. We present a novel method for using Neural Networks (NNs) for finding solutions to a class of Partial Di ff erential Equations (PDEs). Our method builds on recent advances in Neural Radiance Field research (NeRFs) and allows for a NN to converge to a PDE solution orders of magnitude faster than classic Physically Informed Neural Network (PINNs) approaches.
Paper
References (10)
09The flux distribution in the airgap has the characteristic v-shape, with higher density at the corners of the iron – seeFig 4
10The flux “cuts corners” – the flux density in high close to the inner corners of the iron core and very low at the outer cornerssee Fig 3