Solving 1D non‐linear magneto quasi‐static Maxwell's equations using neural networks

Abstract

Electromagnetics (EM) can be described, together with the constitutive laws, by four PDEs, called Maxwell's equations. "Quasi-static" approximations emerge from neglecting particular couplings of electric and magnetic field related quantities. In case of slowly time varying fields, if inductive and resistive effects have to be considered, whereas capacitive effects can be neglected, the magneto quasi-static (MQS) approximation applies. The solution of the MQS Maxwell's equations, traditionally obtained with finite differences and elements methods, is crucial in modelling EM devices. In this paper, the applicability of an unsupervised deep learning model is studied in order to solve MQS Maxwell's equations, in both frequency and time domain. In this framework, a straightforward way to model hysteretic and anhysteretic non-linearity is shown. The introduced technique is used for the field analysis in the place of the classical finite elements in two applications: on the one hand, the B-H curve inverse determination of AISI 4140, on the other, the simulation of an induction heating process. Finally, since many of the commercial FEM packages do not allow modelling hysteresis, it is shown how the present approach could be further adopted for the inverse magnetic properties identification of new magnetic flux concentrators for induction applications. Recently, deep learning emerges as a powerful technique in many applications, including computer vision, speech recognition, natural language process, and bioinformatics. There is This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Physics-Informed Neural Networks for Magnetostatic Problems on Axisymmetric Transformer Geometries

“…In the field of electromagnetics, PINNs have already been applied to predict the magnetic flux distribution based on a given magnetization [8], and in a hybrid setup combined with data for simple electro-and magneto-static problems [9]. More recent results demonstrate their potential for the design of a single coil or choke [10], or coil systems used for induction heating and hardening [11], [12]. The aforementioned examples use Fully Connected Neural Networks (FCNNs) as basic architecture to approximate the physics and allow only limited degrees of freedom in their geometric setups.…”

Physics-informed Neural Networks for the Resolution of Analysis Problems in Electromagnetics

“…In turn, [12] predicted the time evolution field in transient electrodynamics making use of an encoder-recurrent-decoder architecture. PINNs have also been used in magnetostatics and magneto-quasi-statics [13][14][15][16].…”

“…It can be noted that in most works (e.g., [2,4,[10][11][12][13][14]), PINNs do not take system parameters (i.e., geometries, field sources, material properties) as an input and therefore they must be retrained, eventually taking advantage of transfer learning whenever the system parameters in the model must be changed. However, a few exceptions are reported in [8], [9], [15] where, once trained, PINNs could provide the solution of a class of direct field problems.…”

Artificial neural network-based method for overhead lines magnetic flux density estimation

“…The magnetic field plays an essential role in various applications in industry, science, medicine and everyday life. Therefore, various methods are being developed for determining the value and distribution of the magnetic field in space, from analytical and numerical calculation methods to field measurements or device prototype measurements [5][6][7][8][9]. In recent years, the possibility of applying artificial intelligence in electromagnetism has been intensively considered in order to facilitate these processes.…”