Search results

This paper aims to investigate the approach combine the deep learning (DL) and finite element method for the magneto-thermal coupled problem.

To achieve the DL of electrical device with the hypothesis of a small dataset, with ground truth data obtained from the FEM analysis, U-net, a highly efficient convolutional neural network (CNN) is used to extract hidden features and trained in a supervised manner to predict the magneto-thermal coupled analysis results for different topologies. Using part of the FEM results as training samples, the DL model obtained from effective off-line training can be used to predict the distribution of the magnetic field and temperature field of other cases.

The possibility and feasibility of the proposed approach are investigated by discussing the influence of various network parameters, in particular, the four most important factors are training sample size, learning rate, batch size and optimization algorithm respectively. It is shown that DL based on U-net can be used as an efficiency tool in multi-physics analysis and achieve good performance with only small datasets.

It is shown that DL based on U-net can be used as an efficiency tool in multi-physics analysis and achieve good performance with only small datasets.

The purpose of this paper is to propose some a posteriori residual error estimators (REEs)to evaluate the accuracy of the finite element method for quasi-static electromagnetic problems with mixed boundary conditions. Both classical magnetodynamic A-ϕ and T-Ω formulations in harmonic case are analysed. As an example of application the estimated error maps of an electromagnetic system are studied. At last, a remeshing process is done according to the estimated error maps.

The paper proposes to analyze the efficiency of numerical REEs in the case of magnetodynamic harmonic formulations. The deal is to determine the areas where it is necessary to improve the mesh. Moreover the error estimators are applied for structures with mixed boundary conditions.

The studied application shows the possibilities of the residual error estimators in the case of electromagnetic structures. The comparison of the remeshed show the improvement of the obtained solution when the authors compare with a reference one.

The paper provides some interesting results in the case of magnetodynamic harmonic formulations in terms of potentials. Both classical formulations are studied.

The paper provides some informations to develop the proposed formulations in the software using finite element method.

The paper deals with the possibility to improve the determination of the meshes in the analysis of electromagnetic structure with the finite element method. The proposed method can be a good solution to obtain an optimal mesh for a given numerical error.

The paper proposes some elements of solution for the numerical analysis of electromagnetic structures. More particularly the results can be used to determine the good meshes of the finite element method.

In this paper, the aim is to propose a residual‐based error estimator to evaluate the numerical error induced by the computation of the electromagnetic systems using a finite element method in the case of the harmonic A‐φ formulation.

The residual based error estimator used in this paper verifies the mathematical property of global and local error estimation (reliability and efficiency).

This estimator used is based on the evaluation of quantities weakly verified in the case of harmonic A‐φ formulation.

In this paper, it is shown that the proposed estimator, based on the mathematical developments, is hardness in the case of the typical applications.