Neural oscillators for magnetic hysteresis modeling
This work addresses hysteresis modeling for magnetic materials, where traditional methods are inadequate, but it appears incremental as it builds on existing neural oscillator and phenomenological approaches.
The authors tackled the problem of modeling magnetic hysteresis, which is crucial for understanding and optimizing systems, by developing HystRNN, an ordinary differential equation-based recurrent neural network. The results show that HystRNN can generalize to untrained regions, such as first-order reversal curves and minor loops, outperforming traditional RNN-based methods in capturing complex patterns.
Hysteresis is a ubiquitous phenomenon in science and engineering; its modeling and identification are crucial for understanding and optimizing the behavior of various systems. We develop an ordinary differential equation-based recurrent neural network (RNN) approach to model and quantify the hysteresis, which manifests itself in sequentiality and history-dependence. Our neural oscillator, HystRNN, draws inspiration from coupled-oscillatory RNN and phenomenological hysteresis models to update the hidden states. The performance of HystRNN is evaluated to predict generalized scenarios, involving first-order reversal curves and minor loops. The findings show the ability of HystRNN to generalize its behavior to previously untrained regions, an essential feature that hysteresis models must have. This research highlights the advantage of neural oscillators over the traditional RNN-based methods in capturing complex hysteresis patterns in magnetic materials, where traditional rate-dependent methods are inadequate to capture intrinsic nonlinearity.