With the continuing global pandemic of coronavirus (COVID-19) sickness, it is critical to seek diagnostic approaches that are both effective and rapid to limit the number of people infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The results of recent research suggest that radiological images include important information related to COVID-19 and other chest diseases. As a result, the use of deep learning (DL) to assist in the automated diagnosis of chest diseases may prove useful as a diagnostic tool in the future. In this study, we propose a novel fusion model of hand-crafted features with deep convolutional neural networks (DCNNs) for classifying ten different chest diseases such as COVID-19, lung cancer (LC), atelectasis (ATE), consolidation lung (COL), tuberculosis (TB), pneumothorax (PNET), edema (EDE), pneumonia (PNEU), pleural thickening (PLT), and normal using chest X-rays (CXR). The method that has been suggested is split down into three distinct parts. The first step involves utilizing the Info-MGAN network to perform segmentation on the raw CXR data to construct lung images of ten different chest diseases. In the second step, the segmented lung images are fed into a novel pipeline that extracts discriminatory features by using hand-crafted techniques such as SURF and ORB, and then these extracted features are fused to the trained DCNNs. At last, various machine learning (ML) models have been used as the last layer of the DCNN models for the classification of chest diseases. Comparison is made between the performance of various proposed architectures for classification, all of which integrate DCNNs, key point extraction methods, and ML models. We were able to attain a classification accuracy of 98.20% for testing by utilizing the VGG-19 model with a softmax layer in conjunction with the ORB technique. Screening for COVID-19 and other lung ailments can be accomplished using the method that has been proposed. The robustness of the model was further confirmed by statistical analyses of the datasets using McNemar’s and ANOVA tests respectively.

The rapid advancement of electric vehicle technology towards environmentally friendly transportation emphasizes the necessity dynamic wireless charging. However, challenges such as the initial charging infrastructure cost, power transfer efficiency, and output power pulsation pose significant limitations to dynamic wireless charging. Overcoming these challenges requires optimizing the design of various functional elements in dynamic charging, including the magnetic coupler, spacing between couplers, high-frequency inverter, and compensators. Despite the nonlinear relationships among these elements, obtaining mathematical relations proves cumbersome. This article proposes an effective machine learning approach to achieve the optimal design of the charging track, considering the cross-coupling effect. The algorithm not only aids in estimating the infrastructure cost of the charging lane but also predicts optimal design parameters using trained data. The machine learning approach, which predicts optimal design parameters with a trained dataset, is more efficient with reduced duration than conventional FEA tools and stochastic methods. The learning algorithms consider variables such as core structure, cross-coupling effect, and coil flux pipe length. Simulation and experimental prototype validation for a 3.3 kW system demonstrated an impressive efficiency of 93.21%.

The paper deals with impact of electric asymmetry of rotor coil on induction machine on the time course of electromagnetic flow inside the machine as well as any change to the course of electromagnetic leakage flux on the surface of machine frame and in its immediate vicinity. Familiarity with dependency between the course of flux and specific failures of the machine helps with measuring of the leakage flux by simple means, with records to be utilised as a value easy to obtain and measure to proceed with non-contact diagnostics of a specific machine failure. The paper further refers to results of mathematical modelling to show the indication of a specific failure, including its comparison with measurement.

Contact connections in electrical machines and apparatus are important elements in the whole power supply network and a high level of reliability is expected there. Contact resistance is a fundamental criterion in the design of an electrical contact or contact system. The contact resistance should be as low as possible to minimize losses due to the current passage and the related heating of the contact connection. The value of the contact resistance depends on the material used, the value of the applied force, the type of contact, and, last but not least, the quality of the surface and chemical layers. In this paper, an initial diagnosis of the contact material is performed based on the determination of the sample’s specific resistivity by the four-wire method and the evaluation of the measurement uncertainty. The work is followed by the design of a testing device that uses crossed bars to measure the change in contact resistance as a function of the magnitude of the applied force. An analysis of the sample mounting method is performed here using FEM simulations of the current field and shows the interaction between the holder and the sample in terms of current line transfer. The proposed system is then used for experimental measurements of the material-dependent coefficient K_C for verification of existing or newly developed materials in electrical engineering, where the values of the K_C coefficient are not known. Finally, the paper also deals with the measurement of fritting voltage for individual contact pairs having surface quality corresponding to brushing.

A short-circuit tripping device is an integral part of a miniature low-voltage circuit breaker. As far as its design is concerned, the release mechanism comprises a metal case with a moving armature and a compression spring; the armature is further surrounded with winding (coil) made of copper wire. Short-circuit current flowing through the protected circuit brings the release armature in motion and the force produced acts on the mechanism lock to arm the breaker. This paper will present application of electromagnetic FEM analysis to calculate the static and dynamic characteristics of force acting in short-circuit release of a circuit breaker. The both analysis are compared to the real measurement of armature moving by the help of high-speed camera.

This paper focuses on description of the operation principle inherent to the Adams' electric motor-generator fitted with permanent magnets made of rare earth (NdFeB). For checking of the basic design we have used the FEM electromagnetic simulation made by Ansys Workbench and Ansys Maxwell. The Adams' motor generator is basically assembled with slight deviations from the original patent with respect to the stator magnetic circuit design. The resultant speed-torque characteristics obtained by measurement and the input power values have been processed to determine the machine's efficiency.