Learning from examples is the golden rule in the construction of behavioral models using neural networks (NN). When NN are trained to simulate physical equations, the tight enforcement of such laws is not guaranteed by the training process. In addition, there can be situations in which providing enough examples for a reliable training can be difficult, if not impossible. To alleviate these drawbacks of NN, recently a class of NN incorporating physical behavior has been proposed. Such NN are called “physics-informed neural networks” (PINN). In this contribution, their application to direct electromagnetic (EM) problems will be presented, and a formulation able to minimize an integral error will be introduced.
Physics-informed Neural Networks for the Resolution of Analysis Problems in Electromagnetics
Barmada S.;Tucci M.
2023-01-01
Abstract
Learning from examples is the golden rule in the construction of behavioral models using neural networks (NN). When NN are trained to simulate physical equations, the tight enforcement of such laws is not guaranteed by the training process. In addition, there can be situations in which providing enough examples for a reliable training can be difficult, if not impossible. To alleviate these drawbacks of NN, recently a class of NN incorporating physical behavior has been proposed. Such NN are called “physics-informed neural networks” (PINN). In this contribution, their application to direct electromagnetic (EM) problems will be presented, and a formulation able to minimize an integral error will be introduced.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
