A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics

• URL: http://arxiv.org/abs/2608.02965v1
• Date: Mon, 03 Aug 2026 23:59:02 GMT
• Title: A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics
• Abstract summary: This work proposes a compact material-specific neural model with B-H energy-consistency regularization for transient magnetization prediction.<n>PI-HNO achieves a compact trade-off between sequence accuracy and B(t)-H(t) energy consistency, with the mean and 95th percentile B(t)-H(t) energy consistency errors of 1.92% and 7.60%, respectively.
• Score: 2.938272719942146
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Magnetic components in high-frequency, high-power-density converters are increasingly driven by non-sinusoidal flux-density waveforms with fast transitions, minor-loop operation, dc bias, and temperature variation. Under these conditions, steady-state core-loss formulas and single-valued material curves cannot fully capture transient magnetization responses. This work proposes the Physics-Informed Hybrid Neural Operator (PI-HNO), a compact material-specific neural model with B-H energy-consistency regularization for core-loss-oriented transient magnetization prediction. Given the measured B(t)-H(t) history, the input B(t) series over the prediction interval and operating-condition information, PI-HNO predicts the H(t) series and the corresponding reconstructed B-H trajectory. The model integrates a local recurrent branch for boundary-state representation and rate-dependent response evolution with a Preisach-inspired global branch that extracts waveform-level hysteresis context. Evaluation on the MagNetX transient database using material-specific models for 14 ferrite materials demonstrates that PI-HNO achieves a compact trade-off between sequence accuracy and B(t)-H(t) energy consistency, with the mean and 95th percentile B(t)-H(t) energy consistency errors of 1.92% and 7.60%, respectively, using only 4777 trainable parameters per model. Ablation studies further demonstrate that the local, global, and energy-aware regularized components provide distinct contributions to transient magnetization prediction.

Related papers

• Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields [9.34545560117171]
  Energy-based models (EBMs) are a natural fit since energies compose additively, which enables augmenting physics information during inference.<n>We show in this work that flow matching models with a potential-induced velocity yield an explicit energy at all transport times.<n>Access to the energy function from a trained model serves three roles: energy-corrected data generation, energy as a scoring function for out-of-distribution (OOD) detection, and energy compositional posterior sampling for inverse problems.
  arXiv  Detail & Related papers  (2026-08-18T16:53:08Z)
• Precision quantum simulation of magnon spectra and interactions [94.30337065819249]
  We show high-precision simulation of both linear and non-linear response functions in a 2D XY spin-1/2 magnet using an analog-digital superconducting processor of up to 97 qubits.<n>Our results reveal stark variations in magnon decay rates across the Brillouin zone, with enhancement near van Hove singularities and suppression for edge-localized modes.
  arXiv  Detail & Related papers  (2026-07-14T22:11:22Z)
• Hybrid Neural Ordinary Differential Equations for Data-Efficient Polymerization Modeling with Incomplete Kinetics [42.58292307702424]
  We propose a hybrid Neural Ordinary Differential Equation framework for data-efficient modeling of free-radical polymerization.<n>The hybrid NODE is evaluated against a discrete-time feedforward neural network and a purely data-driven NODE under sparse data conditions.<n>In a generalization scenario with noisy data and unseen operating conditions, the hybrid NODE achieves an RMSE of 0.013, compared to 0.31 for the data-driven NODE and 0.68 for the discrete-time model.
  arXiv  Detail & Related papers  (2026-06-01T12:10:48Z)
• Application of parametric Shallow Recurrent Decoder Network to magnetohydrodynamic flows in liquid metal blankets of fusion reactors [0.0]
  This study investigates a fully data-driven framework for MHD state reconstruction.<n>SHallow REcurrent Decoder (SHRED) is a neural network architecture designed to reconstruct the full-temporal state.<n>SHRED achieves high reconstruction accuracy, generalization, and to magnetic field intensities, orientations, and temporal evolutions not seen during training.
  arXiv  Detail & Related papers  (2026-04-02T15:12:24Z)
• Orbital Transformers for Predicting Wavefunctions in Time-Dependent Density Functional Theory [45.322818939044645]
  We aim to learn wavefunctions simulated by time-dependent density functional theory (TDDFT)<n>In real-time TDDFT, the electronic wavefunctions of a molecule evolve over time in response to an external excitation.<n>We propose OrbEvo, which learns to evolve the full electronic wavefunction coefficients across time steps.
  arXiv  Detail & Related papers  (2026-03-03T20:34:05Z)
• Physics Aware Neural Networks: Denoising for Magnetic Navigation [3.624059602945058]
  Airborne systems face a key challenge in extracting geomagnetic field data: the aircraft itself induces magnetic noise.<n>We propose a framework based on two physics-based constraints: divergence-free vector field and E(3)equivariance.<n>Experiments show that embedding these constraints significantly improves predictive accuracy and physical plausibility, outperforming classical deep learning approaches.
  arXiv  Detail & Related papers  (2026-02-14T09:23:57Z)
• A saturation-absorption rubidium magnetometer with multilevel optical Bloch-equation modeling for intermediate-to-high fields [0.054175212412726444]
  We present SASHMAG, an atomic sensor designed for precision magnetic-field measurements.<n>The sensor operates in the hyperfine Paschen-Back regime, where the hyperfine and Zeeman interactions decouple.<n>To interpret the resulting spectra in this strongly field-dependent regime, we developed a comprehensive multilevel optical Bloch-equation model.
  arXiv  Detail & Related papers  (2026-01-14T03:29:40Z)
• Design and Optimization of Spin Dynamics in Ge Quantum Dots: g-Factor Modulation, Dephasing Sweet Spots, and Phonon-Induced Relaxation [0.0]
  We present a three-dimensional study of gate-defined quantum dot hole spin qubits in strained Si$_0.2$Ge$_0.8$/Ge heterostructures.<n>We quantify the impact of device size and gate bias on wavefunction localization, electric-field-induced g-factor modulation, and identify "sweet spots" in vertical electric field where g-factor sensitivity to charge noise is minimized.
  arXiv  Detail & Related papers  (2025-09-12T22:39:03Z)
• Electron-Electron Interactions in Device Simulation via Non-equilibrium Green's Functions and the GW Approximation [71.63026504030766]
  electron-electron (e-e) interactions must be explicitly incorporated in quantum transport simulation.<n>This study is the first one reporting large-scale atomistic quantum transport simulations of nano-devices under non-equilibrium conditions.
  arXiv  Detail & Related papers  (2024-12-17T15:05:33Z)
• Transport properties and quantum phase transitions in one-dimensional superconductor-ferromagnetic insulator heterostructures [44.99833362998488]
  We propose a one-dimensional electronic nanodevice inspired in recently fabricated semiconductor-superconductor-ferromagnetic insulator hybrids. We show that the device can be tuned across spin- and fermion parity-changing QPTs by adjusting the FMI layer length orange and/or by applying a global backgate voltage. Our findings suggest that these effects are experimentally accessible and offer a robust platform for studying quantum phase transitions in hybrid nanowires.
  arXiv  Detail & Related papers  (2024-10-18T22:25:50Z)
• Predictions of Electromotive Force of Magnetic Shape Memory Alloy (MSMA) Using Constitutive Model and Generalized Regression Neural Network [0.0]
  Ferromagnetic shape memory alloys (MSMAs) can exhibit the shape memory effect due to an applied magnetic field at room temperature. This work introduced a new feature to the existing macroscale magneto-mechanical model for Ni-Mn-Ga single crystal. Model predictions are compared to experimental data collected on a Ni-Mn-Ga single crystal.
  arXiv  Detail & Related papers  (2022-06-08T06:38:33Z)
• Rotating Majorana Zero Modes in a disk geometry [75.34254292381189]
  We study the manipulation of Majorana zero modes in a thin disk made from a $p$-wave superconductor. We analyze the second-order topological corner modes that arise when an in-plane magnetic field is applied. We show that oscillations persist even in the adiabatic phase because of a frequency independent coupling between zero modes and excited states.
  arXiv  Detail & Related papers  (2021-09-08T11:18:50Z)
• Controlled coherent dynamics of [VO(TPP)], a prototype molecular nuclear qudit with an electronic ancilla [50.002949299918136]
  We show that [VO(TPP)] (vanadyl tetraphenylporphyrinate) is a promising system suitable to implement quantum computation algorithms. It embeds an electronic spin 1/2 coupled through hyperfine interaction to a nuclear spin 7/2, both characterized by remarkable coherence.
  arXiv  Detail & Related papers  (2021-03-15T21:38:41Z)
• Spin Entanglement and Magnetic Competition via Long-range Interactions in Spinor Quantum Optical Lattices [62.997667081978825]
  We study the effects of cavity mediated long range magnetic interactions and optical lattices in ultracold matter. We find that global interactions modify the underlying magnetic character of the system while introducing competition scenarios. These allow new alternatives toward the design of robust mechanisms for quantum information purposes.
  arXiv  Detail & Related papers  (2020-11-16T08:03:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.