and Artificial Neural Networks. The comparison of the new concept with popular methods showed that thanks to pixel-oriented ensemble learning, the reconstructions obtained with the new approach are much better than those obtained with typical machine learning methods.

Grain Oriented Electrical Steel (GOES) have better performance in terms of permeability and iron losses compared to conventional Fe-Si 3% Non-Oriented Grains Electrical Steel (NOES), particularly when it is magnetized in the rolling direction. This paper presents a concentrated winding radial flux permanent magnets synchronous machine (PMSM) equipped with teeth made of GOES sheet. The goal is to assess the suitability of the use of GOES sheets to improve the efficiency of electric motors. This work is based on the comparison of the performances (Joule losses, iron losses, losses in the permanent magnets and efficiency) of two iso-geometric motors: a reference motor made of NOES sheets and a motor with GOES sheet teeth, at iso-torque and over the operating range (at constant torque and flux weakening). The comparison is made using a finite element software application considering the magnetic anisotropy of the GOES sheets.

In this work, a novel superconducting (SC) inductor topology for an axial flux synchronous machine is presented and tested. The proposed device combines HTS YBaCuO bulks and coils supplied with DC current to create a variable air gap flux density distribution. In fact, the two SC bulks modulate and redirect the flux lines produced by the coil thanks to their magnetic field shielding property. This results in a periodic space variation of the axial component of the flux density. A 3D electromagnetic modeling based on a finite element solution is developed to demonstrate the relevance of using the magnetic shielding properties of SC bulks. In order to verify the screening properties of the SC bulk, a prototype of the proposed inductor was constructed and tested in the laboratory.

A significant advance has been made in medical diagnosis through introduction of mathematical theories and artificial intelligence (AI). The main theme of this research work is to presents a novel arteries unblocks sensor model based on the principle of the propagation electromagnetic waves. Sensor model based on an electromagnetic waves transmit shock waves through guide wires to specifically cross calcified and fibrotic tissues in the arterial vascular system while leaving intact the elastic wall of healthy vessels. This sensor model has been implemented in a designed system model in an electric circuit inside stockings. The observed results are presented to illustrate the performances of his ability to move strange objects which represents the suspended cholesterol. The results expressed by the distance traveled by the stone under the influence of electromagnetic waves transmitted in water showed that the application of this principle for a period of time allows the opening of blockage of the arteries which demonstrates the performance of the proposed sensor model and the entire system. For health state monitoring: severity and localization coordinates of the arteries unblocks by incorporating artificial intelligence tools are studied in detail in second part for better obstruction treatment.

The aim of this article is the mathematical modeling of the car wheel with an energy harvester. The car wheel will be represented as a 3-DoF robotic kinematic chain. The Matlab program has been used to simulate the movement of the car wheel and the movement of the electromagnetic energy harvester located on the tire of the wheel. Simulation of the movement of the energy harvesting element allows us to compute the energy harvested in such a system.

Throughout the past few decades, the share of distributed generation in power systems has increased continuously. This increasing trend coupled with the continuous demand growth in the distribution systems started a shift towards heavier reactive power consumption. The latter paved the way for the development of advanced operational and planning algorithms for power distribution systems. Following these trends in the distribution systems, the distribution grids must be developed with greater reliability and flexibility, i.e. smart grids. Consequently, the implementation of smart technologies instead of traditional ones should be considered wherever feasible. This paper presents an approach for optimal placement, economic sizing, and operation point search of distribution static VAR compensator (D-SVC) using an exhaustive analytical search. The proposed algorithm introduces quite a few novelties, unique, superior, and repetitive results presented on a distribution test system IEEE 69.

The Epstein frame is a well-known standardized system used to characterize soft magnetic materials. The users of this device usually consider that all the strips of a same grade placed in the frame are homogeneous, and they do not take into account the potential impact of the heterogeneity of the sheets on the quality of the characteristics deduced from the measurements. The aim of this paper is to quantify the individual heterogeneity of Epstein samples of the same FeSi grade (BH curve, losses, permeability), and to analyze, by both experimental and numerical ways, if the layout of the sheets can impact the Epstein core losses.